query
stringclasses 259
values | prequel
listlengths 0
30
| sequel
listlengths 0
30
| during
listlengths 0
30
| metadata
dict | num_of_frames
int64 8
8
| frame_captions
listlengths 8
8
| video_id
stringlengths 6
45
| frame2video_caption
stringlengths 194
2.16k
|
|---|---|---|---|---|---|---|---|---|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=t8lY-rjy7-Y",
"video_description": "9월 12일, 경주에서는 역대 최대 규모인 5.8 지진이 일어났다. 지진으로 서울과 수도권까지 전국이 흔들렸고, 이로 인해 전화와 카카오톡도 모두 먹통이었다. 정부는 지진 발생 9분이 지나서야 긴급재난문자를 발송했고 이마저도 서울과 수도권 지역 국민들은 문자를 받지 못했다. #경주 #지진 #재난문자",
"video_id": "t8lY-rjy7-Y"
}
| 8
|
[
"A group of people in a classroom appears to be engaged in a lively discussion or activity. Several individuals are standing and interacting with each other, some leaning over desks, while others are moving around. The desks are arranged in rows, with papers and books on them, indicating an academic setting. The participants are dressed in casual and semi-formal attire, suggesting a school or educational environment.",
"The current frame depicts a store aisle lined with shelves stocked with various boxed products, likely in a retail or warehouse setting. The shelves are neatly organized, with multiple rows of boxes visible. The text overlay on the image reads \"제목 7시간 44분 경주 남남서쪽 9km 부근 첫 지진 발생\" which translates to \"Title 7 hours 44 minutes, first earthquake occurs near 9km southwest of Gyeongju\". This indicates that the video may be part of a news report or documentation of an event related to the earthquake in Gyeongju. There are no people visible in the frame, and the focus is on the organized shelves and boxed products, suggesting a calm and orderly environment possibly captured before or after the earthquake event.",
"The current frame shows a scene of destruction and chaos, likely a result of the earthquake mentioned in the previous frame's text. The ground is littered with broken pieces of red and blue bricks, indicating damage to structures or paving. A yellow caution tape is stretched across the area, suggesting that this is a restricted zone due to the aftermath of the earthquake. The text overlay on the image reads \"밤 8시 8분 경주에서 첫 지진 인명 피해 발생\" which translates to \"At 8:08 PM, the first earthquake-related casualties occur in Gyeongju\". This confirms that the event is indeed related to the earthquake, and the visual elements support the narrative of an immediate and severe impact on the area.",
"The current frame shows a black and white night vision scene, likely captured by a surveillance camera, depicting a person in a white outfit lying on a bed or cot, seemingly in distress or unconscious. The setting appears to be indoors, with a fan visible on the left side of the frame. The text overlay reads \"서울과 수도권까지 전국이 흔들려,\" which translates to \"The whole country, including Seoul and the metropolitan area, is shaken.\" This suggests that the earthquake's impact is widespread, affecting areas beyond the immediate vicinity of the initial event.",
"In the current frame, a woman in a white suit is speaking into a microphone. She is smiling and appears to be addressing an audience or the media. Behind her, there is a man in a dark suit, and they are both standing in front of a blue backdrop with Korean text that includes the phrase \"2시간 47분 동안 대통령과 통화하는 보이지 않아,\" which translates to \"During the 2 hours and 47 minutes, not visible while talking to the president.\" The setting suggests a formal or official event, and the woman seems to be delivering an important message or statement.",
"The woman in the white suit is now seated at a desk, speaking into a microphone. The background features a blue flag with a yellow emblem, and there is Korean text at the bottom of the screen. The setting suggests a formal or official event, and the woman seems to be delivering an important message or statement.",
"The woman in the white suit continues to be seated at the desk, speaking into the microphone. The blue flag with a yellow emblem remains in the background, and the Korean text at the bottom of the screen is still present. The scene maintains its formal and official atmosphere, indicating that the woman is still delivering her important message or statement.",
"The woman in the white suit remains seated at the desk, continuing her speech into the microphone. The blue flag with a yellow emblem is still visible in the background, maintaining the formal atmosphere. The Korean text at the bottom of the screen remains, reinforcing the context of the ongoing official statement or announcement."
] |
t8lY-rjy7-Y
|
The video depicts a series of events related to an earthquake in Gyeongju, South Korea. It begins with a classroom scene, possibly showing students discussing or learning about the earthquake, before transitioning to a store aisle, which may be part of a news report or documentation of the event. The scene then shifts to show the destruction and chaos caused by the earthquake, with broken bricks and caution tape indicating a restricted zone. A night vision scene shows a person in distress, and a subsequent frame features a woman in a white suit addressing the media, suggesting an official response to the disaster. The woman continues to deliver a statement, seated at a desk with a formal backdrop, indicating an ongoing effort to inform the public about the situation. The video captures the immediate impact of the earthquake, the official response, and the widespread effects of the disaster on the country, including Seoul and the metropolitan area.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=CXe6_CDrdB8",
"video_description": "찐♡기상청사람들 예고 없이 찾아오는 지진! 한 번 발생하면 큰 피해를 주는 지진이기에 감시하는 일은 한시도 소홀히 할 수 없습니다. 그 최전방에서... 1년 365일 24시간 지진화산 감시 및 분석 업무에 최선을 다해 신속·정확하게 알리고자 노력하는 사람이 있습니다. 지진화산 감시 및 분석 업무 9년 차... 반복되는 주간 근무와 야간 근무가 힘들긴 하지만, 누구보다 묵묵하게 자리를 지키고 있는 진득한 뚝배기 같은 지진업무의 대들보!! 지진화산 감시 업무를 담당하는 기상청 사람을 만나고 왔습니다.(^_^)v 우리나라에서 가장 강력했던 규모 5.8의 경주 지진 때 지진감시 및 분석을 수행했던 기상청 사람은 누구? 지진감시 업무를 들어올 때마다 긴장되는 기상청 사람은 누구? 국민의 안전을 누구보다 걱정하는 기상청 사람은 누구? 지진 올바로 알고 지진 발생 시 빠르게 대처하길 바라는 기상청 사람은 누구? 최근 지진 안전을 홍보해 주시는 지진희 배우님을 그 누구보다 고마워하는 기상청 사람은 누구? 만나볼까요 :) #기상청사람들 #지진화산 #행동하는파수꾼",
"video_id": "CXe6_CDrdB8"
}
| 8
|
[
"The frame shows a person seated at a desk with multiple computer monitors displaying data and graphs. The individual is working, using a keyboard and mouse, surrounded by maps and scientific charts on the desk and wall. The person is wearing a face mask, indicating a setting that may require health precautions. Text in the frame includes Korean, suggesting the location or context might be related to a Korean-speaking area.",
"The current frame shows a street scene with several people walking, including individuals in casual attire and one person in a white outfit. There is a vehicle and some signage in the background. The text in the frame is in Korean and mentions \"경주서 규모 5.8지진 발생\" which translates to \"a magnitude 5.8 earthquake occurred in Gyeongju.\" The image suggests an area affected by a significant earthquake, with the people likely reacting to or being cautious due to the seismic event.",
"The scene is set in an office environment where three individuals are gathered around a workstation. One person stands and appears to be explaining something, gesturing with their hands, while two others observe attentively. The monitors display data, and the room is equipped with multiple workstations. The text in the frame is in Korean and reads \"규모 5.1의 지진을 통보했는데\" which translates to \"an earthquake of magnitude 5.1 was reported.\" This suggests that the individuals are discussing or analyzing the recent earthquake data.",
"In the current frame, a man is standing and speaking in front of a large screen displaying various data and graphs, indicating a continuation of the discussion or analysis from the previous frame. The background screen features Korean text, including \"최대한 더 빠르게 (운영) 해야겠다\" which translates to \"we must operate more quickly,\" suggesting a focus on rapid response or efficiency. The man appears to be addressing the audience or a group of people, likely elaborating on the earthquake report or related data. His attire and the presence of a lanyard with an ID badge suggest he may be a professional or expert in the field. The overall setting remains consistent with an office or control room environment, emphasizing the importance of the data being discussed.",
"The current frame shows a person seated at a desk in what appears to be an office or control room setting. The individual is wearing a mask and is focused on multiple computer monitors displaying data, indicating they are engaged in monitoring or analyzing information. The text on the monitors is not clearly visible, but the presence of multiple screens suggests a need for extensive data tracking or management. The desk is equipped with various office supplies and devices, including a telephone and a mouse, reinforcing the professional environment. The overall scene depicts a scenario where the person is likely working on tasks related to earthquake monitoring or data analysis, consistent with the theme suggested by the previous frame's text \"최대한 더 빠르게 (운영) 해야겠다\" (\"we must operate more quickly\").",
"The current frame depicts a person standing in front of a computer screen displaying complex data charts. The individual is wearing a name badge and a watch, suggesting a professional setting. The background shows a digital display with numerous lines of data, possibly indicating real-time monitoring or analysis. The person appears to be explaining or presenting information related to the data on the screen. The text on the screen includes phrases in Korean, such as \"지진을 막고 있는 담당자의 숙명이란 생각합니다,\" which translates to \"I think it is the fate of the person responsible for preventing earthquakes.\" This suggests that the person is discussing the critical role they play in monitoring seismic activity to prevent earthquakes.",
"The current frame features a person speaking in front of a computer screen filled with data charts, likely continuing the presentation from the previous frame. The individual is dressed in professional attire, indicating a formal setting. The screen in the background displays various numerical data and graphs, possibly related to real-time seismic monitoring. The text on the screen is in Korean and includes phrases such as \"지진 안전총괄본부,\" which translates to \"Earthquake Safety Headquarters,\" suggesting the topic involves earthquake safety and monitoring. The individual appears to be providing information or instructions related to seismic activity, emphasizing the importance of their role in ensuring safety.",
"The current frame shows a close-up of a spiral-bound notebook with handwritten Korean text. The text discusses the importance of being prepared for earthquakes, emphasizing that one cannot predict when an earthquake will occur and that every day is a good time to prepare. It suggests that earthquakes are common and that individuals should be prepared, emphasizing the need for knowledge and resources to respond effectively. The hashtags at the bottom of the page highlight the urgency and relevance of earthquake safety awareness."
] |
CXe6_CDrdB8
|
A video depicting the response to a significant earthquake in Gyeongju, Korea, with a magnitude of 5.8. The event is being monitored and analyzed by professionals in an office or control room setting, where they track data and discuss the earthquake's impact. The individuals involved are likely experts in seismology or emergency response, working together to understand the situation and respond effectively. The video highlights the importance of rapid response and preparedness, with a focus on earthquake safety and monitoring. Throughout the frames, text in Korean emphasizes the need for quick action, the role of those responsible for preventing earthquakes, and the importance of being prepared for such natural disasters. The setting is professional, with individuals wearing masks, ID badges, and formal attire, indicating a serious and coordinated response to the earthquake. Overall, the video appears to be educational or informative, aiming to raise awareness about earthquake safety and the work of those involved in monitoring and responding to seismic activity.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=uF3x63vtddc",
"video_description": "\"경주 지진, 지하수는 1~2일 전에 미리 알았다\" 지난 12일과 19일 경주에서 규모 5.8을 비롯한 대형 지진이 잇따라 발생하기 하루 이틀 전 주변 지하수 수위가 크게 상승해, 향후 지진예측에 활용할 수 있다는 주장이 나왔습니다. 정상용 부경대 지구환경과학과 교수는 진앙에서 가장 가까운 경북 경주시 산내면에 있는 지하수 관측소 자료를 분석한 결과, 이 같이 밝혔습니다. 자료를 보면 지난 11일 암반 지하수 수위는 하루 사이에 무려 49㎝ 상승했고, 17일에도 39㎝나 올라갔습니다. 정 교수는 지진에 앞서 암석에 강한 압력이 가해져 지하수 수위가 많이 올라간 것으로 보인다며, 규모 4.5 이상의 지진에만 영향을 받았다고 설명했습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "uF3x63vtddc"
}
| 8
|
[
"The image shows a surveillance video capturing a nighttime scene with heavy snowfall. It is taken from an outdoor area, possibly near a patio or garden, as indicated by the presence of potted plants and a railing. A large plume of snow is being blown across the scene, suggesting strong winds. \n\nKey text in the image provides context: \"경주 지진, 지하수는 1~2일 전에 미리 알았다\" translates to \"Gyeongju earthquake, groundwater knew 1-2 days in advance.\" This suggests the video may be related to an event or occurrence linked to the Gyeongju earthquake, potentially showing environmental conditions before the earthquake.",
"The current frame shows a similar scene to the previous one, still depicting a nighttime environment with heavy snowfall. The setting remains consistent with an outdoor area, likely a patio or garden, indicated by the visible potted plants and railing. The snow continues to be blown across the scene, suggesting that the strong winds persist. The surveillance camera angle remains unchanged, capturing the ongoing environmental conditions. \n\nKey text in the image reinforces the previous frame's context: \"경주 지진, 지하수는 1~2일 전에 미리 알았다\" translates to \"Gyeongju earthquake, groundwater knew 1-2 days in advance.\" This text continues to suggest that the video is capturing conditions potentially linked to the Gyeongju earthquake, possibly showing environmental anomalies or changes that occurred before the earthquake. The time displayed on the screen is 09:34, which provides a timestamp for this scene.",
"The current frame continues to show a nighttime scene with the street illuminated by streetlights. The environment remains consistent with the previous frames, featuring the same outdoor setting. The text overlay \"경주 지진, 지하수는 1~2일 전에 미리 알았다\" (Gyeongju earthquake, groundwater knew 1-2 days in advance) remains visible, maintaining the context that the video is capturing conditions potentially linked to the Gyeongju earthquake. The timestamp on the screen is 09:35, indicating a minute has passed since the previous frame. The presence of cars on the street and the absence of any significant movement or anomalies suggest a normal nighttime traffic situation, with no immediate signs of environmental change or distress.",
"The current frame shows an indoor setting with a focus on a large air conditioning unit positioned against a wall with decorative elements. The text overlay \"경주 지진, 지하수는 1~2일 전에 미리 알았다\" (Gyeongju earthquake, groundwater knew 1-2 days in advance) is still visible, suggesting the video is discussing the Gyeongju earthquake and its precursors. The timestamp indicates it is 09:35, which matches the previous frame's time, implying no significant passage of time has occurred. There are no people visible, and the environment appears to be a typical indoor space, possibly an office or a living area. The scene lacks any signs of disturbance or emergency, indicating normalcy despite the context of the earthquake discussion.",
"The current frame transitions to an outdoor setting at night, showing a street lined with various shops and illuminated signs. The street is relatively quiet with a few vehicles and pedestrians. A white car and a blue van are parked on the side of the road, and another white car is driving down the street. The text overlay \"경주 지진, 지하수는 1~2일 전에 미리 알았다\" (Gyeongju earthquake, groundwater knew 1-2 days in advance) continues to be displayed, reinforcing the theme of the video. The timestamp now reads 09:35, indicating that the video has not moved forward in time since the previous indoor scene. The overall atmosphere is calm, with no visible signs of the earthquake's impact or urgency.",
"The video now captures a nighttime scene on a city street, where a white car is parked, and several pedestrians are walking. The ongoing text \"경주 지진, 지하수는 1~2일 전에 미리 알았다\" (Gyeongju earthquake, groundwater knew 1-2 days in advance) is still present, maintaining the video's focus on the earthquake's warning signs. The timestamp remains at 09:35, suggesting the video is revisiting or continuing the same time frame. The atmosphere appears calm, with no apparent earthquake-related disruptions or emergencies.",
"The current frame shows a daytime scene focusing on a traditional building roof with numerous chimneys or ventilation pipes. There is a person working on the roof, and below, a vehicle is parked, with various items, including a blue tarp and a green bag, secured on its roof rack. The text \"경주 지진, 지하수는 1~2일 전에 미리 알았다\" (Gyeongju earthquake, groundwater knew 1-2 days in advance) continues to be displayed, indicating the video's focus on the earthquake and its warning signs. The timestamp at 09:35 suggests continuity from the previous scene, possibly showing a different aspect of the same time frame. The sky is partly cloudy, and the overall setting appears to be a calm, possibly residential area with no immediate signs of earthquake-related activity.",
"The current frame depicts a daytime scene where a person is still actively working on the traditional building roof, continuing their task from the previous frame. The roof remains lined with chimneys or ventilation pipes. Below, the vehicle remains parked with the blue tarp and green bag still secured on its roof rack, suggesting no change in this setup. The text \"경주 지진, 지하수는 1~2일 전에 미리 알았다\" (Gyeongju earthquake, groundwater knew 1-2 days in advance) is still displayed, reinforcing the video's theme. The timestamp at 09:35 has not changed, indicating that this is a momentary continuation of the same scene without progression in time or activity. The sky remains partly cloudy, and the area appears calm and residential with no visible earthquake-related activity."
] |
uF3x63vtddc
|
The video depicts various scenes related to the Gyeongju earthquake, focusing on the idea that groundwater levels may have indicated the earthquake 1-2 days in advance. The footage shows a mix of nighttime and daytime environments, including outdoor settings such as streets, a patio or garden, and a traditional building, as well as an indoor setting with an air conditioning unit. The scenes are generally calm, with people engaged in normal activities like walking or working on a roof, and there are no immediate signs of earthquake-related distress or emergency. The video's timestamp remains consistent at 09:35 across several frames, suggesting a focus on a specific moment or period. Throughout, the text overlay "경주 지진, 지하수는 1~2일 전에 미리 알았다" (Gyeongju earthquake, groundwater knew 1-2 days in advance) emphasizes the video's theme of exploring potential precursors to the earthquake. Overall, the video appears to be presenting a series of vignettes or observations that may be related to the earthquake, without depicting the earthquake itself.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=nln3QFJggKs",
"video_description": "106억 → 58억…경주 지진 피해금액 반토막 잇단 강진으로 100억원이 넘는 것으로 추정됐던 경주시의 공식 피해규모가 58억원 수준에 그치는 것으로 집계됐습니다. 경주시가 지진 발생 뒤 전수조사를 통해 발표한 잠정 추산 피해액은 약 107억원이었지만 사유재산 피해는 대부분 공식 피해액에서 빠졌습니다. 규정상 기와가 떨어지거나 벽체에 금이 가고 담장이 파손된 것은 재산피해 산정되지 않습니다. 이에 따라 사유재산 중에는 지진으로 주택이 완전히 부서지거나 반쯤 허물어진 것만 공식 피해액에 들어갔습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "nln3QFJggKs"
}
| 8
|
[
"The image shows a wide aerial view of a cityscape with numerous buildings and green areas. Text in Korean appears on the image providing information, including \"경주 4.5여진\" (Gyeongju 4.5 magnitude earthquake), \"오늘도 여진 계속돼\" (Continued aftershocks today), and \"106억 → 58억...경주 지진 공식 피해금액 반토막\" (106 billion → 58 billion... Official damage amount from the Gyeongju earthquake cut in half). The scene suggests a news report covering ongoing aftershocks and economic impacts of an earthquake in Gyeongju.",
"The scene transitions to a closer ground-level view of a damaged area, possibly a construction site or a building undergoing repair following the earthquake. A crane is lifting a large object, likely debris or building materials, indicating ongoing recovery efforts. Multiple vehicles, including trucks and a car, are parked on the grassy field, suggesting a temporary setup for work crews. The background features traditional Korean architecture, hinting at the cultural significance of the site being repaired. Text overlays mention the financial impact of the earthquake, \"106억 → 58억...경주 지진 공식 피해금액 반토막\" (106 billion → 58 billion... Official damage amount from the Gyeongju earthquake cut in half), reinforcing the economic repercussions of the disaster.",
"The current frame shows a close-up view of the aftermath of a natural disaster, likely an earthquake, with scattered debris along a roadside. The focus is on broken black tiles and rubble strewn across the ground, indicating significant structural damage. The presence of a large rock wall in the background suggests the extent of the collapse or shifting of structures. The text overlay \"106억 → 58억...경주 지진 공식 피해금액 반토막\" (106 billion → 58 billion... Official damage amount from the Gyeongju earthquake cut in half) is reiterated, emphasizing the revised financial impact assessment due to the disaster. The scene likely captures the ongoing recovery and cleanup efforts in the affected area.",
"The current frame shows a rural setting with a small building and a man standing on a ladder, possibly repairing or inspecting the roof. A woman is holding a rope or tool, and another person is seen from behind, possibly observing the work. The scene is set in daylight with natural surroundings, including trees and a wooden fence. The text overlay \"경주 4.5 여진 놀란 시민들 식량·옷 챙겨\" (Gyeongju 4.5 aftershocks, shocked citizens prepare food and clothes) indicates a response to the aftermath of the earthquake, suggesting that people are taking precautions and preparing for potential further impacts.",
"In the current frame, a man is standing near a wall that has a noticeable crack, indicating damage from an earthquake. The text overlay \"경주 4.5 여진\" (Gyeongju 4.5 aftershocks) reinforces the context of the previous earthquake's impact. The man, wearing a red and white jacket and a cap, is observing the damage, suggesting he is assessing the extent of the structural damage. The surrounding area appears to be a residential neighborhood, with other buildings visible in the background. The scene suggests that the community is dealing with the aftermath of the earthquake, with individuals inspecting their properties for safety.",
"The frame displays a road with cracked pavement, indicating damage likely caused by the same earthquake as referenced in the previous frame. The text overlay \"경주 4.5 여진\" (Gyeongju 4.5 aftershocks) is again visible, providing context. There are no people in the frame, and the focus is on the cracked road, which suggests that the earthquake has caused significant infrastructure damage. The surrounding area appears to be an urban setting, with the damage affecting public spaces. The scene reinforces the aftermath of the earthquake, highlighting the extensive impact on the community's infrastructure.",
"The current frame shows a nighttime scene of a road with a crosswalk, where the pavement appears damaged with visible cracks, consistent with the earthquake damage from the previous frames. The text overlay \"경주 4.5 여진\" (Gyeongju 4.5 aftershocks) is present, indicating ongoing aftershocks. A vehicle's headlights are visible in the distance, suggesting some traffic despite the apparent damage. The urban setting remains, with a street lamp and traffic sign visible. The damage to the infrastructure is evident, emphasizing the earthquake's impact on the community.",
"The current frame depicts an interior view of a building, focusing on a section of a wall where tiles are visibly damaged, with some tiles partially detached and a large crack running through the wall. The text overlay \"경주 4.5 여진\" (Gyeongju 4.5 aftershocks) is present, indicating the earthquake's impact on this structure. The damage suggests significant structural compromise, highlighting the extensive impact of the aftershocks on buildings. The timestamp and additional text indicate that this footage is from a news broadcast, providing context to the earthquake's aftermath and its effects on urban infrastructure."
] |
nln3QFJggKs
|
The video depicts the aftermath of a 4.5 magnitude earthquake in Gyeongju, showing the damage and recovery efforts in the city. The earthquake caused significant structural damage to buildings, roads, and infrastructure, with cracked walls, broken tiles, and rubble strewn across the ground. The video shows a construction site with a crane lifting debris, indicating ongoing recovery efforts, as well as individuals inspecting and repairing damaged buildings. The economic impact of the earthquake is also highlighted, with the official damage amount being cut in half from 106 billion to 58 billion. Citizens are shown preparing for potential further aftershocks by gathering food and clothes. The video captures the extent of the damage in various settings, including residential neighborhoods, roads, and public spaces, emphasizing the earthquake's impact on the community's infrastructure and daily life.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=n6UmQ9Kw2GQ",
"video_description": "경주 지진 이후 여진 307회 발생…\"강도 약해져\" 지난 12일 저녁 발생한 규모 5.8의 경주 지진 탓에 여진이 307차례 발생한 것으로 집계됐습니다. 기상청에 따르면 오늘 오후 4시까지 경주 지진 이후 여진은 규모 1.5∼3.0도 292회 등 모두 307차례 발생했습니다. 기상청 관계자는 \"경주 지진 탓에 여진이 계속 발생하고 있지만 강도가 약해지고 있다\"며 \"앞으로 일어날 여진 규모는 3.0 이하로 예상되기 때문에 그렇게 우려하지 않아도 될 것 같다\"고 말했습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "n6UmQ9Kw2GQ"
}
| 8
|
[
"The image shows two news anchors, a man on the left and a woman on the right, standing in front of a map and a cityscape backdrop. The map in the background highlights areas affected by a recent event, indicated by red and yellow regions. The text on the screen reads \"경주 지진 이후 여진 307회 발생... '강도 약해져'\" which translates to \"After the Gyeongju earthquake, 307 aftershocks occurred... 'strength has weakened'\". There is also additional text on the bottom right indicating temperature and other details.",
"The current frame shows a kitchen with various cooking utensils and appliances visible, including a red pan hanging on the wall, a cutting board on the counter, and a sink. The kitchen appears to be in an ordinary household setting. The text overlay on the screen reads \"연합뉴스TV\" indicating the news channel, and \"경주 지진 이후 여진 307회 발생... '강도 약해져'\" which translates to \"After the Gyeongju earthquake, 307 aftershocks occurred... 'strength has weakened'\". There is also additional text on the top right providing information about the broadcast time, \"고속도로 예상 소요시간 서울~부산 4시간 20분\" meaning \"Expected travel time on the highway Seoul~Busan 4 hours 20 minutes\".",
"The current frame shows a close-up of a ceiling light fixture in a room. The light fixture is white with decorative patterns on the lampshade. The text overlay on the screen continues to read \"연합뉴스TV\" indicating the news channel, and \"경주 지진 이후 여진 307회 발생... '강도 약해져'\" which translates to \"After the Gyeongju earthquake, 307 aftershocks occurred... 'strength has weakened'\". There is also additional text on the top right providing information about the broadcast time, \"고속도로 예상 소요시간 서울~부산 4시간 20분\" meaning \"Expected travel time on the highway Seoul~Busan 4 hours 20 minutes\".",
"The current frame continues to focus on the ceiling light fixture in a room. The light fixture is white with decorative patterns on the lampshade. The text overlay on the screen still reads \"연합뉴스TV\" indicating the news channel, and \"경주 지진 이후 여진 307회 발생... '강도 약해져'\" which translates to \"After the Gyeongju earthquake, 307 aftershocks occurred... 'strength has weakened'\". There is also additional text on the top right providing information about the broadcast time, \"고속도로 예상 소요시간 서울~부산 4시간 23분\" meaning \"Expected travel time on the highway Seoul~Busan 4 hours 23 minutes\".",
"The current frame shows a close-up of a baby swing with toys attached to it. The swing is white, and there is a small giraffe toy hanging above it. The text overlay on the screen still reads \"연합뉴스TV\" indicating the news channel, and \"경주 지진 이후 여진 307회 발생... '강도 약해져'\" which translates to \"After the Gyeongju earthquake, 307 aftershocks occurred... 'strength has weakened'\". Additional text on the bottom of the screen provides information about the date and time, \"채널 23 17:21\" meaning \"Channel 23 17:21\", and weather information for Seoul, \"서울 21.1°C\". The text on the top right provides information about the broadcast time, \"고속도로 예상 소요시간 서울~광주 3시간 20분\" meaning \"Expected travel time on the highway Seoul~Gwangju 3 hours 20 minutes\".",
"The current frame continues to show the interior of a home, now with a focus on a dimly lit room. The text overlay remains consistent, still reading \"연합뉴스TV\" indicating the news channel, and \"경주 지진 이후 여진 307회 발생... '강도 약해져'\" which translates to \"After the Gyeongju earthquake, 307 aftershocks occurred... 'strength has weakened'\". The room contains a potted plant near the entrance and a television screen on the right side, which is turned on and displaying an image. Additional text on the bottom of the screen continues to provide information about the time and date, \"채널 23 17:21\" meaning \"Channel 23 17:21\", and weather information for Seoul, \"서울 21.1°C\". The text on the top right provides the same information about the broadcast time, \"고속도로 예상 소요시간 서울~광주 3시간 20분\" meaning \"Expected travel time on the highway Seoul~Gwangju 3 hours 20 minutes\". The overall scene suggests a calm, home environment following the discussion of the earthquake and its aftershocks.",
"The current frame maintains focus on the dimly lit room within the home, continuing the narrative of the aftermath of the Gyeongju earthquake. The room remains unchanged with the potted plant near the entrance and the television screen on the right side still on, displaying content. The text overlay \"연합뉴스TV\" and \"경주 지진 이후 여진 307회 발생... '강도 약해져'\" persist, indicating ongoing coverage of the earthquake and its aftershocks. The time and date displayed as \"채널 23 17:21\" remain the same, along with the weather information for Seoul \"서울 28.1°C\". The broadcast time for Seoul~Gwangju \"고속도로 예상 소요시간 서울~광주 2시간 30분\" is also unchanged. The scene suggests a consistent continuation of the news report in a home environment.",
"The current frame shows the same dimly lit room within the home, maintaining the focus on the aftermath of the Gyeongju earthquake. The potted plant near the entrance and the television screen on the right side are still visible, with the TV continuing to display content. The text overlay \"연합뉴스TV\" and \"경주 지진 이후 여진 307회 발생... '강도 약해져'\" are still present, indicating the ongoing news coverage of the earthquake and its aftershocks. The time and date display \"채널 23 17:21\" remains unchanged, as does the weather information for Seoul \"서울 28.1°C\". The broadcast time for Seoul~Gwangju \"고속도로 예상 소요시간 서울~광주 2시간 30분\" is also the same. The scene continues to depict a consistent news report within a home environment, focusing on the earthquake's impact and updates on the situation."
] |
n6UmQ9Kw2GQ
|
A news broadcast on 연합뉴스TV reports on the aftermath of the Gyeongju earthquake, stating that 307 aftershocks have occurred with weakening strength. The report is interspersed with scenes of ordinary household settings, including a kitchen and a dimly lit room with a television, suggesting a calm home environment despite the earthquake. The broadcast provides updates on the situation, including expected travel times on highways and weather information for Seoul. The news anchors are initially shown in front of a map highlighting the affected areas, before the scene cuts to various household settings, maintaining a consistent narrative of the earthquake's impact and the ongoing news coverage.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=uoagwCVoHGM",
"video_description": "경주 지진으로 8명 부상…재산피해 253건 어제 저녁 경주 일대에서 발생한 지진으로 인해 8명이 다치고 카카오톡과 국민안전처 홈페이지 등 통신망이 일시적으로 마비되는 등의 장애가 있었습니다. 국민안전처는 경주 일대에서 오늘과 어제에 걸쳐 일어난 지진으로 인해 80살 여성 황 모 씨 등 8명이 경상을 입고 253건의 재산피해가 신고됐다고 밝혔습니다. 이번 지진으로 인해 KTX 대전~부산 구간이 5분가량 정차하기도 했습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "uoagwCVoHGM"
}
| 8
|
[
"The image is from a news broadcast on Yonhap News TV, featuring a female news anchor standing on the right side of the screen. The main focus of the broadcast is an incident involving a sewer explosion that resulted in the death of eight people, with the text \"8명 부상...재산피해 253건\" displayed prominently. The image on the left shows a flooded and damaged area, likely caused by the sewer explosion, with water gushing out and debris scattered around. The scene appears to be chaotic and destructive, indicating a severe incident.",
"The current frame continues the news broadcast on Yonhap News TV, maintaining the focus on the incident involving a sewer explosion. The text \"경주 지진으로 8명 부상...재산피해 253건\" is prominently displayed, indicating that the explosion caused injuries to eight people and resulted in 253 property damages. The image shows a flooded and damaged area, with water gushing out and debris scattered around, reinforcing the severity of the incident. The scene remains chaotic and destructive, emphasizing the impact of the sewer explosion.",
"The current frame continues the news broadcast on Yonhap News TV, showing a blacked-out image of a street with a vehicle, likely reflecting the aftermath of the incident involving a sewer explosion. The text \"경주 지진으로 8명 부상...재산피해 253건\" is prominently displayed, indicating that the explosion caused injuries to eight people and resulted in 253 property damages. The scene remains dark and unclear, emphasizing the disruption and damage caused by the sewer explosion.",
"The video now shifts to a scene where a person is seen sweeping up debris on a tiled floor, indicating cleanup efforts following the incident. The same text \"경주 지진으로 8명 부상...재산피해 253건\" is displayed, reinforcing the severity of the disaster. The image of the person cleaning highlights the ongoing recovery process.",
"The current frame shows a close-up view of a floor with scattered debris, suggesting the aftermath of an incident. The same text \"경주 지진으로 8명 부상...재산피해 253건\" is displayed, indicating the event's impact. The person's presence is not visible in this frame, but the cleanup efforts are implied by the debris and context from the previous frame.",
"The current frame displays a close-up of a person's back, focusing on a prominent scar running down the spine. The text \"경주 지진으로 8명 부상...재산피해 253건\" remains visible, suggesting the person's injury is related to the earthquake in Gyeongju. The presence of medical attire and the detail of the scar indicate a focus on the human impact of the disaster, highlighting recovery and the aftermath of the event.",
"The scene transitions to a news studio where an anchor stands behind a desk, dressed in a dark suit. The text \"시사 파일\" is visible, indicating a segment of a news program. The setting suggests a continuation of reporting, possibly on the earthquake's impact and the ongoing recovery efforts.",
"The scene shows three individuals walking in what appears to be a hallway. The person in the foreground is wearing a blue tracksuit with white stripes on the sleeves, suggesting they may be involved in physical activity or sport. The other two individuals are walking alongside, with one wearing a gray shirt. The text \"연합뉴스TV\" indicates that this footage is from a news broadcast by the Korea News Service. The time displayed is 14:58, and additional text mentions \"검찰, '대우조선 투자' 비 코스피200\", suggesting a report about the prosecution's investigation into investment in Daewoo Shipbuilding & Marine Engineering, which is not listed on the Korea Composite Stock Price Index (KOSPI)."
] |
uoagwCVoHGM
|
A news broadcast on Yonhap News TV reports on a sewer explosion incident, resulting in the death of no one but injuring eight people and causing 253 property damages, although the initial frames suggest a more severe incident. The explosion is attributed to an earthquake in Gyeongju. The video shows the aftermath of the disaster, with flooded and damaged areas, debris scattered around, and cleanup efforts underway. The human impact of the disaster is highlighted through the display of a person's scar, implied to be a result of the earthquake. The broadcast continues with a news studio segment, indicating ongoing reporting on the event and its recovery efforts. The video then cuts to unrelated footage of individuals walking in a hallway, followed by a report on a separate news story about the prosecution's investigation into an investment in Daewoo Shipbuilding & Marine Engineering.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=5p1N4MtudiI",
"video_description": "경주 지진 316회 이어가다 현재는 '잠잠' 지난 12일 발생한 규모 5.8의 경주 지진의 여진이 316회 발생한 것으로 집계됐습니다. 기상청은 오늘 오전 11시 기준 여진 횟수가 316회라고 발표했습니다. 규모별 횟수는 1.5에서 3.0이 301차례, 3.0에서 4.0은 14차례, 4.0에서 5.0은 1차례 감지됐습니다. 사흘째 계속된 여진은 일단 멈추는 징후를 보이고 있는 것으로 기상청은 파악하고 있습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "5p1N4MtudiI"
}
| 8
|
[
"In the current frame, two news anchors are standing in front of a cityscape backdrop, presumably delivering a news broadcast. The backdrop features a river, a bridge, and a city skyline with a prominent tall building. The anchors are dressed in traditional Korean attire. The text on the screen includes the headline \"경주 지진 316회 이어가다 현제는 '잠잠'\" which translates to \"The Gyeongju earthquake has continued 316 times and is now 'calm'\". Additional text provides a date and time of \"2023년 9월 23일 오후 7시 40분\" (September 23, 2023, at 7:40 PM).",
"The current frame shows a news broadcast focused on seismic activity, specifically monitoring and reporting on the Gyeongju earthquake, which has occurred 316 times. The frame features a series of screens displaying seismographic data, maps indicating earthquake activity, and various charts and graphs with technical details. The text at the bottom reads \"경주 지진 316회 이어가다 현제는 '잠잠'\" meaning \"The Gyeongju earthquake has continued 316 times and is now 'calm'\". The broadcast appears to be from \"연합뉴스TV\" and includes a timestamp of 15:01, suggesting the broadcast is during the afternoon. The presence of multiple monitors with real-time data indicates a detailed and technical analysis of the seismic event.",
"The current frame continues to focus on the seismic activity related to the Gyeongju earthquake, which has occurred 316 times. The frame displays a complex network of lines and nodes, possibly representing seismic activity data, with prominent colors like yellow, red, and blue. The text at the bottom reads \"경주 지진 316회 이어가다 현재는 '잠잠'\" meaning \"The Gyeongju earthquake has continued 316 times and is now 'calm'\". The broadcast remains from \"연합뉴스TV\" with the time still at 15:01, indicating continuity in the reporting. The technical analysis of the seismic event is ongoing, with the visual representation suggesting a detailed examination of the earthquake's patterns and intensity.",
"The current frame continues to depict the seismic activity data related to the Gyeongju earthquake, with a similar focus on the network of lines and nodes, showing the earthquake's 316 occurrences. The prominent colors, including yellow, red, and blue, highlight different seismic readings. The text \"경주 지진 316회 이어가다 현재는 '잠잠'\" at the bottom remains, reinforcing that the earthquake has now subsided. The broadcast is still from \"연합뉴스TV\" at the same time, 15:01, indicating ongoing coverage. The detailed examination of the earthquake's patterns and intensity is evident, suggesting a thorough analysis is being conducted.",
"The video continues with a depiction of the Gyeongju earthquake's seismic activity data. The visual representation on the screen displays the earthquake's 316 occurrences, indicated by a network of lines and nodes. The colors yellow, red, and blue are used to differentiate various seismic readings. The text \"경주 지진 316회 이어가다 현재는 '잠잠'\" at the bottom of the screen confirms that the earthquake has now subsided. The broadcast is still from \"연합뉴스TV\" at the same time, 15:01, indicating ongoing coverage. This frame shows a detailed examination of the earthquake's patterns and intensity, suggesting a thorough analysis is being conducted.",
"The video continues to depict the Gyeongju earthquake's seismic activity data. The current frame shows a map with numerous yellow and orange circles, indicating the locations and intensity of the earthquakes. The text \"경주 지진 316회 이어가다 현재는 '잠잠'\" remains at the bottom of the screen, confirming the earthquake has subsided. The broadcast is still from \"연합뉴스TV\" at the same time, 15:01, indicating ongoing coverage. The map provides a geographical overview of the earthquake's impact, suggesting a detailed analysis of the seismic events is being presented.",
"The video displays a screen with text and a digital display showing the number \"89.\" The text indicates the ongoing coverage of the \"경주 지진 316회 이어가다 현재는 '잠잠'\" (Gyeongju earthquake continuing 316 times, currently 'quiet'). The broadcaster is \"연합뉴스TV,\" and the time displayed is 15:01, consistent with the previous frame. The image likely indicates a counter or the number of earthquakes recorded since the previous update.",
"The image shows a map focusing on South Korea, specifically highlighting the areas of Daegu, Ulsan, and Busan. A bright red dot marks a specific location on the map, suggesting an earthquake epicenter. The text at the top indicates the broadcaster is \"연합뉴스TV\" (Yonhap News TV) and displays the time as 15:01. Additional text on the screen mentions \"KERI,\" \"O.T.,\" \"EventID: gfz2016ryxp,\" and \"Status: automatic,\" which are likely related to the earthquake monitoring system. The image emphasizes the continuous monitoring and updates on the earthquake situation, continuing the theme of the previous frames."
] |
5p1N4MtudiI
|
A news broadcast from 연합뉴스TV (Yonhap News TV) reports on the Gyeongju earthquake, which has occurred 316 times and is currently calm. The broadcast, which took place on September 23, 2023, at 7:40 PM, and also shown at 15:01 on a different time display, features two news anchors dressed in traditional Korean attire standing in front of a cityscape backdrop. The report includes detailed technical analysis of the seismic event, displaying seismographic data, maps, charts, and graphs. The earthquake's patterns and intensity are examined through a network of lines and nodes, with various colors used to highlight different seismic readings. A map showing the locations and intensity of the earthquakes provides a geographical overview of the impact. The broadcast also displays a counter or update on the number of earthquakes recorded. The report focuses on the areas of Daegu, Ulsan, and Busan in South Korea, with a specific location marked as an earthquake epicenter. The continuous coverage indicates a thorough analysis and monitoring of the earthquake situation.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=roaxxb8zRLU",
"video_description": "국제신문 뉴스&이슈 구독하기 http://goo.gl/FFQL4 국제신문 근교산&기획특집 구독하기 http://goo.gl/SM0fM 국제신문 기사보기 http://iii.im/pk3Z 국제신문 영상팀이 경주 지진피해 복구 현장을 드론으로 담았다.",
"video_id": "roaxxb8zRLU"
}
| 8
|
[
"The frame shows an aerial view of a traditional Korean neighborhood with numerous houses, each featuring distinct, sloped, tiled roofs. The text in the image, written in Korean, suggests a focus on real estate, indicating that the video might be about property or architectural features. The background reveals a hilly landscape, emphasizing the scenic setting of the neighborhood.",
"The aerial view continues, highlighting a traditional Korean house with a sloped, tiled roof, where blue plastic sheets are visible, possibly indicating repair or maintenance work. The surrounding environment includes other similar houses, suggesting the scene is set in a residential area. The road and parked cars below provide context to the neighborhood's layout and daily life.",
"The current frame captures the ongoing aerial view of a traditional Korean neighborhood, focusing on a house where maintenance or repair work is being conducted. Blue plastic sheets cover parts of the house, likely to protect the structure or workers from the weather. A worker is seen on a green platform elevated on a red crane, actively engaged in the repair process. The surrounding environment includes other similar houses, reinforcing the residential setting. The presence of the crane and the elevated platform indicates a significant repair effort, possibly involving structural adjustments or roof maintenance. The road and parked cars below continue to provide context to the neighborhood's layout and daily life.",
"In the current frame, the focus remains on the traditional Korean house undergoing maintenance or repair. Workers are actively engaged in covering the roof with blue plastic sheets, likely for weather protection or to prepare for further repair work. The workers are wearing safety gear, including helmets and reflective vests, indicating adherence to safety protocols. The surrounding environment still includes other similar houses, maintaining the residential context. The ongoing repair efforts suggest a continued focus on structural adjustments or roof maintenance.",
"The current frame captures an aerial view of a park, with a stone tower standing prominently in the center of a circular plaza. People are seen walking around the plaza and the surrounding paths, indicating a leisurely atmosphere. The green grass and trees suggest a well-maintained park. The text in the image suggests a comparison to Pemso and a visit to the location, emphasizing the park's significance.",
"The current frame captures an aerial view of a farm, with a blue building standing prominently on the left side of the image. There are several buildings and vehicles, indicating a working farm. The green fields and crops suggest a well-maintained farm. The text in the image suggests a comparison to a location in Korea and a visit to the farm, emphasizing its significance.",
"The current frame shows an aerial view of a highway near a mountainous area. The highway appears to have two lanes, one in each direction, and is surrounded by green fields and a river. The text in the image is in Korean and mentions a comparison to a location in Korea and a visit to the area, suggesting the highway's significance.",
"The current frame shows an aerial view of a river flowing near a mountainous area. The river appears to have multiple curves and is surrounded by green fields. The text in the image is in Korean and mentions a comparison to a location in Korea and a visit to the area, suggesting the river's significance."
] |
roaxxb8zRLU
|
The video depicts a scenic tour of various locations in Korea, showcasing traditional architecture, natural landscapes, and daily life. It begins with an aerial view of a traditional Korean neighborhood, highlighting houses with sloped, tiled roofs, and ongoing repair work on one of the houses. The scene then shifts to a park with a stone tower, where people are walking and enjoying the surroundings, followed by a visit to a farm with blue buildings and green fields. The video also captures aerial views of a highway and a river near a mountainous area, emphasizing the natural beauty of the region. Throughout the video, text comparisons are made to other locations in Korea, suggesting a focus on real estate, tourism, or cultural heritage. The overall context suggests a promotional or documentary-style video aiming to showcase the charm and diversity of Korean landscapes and architecture.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=3ojHTwrvx90",
"video_description": "박 대통령, 경주 지진현장 방문 \"특별재난지역 선포\" 박근혜 대통령은 최근 강진이 잇따라 발생한 경북 경주 지역을 찾아 특별재난지역 선포를 적극 검토하라고 지시했습니다. 이어 지진 등 재난 안전 시스템을 원점에서 재점검할 것도 주문했습니다. 박 대통령은 아울러 인근 월성 원자력발전소를 찾아 \"원전은 단 한치의 실수도 용납되지 않는다\"며 지진 방재대책을 철저히 재점검해달라고 당부했습니다. 박 대통령의 지시에 국민안전처 또한 경주시를 특별재난지역으로 선포할 예정입니다. 특별재난지역으로 지정되면 지자체의 피해 복구비 부담이 완화되고, 피해 주민들은 공공요금 감면혜택을 받게됩니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "3ojHTwrvx90"
}
| 8
|
[
"The image shows a group of people in yellow jackets walking together. They appear to be on a street, and some individuals are being recorded by a camera crew. The setting seems to be outdoors during the daytime. A banner is visible in the background with text that seems to be in Korean. The text at the bottom of the image is in Korean, which translates to \"President Park, Gyeongju Jinhyeon Hospital visit, 'Special disaster area selection'\" and the time displayed is 08:50. The weather is indicated as 18.9°C, and the location is Yeosu.",
"The image shows the same group of people in yellow jackets walking together, maintaining the continuity from the previous frame. They are still outdoors on the street. The setting remains the same with the group being recorded by a camera crew. The banner in the background is still visible with text in Korean. The text at the bottom of the image is also in Korean, translating to \"President Park, Gyeongju Jinhyeon Hospital visit, 'Special disaster area selection'\" and the time displayed is 08:50. The weather is now indicated as 21.7°C, showing a slight increase from the previous frame, and the location remains Yeosu.",
"The group of people in yellow jackets is still walking together on the street, maintaining the same formation as seen in the previous frames. They are outdoors and continue to be recorded by a camera crew, indicating a continuation of the same event. The banner in the background remains visible with text in Korean, consistent with the previous frame. The text at the bottom of the image still translates to \"President Park, Gyeongju Jinhyeon Hospital visit, 'Special disaster area selection'\" and the time is still shown as 08:50. The weather has slightly cooled to 15.4°C, and the location remains Yeosu.",
"The group of people in yellow jackets continues to walk together on the street, maintaining their formation. They are outdoors, and a camera crew is still recording the event, indicating continuity. The banner in the background is still visible with text in Korean. The text at the bottom of the image translates to \"President Park, Gyeongju Jinhyeon Hospital visit, 'Special disaster area selection'\". The time is 08:50, and the weather is 19.0°C, with the location still Yeosu.",
"The group of people in yellow jackets is now standing in front of a large building entrance, with the camera crew capturing the scene. A man in a yellow jacket is prominently speaking or gesturing. The banner in the background remains visible with the same Korean text. The text at the bottom of the image still reads \"President Park, Gyeongju Jinhyeon Hospital visit, 'Special disaster area selection'\". The time is 08:50, and the weather is now 20.2°C, with the location still Yeosu.",
"The group of people in yellow jackets is now standing in front of a building entrance, with the camera crew capturing the scene. A man in a yellow jacket is prominently speaking or gesturing. The banner in the background remains visible with the same Korean text. The text at the bottom of the image still reads \"President Park, Gyeongju Jinhyeon Hospital visit, 'Special disaster area selection'\". The time is 08:50, and the weather is now 18.1°C, with the location still Yeosu.",
"The group of people in yellow jackets is now walking down a street, still with the camera crew filming. The man in a yellow jacket who was speaking or gesturing is now leading the group. The banner in the background is no longer visible. The text at the bottom of the image reads \"News on Today 23,\" indicating a news segment. The time is 08:50, and the weather is now 20.1°C, with the location still Yeosu.",
"The group of people in yellow jackets continues walking down the street, with the camera crew still filming. The man in a yellow jacket who was leading the group is now accompanied by others in the group, some carrying bags. The text at the bottom of the image reads \"Yonhap News TV,\" indicating the news channel. The time is now 08:50, and the weather is 18.7°C, with the location still Yeosu."
] |
3ojHTwrvx90
|
A group of people in yellow jackets, accompanied by a camera crew, are walking on a street in Yeosu. They appear to be part of an event related to President Park's visit to Gyeongju Jinhyeon Hospital, with a focus on the selection of a special disaster area. The group is led by a man in a yellow jacket who is sometimes speaking or gesturing. As they walk, they pass by a banner with Korean text and eventually arrive at a building entrance, where they stop and the man speaks. They then continue walking down the street, still being filmed by the camera crew, with some members of the group carrying bags. The event is being recorded for news segments, as indicated by the text at the bottom of the images referencing "News on Today 23" and "Yonhap News TV". The time remains consistent at 08:50 throughout the event, with slight fluctuations in the weather.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=w6jdwGYcKZU",
"video_description": "안전처 \"경주지진 부상자 23명ㆍ재산피해 1,118건\" 국민안전처는 경주에서 발생한 규모 5.8의 지진으로 부상자 23명이 발생하고, 재산상 피해는 1천118건으로 집계됐다고 밝혔습니다. 안전처와 보건복지부에 따르면 부상자 23명 가운데 7명은 병원에서 치료를 받고 귀가했으며, 16명은 입원 중입니다. 지역별 부상자는 경북이 12명으로 가장 많고, 울산 4명, 대구 2명, 부산·인천·충북·전남·경남 각 1명입니다. 안전처는 균열이 발생한 주택을 대상으로 구조기술사 등과 함께 안전점검을 하고 귀가 여부와 추가 안전조치 등을 검토할 예정입니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "w6jdwGYcKZU"
}
| 8
|
[
"The image shows a nighttime surveillance camera view of a residential area, likely affected by heavy rainfall. The text in Korean at the bottom of the image reads \"경주 지진 부상자 23명·재산피해 1,118건,\" indicating that 23 people were injured and there were 1,118 property damages due to an earthquake in Gyeongju. The weather at the time is shown as 20.2°C with clear weather.",
"The image shows a black and white surveillance camera view of a damaged interior, likely a residential area, affected by heavy rainfall. The text in Korean at the bottom of the image reads \"경주 지진 부상자 23명·재산피해 1,118건,\" indicating that 23 people were injured and there were 1,118 property damages due to an earthquake in Gyeongju. The weather at the time is shown as 19.8°C with sunny weather.",
"The image is a blurry nighttime view of a street scene with a large truck parked on the side. The text in Korean at the top reads \"연합뉴스 TV 고속도로 예상 소요시간 부산-서울 5시간,\" indicating a news segment about traffic conditions, specifically the expected travel time of 5 hours from Busan to Seoul on the expressway. The text at the bottom of the image reads \"경주 지진 부상자 23명·재산피해 1,118건,\" consistent with the previous frame, continuing to inform about the earthquake in Gyeongju, with 23 injured and 1,118 property damages. The temperature displayed is 19.3°C.",
"The image shows a blurred close-up of a wet surface, likely indicative of water damage or flooding. The Korean text at the top reads \"연합뉴스 TV 고속도로 예상 소요시간 울산-서울 5시간 40분,\" which continues the news segment about traffic conditions, this time specifying an expected travel time of 5 hours and 40 minutes from Ulsan to Seoul on the expressway. The text at the bottom of the image remains consistent with the previous frame, still reporting \"경주 지진 부상자 23명·재산피해 1,118건,\" providing ongoing updates on the earthquake in Gyeongju, with 23 injured and 1,118 property damages. The temperature displayed is now 19.4°C.",
"The current frame shows a close-up of a cluttered room with items scattered on the floor, suggesting disarray likely caused by an earthquake. The Korean text at the bottom continues to report on the Gyeongju earthquake, stating there are 23 injured and 1,118 property damages. The temperature is now 20.8°C.",
"The video shows a close-up of a damaged wall with significant cracks, indicating structural damage likely from the same earthquake. The Korean text at the bottom repeats the earthquake report, confirming 23 injured and 1,118 property damages. The temperature is now 21.4°C.",
"The video shows a close-up of a damaged floor with significant cracks and debris, indicating structural damage likely from the same earthquake. The Korean text at the bottom repeats the earthquake report, confirming 23 injured and 1,118 property damages. The temperature is now 21.5°C.",
"The video displays a scene of destruction with broken tiles scattered across a gravel surface, likely the aftermath of an earthquake. A car is parked in the center, surrounded by the debris. The Korean text at the bottom of the image reiterates the earthquake details, indicating 23 injured and 1,118 property damages, and the current temperature is 22.4°C."
] |
w6jdwGYcKZU
|
The video depicts the aftermath of an earthquake in Gyeongju, showing various scenes of damage and destruction. The earthquake resulted in 23 injuries and 1,118 instances of property damage. The footage includes nighttime surveillance views of residential areas, damaged interiors, and close-ups of structural damage such as cracked walls and floors. Additionally, there are scenes of cluttered rooms, water damage, and debris scattered outdoors, including broken tiles and gravel. The video also mentions traffic conditions, providing expected travel times from Busan and Ulsan to Seoul, indicating potential disruptions due to the earthquake. Throughout the video, the temperature is displayed, ranging from 19.3°C to 22.4°C, and the reports of the earthquake's impact remain consistent, emphasizing the extent of the damage and injuries caused by the event.
|
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.
|
[
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching for trapped people in rubble after the 2017 Pohang earthquake in Heunghae, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in open spaces after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks forming in roads and sidewalks as the ground shakes during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders searching for survivors in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cars and debris scattered on the streets after earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in safe zones after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders rushing to the scene in ambulances and fire trucks during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Rescue teams searching for trapped people in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks and damage to roads and buildings caused by the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=oK2O8Xtkrvs",
"video_description": "15일 오후 2시 29분쯤 경북 포항시 북구 북쪽 9㎞ 지역에서 규모 5.4의 지진이 발생했다. 오마이TV는 지진 발생 당시 포항시 북구 한살림협동조합 매장을 촬영한 CCTV영상을 제보받아 공개한다. 이 영상에는 갑자기 진열대 물건들이 쏟아져내리는 장면이 들어있다. 한살림협동조합에 근무하는 박혜령(경북 영덕군)씨는 영상을 제보하면서 \"당시 사무실에 있었는데 벽지와 창문이 20초 이상 심하게 흔들렸다\"며 \"아직도 가슴이 진정되지 않는다\"고 말했다. 그는 \"바닥이 계속 흔들려 모두 밖으로 나왔고 안으로 들어갈 엄두를 내지 못했다\"며 \"이후 여진을 알리는 재난문자가 세 차례 왔다\"고 당시 상황을 설명했다. (영상제보 : 박혜령 씨/ 영상편집 : 황지희 기자)",
"video_id": "oK2O8Xtkrvs"
}
| 8
|
[
"In a convenience store, a person wearing a dark coat and light pants is bending over and reaching towards the floor, seemingly picking something up. The shelves are stocked with various products. The Korean text in the frame translates to \"Citizen report: During filming, an item fell down.\"",
"The person is now standing upright, holding an item, possibly the one that fell. They are looking towards the camera, possibly acknowledging it.",
"In the current frame, a person is seen in a grocery store, walking away from the camera. They are carrying a bag in one hand and appear to be moving quickly. The floor is littered with various scattered items, indicating a recent disturbance. The text at the bottom of the image, in Korean, reads \"[시민 제보] 포항 지진 순간, 쏟아진 진열대,\" which translates to \"[Citizen Report] During the Pohang earthquake, a collapsed display shelf.\" This suggests that the scene captures the aftermath of an earthquake that caused items to fall off a shelf.",
"The video captures the aftermath of a Pohang earthquake, as indicated by the text at the bottom of the image in Korean, which translates to \"[Citizen Report] During the Pohang earthquake, a collapsed display shelf.\" In the current frame, the interior of a grocery store is visible, with a significant amount of items scattered across the floor, suggesting a recent disturbance. The shelves on either side of the aisle are filled with various products, but the focus is on the central area where items have fallen. The floor is littered with debris, including packages and other goods that have spilled from the shelves. The scene is devoid of people, highlighting the impact of the earthquake and the chaotic aftermath.",
"The video continues to capture the aftermath of the Pohang earthquake, focusing on the interior of a grocery store. The scene is characterized by significant chaos, with a large number of items scattered across the floor in the center aisle. Shelves on both sides of the aisle are visibly intact but filled with various products. The text at the bottom of the image, in Korean, reinforces the context, translating to \"[Citizen Report] During the Pohang earthquake, a collapsed display shelf.\" The absence of people in the frame emphasizes the impact of the earthquake and the subsequent disorder within the store. The focus remains on the central area where the debris is most concentrated, highlighting the extent of the damage.",
"The scene continues to capture the aftermath of the Pohang earthquake inside the grocery store. The central aisle remains significantly cluttered with a large number of items scattered across the floor, highlighting the extent of the damage. Shelves on both sides of the aisle are still visible but are devoid of any people, emphasizing the impact of the earthquake. The text at the bottom of the image, in Korean, remains consistent with the previous frame, translating to \"[Citizen Report] During the Pohang earthquake, a collapsed display shelf.\" The focus continues to be on the central area, where the debris is most concentrated, underscoring the ongoing disorder within the store.",
"The current frame shows a white background with text in Korean. The text at the top indicates the production rights belong to OhmyNews (시민기자), with additional text stating the production and editing credits. In the center, the OhmyTV logo is displayed alongside the website URL, 'www.ohmynews.com'. Below, the text reads that the footage was submitted by members of the 100,000 People's Community. The right side of the frame shows additional text in Korean, which translates to 'Video by: Mudukem'. This frame likely serves as a credits or production information screen, concluding the segment of the video.",
"The current frame continues to display a white background with Korean text, which reaffirms the production rights of OhmyNews (시민기자) and includes credits for production and editing. The OhmyTV logo is prominently featured alongside the website URL, 'www.ohmynews.com'. Additional text indicates that the footage was contributed by members of the 100,000 People's Community, and the video is credited to 'Mudukem'. This frame likely serves as a credits or production information screen, maintaining consistency in providing acknowledgment to the contributors and copyright holders."
] |
oK2O8Xtkrvs
|
A person in a convenience store picks up an item that fell, possibly due to an earthquake, as indicated by a Korean text translation. The scene then shifts to a grocery store where a person is seen walking away quickly, carrying a bag, amidst a floor littered with scattered items, suggesting a recent disturbance caused by the Pohang earthquake. The subsequent frames focus on the aftermath of the earthquake, showing the grocery store's interior with a significant amount of debris and items scattered across the floor, emphasizing the chaos and impact of the earthquake. The video concludes with credits screens, acknowledging the production rights, contributors, and copyright holders, including OhmyNews and the 100,000 People's Community, with the video credited to 'Mudukem'.
|
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.
|
[
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching for trapped people in rubble after the 2017 Pohang earthquake in Heunghae, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in open spaces after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks forming in roads and sidewalks as the ground shakes during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders searching for survivors in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cars and debris scattered on the streets after earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in safe zones after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders rushing to the scene in ambulances and fire trucks during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Rescue teams searching for trapped people in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks and damage to roads and buildings caused by the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=6HhGFKbHFbs",
"video_description": "경북 포항에서 규모 5.4의 지진과 여진이 발생, 전국이 지진파에 흔들거리면서 주민들이 불안에 떨고 있다. 15일 기상청에 따르면 이날 오후 2시29분쯤 포항시 북구 흥해 6㎞ 지점에서 지진이 발생했다. http://www.hankookilbo.com/v/38f7f1c1597443e5ac55aca087a5dae2",
"video_id": "6HhGFKbHFbs"
}
| 8
|
[
"The frame shows a surveillance camera view of a white truck parked on a road beside a rural area with green vegetation. Text in the image indicates that a truck driver and a woman were born in a field in Gyeongbuk, and the date is provided as November 15.",
"The frame shows a surveillance camera view of a white car parked in a shopping district. Text in the image indicates that a traffic accident occurred when the vehicle was born in the area. The date is provided as November 15.",
"In the current frame, the scene shifts to a busy street in the shopping district. Several pedestrians are seen walking along the sidewalk. Two individuals, one on each side of the street, appear to be engaged in an argument or confrontation. They are both holding items, possibly beverages, and seem to be gesturing towards each other. The atmosphere appears tense as they face each other across the road, with other pedestrians in the background going about their activities. The date, November 15, is also displayed in this frame, maintaining continuity with the previous frame.",
"The current frame continues to depict the busy street scene in the shopping district. The tension between the two individuals persists as they remain engaged in their confrontation. One individual, who was previously on the left side of the street, is now closer to the center, continuing to gesture and possibly speak to the other individual, who remains on the right side. The pedestrians in the background continue their activities, seemingly unaware or indifferent to the ongoing argument. The date, November 15, remains displayed, maintaining the continuity of the timeline within the video.",
"The video captures a moment on a busy street where a dispute has arisen between two individuals. The confrontation appears to be ongoing, with one person standing near the center of the street, possibly continuing to argue or speak to the other person, who remains on the right side. The pedestrians in the background are going about their day, seemingly unbothered by the altercation. The date, November 15, is visible, indicating the timeline of the events. The scene captures the essence of a lively street where daily life goes on despite the disagreement between the two individuals.",
"The video continues to show the busy street with a dispute between two individuals still ongoing. The person previously standing in the center of the street is now closer to the camera, possibly escalating the confrontation. Pedestrians in the background appear to be avoiding the altercation, with some looking on. The date, November 15, remains visible, indicating that the events are still unfolding on the same day.",
"In this frame, a large group of people, possibly students, are seen gathering on the street, with several individuals wearing striped uniforms. The focus remains on the interaction between the two central figures, who appear to be at the heart of the ongoing dispute. The crowd has thickened, and the pedestrians' attention is largely directed towards the central confrontation. The date, November 15, continues to be displayed, maintaining the continuity of the events in the video.",
"The current frame displays a static image with the text \"HANKOOKILBO.COM\" prominently featured in green letters. Below the text, in smaller font, it reads \"제작 한국일보 영상 포항시\" which translates to \"Production: Hankook Ilbo Video Pohang City.\" This frame appears to be a transition or title card, likely signaling the beginning or end of a segment in the video. There are no people, actions, or other elements present in this particular frame."
] |
6HhGFKbHFbs
|
A video depicts a series of events unfolding on November 15, starting with a surveillance view of a white truck in a rural area and a white car in a shopping district, where a traffic accident occurred. The scene then shifts to a busy street in the shopping district, where two individuals engage in a heated argument or confrontation, gesturing and speaking to each other across the road. The dispute continues, with the individuals moving closer together and the atmosphere becoming increasingly tense, while pedestrians in the background go about their daily activities, initially unaware or indifferent to the altercation. As the confrontation escalates, more people, possibly students, gather on the street, wearing striped uniforms, and the crowd's attention becomes focused on the central dispute. The video ends with a static image displaying the production information, "HANKOOKILBO.COM" and "Production: Hankook Ilbo Video Pohang City," likely signaling the conclusion of the segment.
|
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.
|
[
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching for trapped people in rubble after the 2017 Pohang earthquake in Heunghae, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in open spaces after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks forming in roads and sidewalks as the ground shakes during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders searching for survivors in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cars and debris scattered on the streets after earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in safe zones after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders rushing to the scene in ambulances and fire trucks during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Rescue teams searching for trapped people in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks and damage to roads and buildings caused by the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=1sXMvTYhnn0",
"video_description": "+--------------------------------------------------------------------------------+ ◈ 중앙일보 공식 SNS 채널 ◈ - 페이스북 : https://www.facebook.com/joongang/ - 인스타그램 : https://www.instagram.com/joongangilbo - 트위터 : http://www.twitter.com/joongangilbo - 유튜브 : https://goo.gl/DyGoPC - 네이버 TV : http://tvcast.naver.com/joongangsisa - 네이버포스트 : https://goo.gl/eeYh4k 당신이 원하는 뉴스, 중앙일보 SNS 채널과 함께하세요. +--------------------------------------------------------------------------------+",
"video_id": "1sXMvTYhnn0"
}
| 8
|
[
"The image shows a clock on a wall with the text below it in Korean. The text mentions a construction site accident where materials fell unexpectedly, causing a severe injury.",
"The image shows a grandfather clock in an office setting with the text below it in Korean. The text continues from the previous frame, likely elaborating on the construction site accident where materials fell unexpectedly, resulting in severe injury.",
"The scene remains inside an office setting, featuring the same grandfather clock. The text continues from the previous frame, detailing the construction site accident where materials fell unexpectedly, causing a severe injury. The context of the ongoing narrative about the accident is maintained.",
"The scene shifts to a street view outside, where a group of people are walking by a shop with Korean signage. The text overlay indicates that the footage shows an incident where a pedestrian was hit by a car. The focus is on the aftermath of the accident and the pedestrian's condition.",
"The current frame shows a group of people inside what appears to be a transportation hub, possibly a bus or train station. The individuals are conversing, with some wearing face masks. The text overlay mentions the detection of four accidents at a university after a breakdown, with the university president and faculty members planning to meet to discuss the situation. The focus is on the interaction among people in the context of an incident response.",
"The current frame shows several individuals walking and standing in the transportation hub. A person on the left is walking while pulling a suitcase, and another person is adjusting their face mask. The text overlay repeats the mention of four accidents at a university after a breakdown, with the university president and faculty members planning to meet to discuss the situation. The scene continues to depict people's reactions and interactions in response to the incident.",
"The current frame shows the interior of a building with a large glass ceiling, allowing natural light to fill the space. The text overlay in Korean reiterates the occurrence of four accidents at a university and mentions that after the breakdown, the president and faculty members are planning to meet the mayor's representative to discuss the situation. The scene suggests a transition to a more formal or administrative setting, focusing on the response to the accidents.",
"The video transitions to a black screen with the Korean text \"종영일보\" (Final Day Report), indicating that the narrative is concluding and summarizing the events leading to the final day. This likely refers to the culmination of the university accident response and the subsequent meeting planned with the mayor's representative, as discussed in the previous frame."
] |
1sXMvTYhnn0
|
The video depicts a series of events and responses to accidents in different settings. It begins with a narrative about a construction site accident where materials fell unexpectedly, causing a severe injury, as indicated by text in Korean below a clock in an office setting. The scene then shifts to a street where a pedestrian was hit by a car, showing the aftermath and the pedestrian's condition. The video then moves to a transportation hub, possibly a bus or train station, where people are conversing and reacting to the news of four accidents at a university after a breakdown. The university president and faculty members plan to meet to discuss the situation, and later, they intend to meet with the mayor's representative. The video concludes with a black screen displaying "종영일보" (Final Day Report), summarizing the events leading to the final day, which likely refers to the culmination of the university accident response and the planned meeting with the mayor's representative.
|
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.
|
[
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching for trapped people in rubble after the 2017 Pohang earthquake in Heunghae, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in open spaces after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks forming in roads and sidewalks as the ground shakes during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders searching for survivors in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cars and debris scattered on the streets after earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in safe zones after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders rushing to the scene in ambulances and fire trucks during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Rescue teams searching for trapped people in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks and damage to roads and buildings caused by the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=MH6_TeWDitQ",
"video_description": "포항 북구 북쪽 9Km 지역서 5.4 지진 이어 여진…전국서 감지 2.2, 2.6 전진 이어 3.6 여진도 발생 기상청은 15일 오후 2시 29분 쯤 경북 포항시 북구 북쪽 9㎞ 지역에서 규모 5.4의 지진이 발생했다고 밝혔습니다. 진앙은 북위 36.10도, 동경 129.37도입니다. 기상청은 이 지진의 깊이를 9㎞로 파악했습니다. 기상청은 당초 지진 발생지역과 규모를 포항시 북구 북쪽 6㎞ 지점, 규모 5.5로 발표했으나 잠시 후 수정하는 등 혼선이 이어지고 있습니다. 이날 오후 2시49분에는 포항시 북구 북쪽 7km에서 규모 3.6의 여진도 발생했습니다. 기상청은 \"이동속도가 빠른 지진파(P파)만을 이용해 자동 추정한 정보\"라며 \"여진 등 안전에 주의해야 한다\"고 당부했습니다. 이날 지진으로 경북과 경남은 물론 서울 지역에서도 건물 흔들림이 느껴지는 등 전국 곳곳에서 진동이 감지됐습니다. 이보다 앞서 이 인근에서는 두 차례 지진이 있었다고 기상청은 발표했습니다. 오후 2시 22분 32초 포항시 북구 북쪽 7km 지역(북위 36.11도, 동경 129.36도)에서 규모 2.2의 지진이 난 후 2시 22분 44초에는 비슷한 지점(북위 36.08도, 동경 129.31도)에서 규모 2.6의 지진이 발생했습니다. (끝)",
"video_id": "MH6_TeWDitQ"
}
| 8
|
[
"The map shows a targeted location in the Pyeonghwa-si area, indicated by a red circle. The surrounding regions labeled are Pyeonghwa-si North, Pyeonghwa-si South, Youngcheon-si, and Gyeongju-si. The map appears to be from a news broadcast, as indicated by the text \"연합뉴스TV\" (Yonhap News TV) in the top right corner.",
"The map continues to display the targeted location in the Pyeonghwa-si area, with the red circle still marking the central spot. The surrounding regions, including Pyeonghwa-si North, Pyeonghwa-si South, Youngcheon-si, and Gyeongju-si, remain visible. The text \"연합뉴스TV\" (Yonhap News TV) still appears in the top right corner, indicating the source of the broadcast.",
"The scene shifts to a street view in a Pyeonghwa-si area, where a crowd of people is gathered on a sidewalk, facing a busy street filled with cars. The focus is on pedestrians, including both men and women, some of whom are wearing dark jackets, suggesting a colder season. The buildings in the background have signage in Korean, and the text \"연합뉴스TV\" (Yonhap News TV) remains in the top right corner, confirming the broadcast source. This frame provides a glimpse of the local environment and the community's presence in the area.",
"The crowd of pedestrians remains gathered on the sidewalk, facing the busy street filled with cars. The scene is ongoing with a consistent number of people, still dressed in winter attire, indicating the colder season. The background still features buildings with Korean signage, and the text \"연합뉴스TV\" (Yonhap News TV) is still visible in the top right corner, maintaining the broadcast source. The video continues to depict the community's presence in the Pyeonghwa-si area.",
"The crowd of pedestrians remains gathered on the sidewalk, facing the busy street filled with cars. The scene is ongoing with a consistent number of people, still dressed in winter attire, indicating the colder season. The background still features buildings with Korean signage, and the text \"연합뉴스TV\" (Yonhap News TV) is still visible in the top right corner, maintaining the broadcast source. The video continues to depict the community's presence in the Pyeonghwa-si area.",
"The scene shows an empty street in a residential area with debris scattered across the road. The focus is on a person standing on the sidewalk, dressed in winter attire, observing the debris. Buildings with Korean signage line the street, and the text \"연합뉴스TV\" (Yonhap News TV) remains visible in the top right corner, indicating the source of the broadcast. The absence of pedestrians and vehicles suggests a recent disturbance or accident, contrasting with the previous frame's bustling street scene.",
"The scene continues to show the empty street in the residential area with debris still scattered across the road. The person dressed in winter attire remains standing on the sidewalk, still observing the debris. The buildings with Korean signage line the street, and the text \"연합뉴스TV\" (Yonhap News TV) remains visible in the top right corner, indicating the source of the broadcast. The absence of pedestrians and vehicles persists, reinforcing the suggestion of a recent disturbance or accident.",
"The scene continues to depict the empty street in the residential area with debris scattered across the road. The person dressed in winter attire remains standing on the sidewalk, observing the debris. The buildings with Korean signage line the street, and the text \"연합뉴스TV\" (Yonhap News TV) remains visible in the top right corner, indicating the source of the broadcast. The absence of pedestrians and vehicles persists, reinforcing the suggestion of a recent disturbance or accident."
] |
MH6_TeWDitQ
|
A news broadcast from Yonhap News TV shows a targeted location in the Pyeonghwa-si area, with the surrounding regions of Pyeonghwa-si North, Pyeonghwa-si South, Youngcheon-si, and Gyeongju-si visible on a map. The scene then shifts to a street view in the Pyeonghwa-si area, where a crowd of people is gathered on a sidewalk, facing a busy street filled with cars, indicating a sense of community presence. However, the scene abruptly changes to an empty street in a residential area with debris scattered across the road, suggesting a recent disturbance or accident. A person dressed in winter attire is shown standing on the sidewalk, observing the debris, and the absence of pedestrians and vehicles persists, reinforcing the notion of a recent incident. The video appears to be reporting on an event or accident that occurred in the Pyeonghwa-si area, with the news broadcast providing footage of the community and the aftermath of the incident.
|
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.
|
[
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching for trapped people in rubble after the 2017 Pohang earthquake in Heunghae, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in open spaces after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks forming in roads and sidewalks as the ground shakes during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders searching for survivors in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cars and debris scattered on the streets after earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in safe zones after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders rushing to the scene in ambulances and fire trucks during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Rescue teams searching for trapped people in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks and damage to roads and buildings caused by the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=_HN3DpC6m6I",
"video_description": "[현장] 포항 지진 피해 상황은…\"여진 등 안전 주의\" 오늘 오후 2시 29분 쯤 경북 포항시 북구에서 규모 5.4의 지진이 발생했습니다. 이번 지진은 작년 9월 12일 경북 경주시에서 발생한 규모 5.8의 지진에 이어 우리나라에서 일어난 지진 중 역대 두번째 규모입니다. 기상청에 따르면 포항지진 발생 지점은 포항시 북구 북쪽 9㎞, 북위 36.10도, 동경 129.37도입니다. 기상청은 이 지진의 깊이를 9㎞로 파악했습니다. 기상청은 당초 지진 발생지역과 규모를 포항시 북구 북쪽 6㎞ 지점, 규모 5.5로 발표했으나 지진 규모를 하향조정하는 등 혼선을 겪었습니다. 규모 5.4 지진에 앞서 오후 2시 22분 32초 포항시 북구 북쪽 7km 지역에서 규모 2.2, 2시 22분 44초 비슷한 지점(북위 36.08도, 동경 129.31도)에서 규모 2.6의 지진 등 전진이 발생했습니다. 아울러 이날 오후 2시 49분 규모 3.6 지진을 시작으로 오후 3시0분 54초께 규모 2.9 지진, 오후 3시 9분 49초 규모 3.6 지진 등 여진도 이어지고 있습니다. 기상청은 \"이동속도가 빠른 지진파(P파)만을 이용해 자동 추정한 정보\"라며 \"여진 등 안전에 주의해야 한다\"고 당부했습니다. 그러면서 \"계속해서 여진이 발생하고 있어 상황을 면밀히 분석 중\"이라며 \"발생 지점이 내륙 쪽으로 들어가 있어 해일의 가능성은 없는 것으로 판단한다\"고 덧붙였습니다. 이날 지진으로 경북과 경남은 물론 서울 지역에서도 건물 흔들림이 느껴지는 등 전국 곳곳에서 진동이 감지됐습니다. 연합뉴스TV : 02-398-4441(기사문의ㆍ제보) 카톡/라인 jebo23 ▣ 연합뉴스TV 유튜브 채널 구독 https://goo.gl/VuCJMi ▣ 대한민국 뉴스의 시작 연합뉴스TV / Yonhap News TV http://www.yonhapnewstv.co.kr/",
"video_id": "_HN3DpC6m6I"
}
| 8
|
[
"The image shows an aerial view of an urban area with numerous buildings and roads. The text indicates that the photo was taken at 5:40 in the morning. The broadcast is by 연합뉴스 TV (Yonhap News TV) with the location identified as 현장영상 (Field Video). Additional text indicates that this is from 경북 포항시 북구 (North District, Pohang, Gyeongbuk).",
"The video presents a view from a vehicle's dashboard camera, showing a parking area under a covered structure. The time stamp indicates the recording was made on November 15, 2017, at 14:29. The text on the screen shows 연합뉴스TV (Yonhap News TV) and 현장영상 (Field Video). The vehicles in the parking lot include a black car in the foreground and a white car parked outside the structure. There are additional cars parked further back under the cover. The environment suggests an urban setting with trees and buildings visible in the background.",
"The current frame shows a large blue water jug placed on a table. The label on the jug reads 동원샘물, indicating the brand and type of water. The text on the screen includes 연합뉴스TV (Yonhap News TV) and 제보영상 (User-Supplied Video), suggesting that the footage is from a viewer. The water jug is the primary focus of the frame, and it appears to be in an indoor setting, possibly an office or a common area, given the presence of a desk and other office supplies in the background.",
"The current frame displays a storefront with a shattered glass window, indicating a recent break-in or incident. The shattered glass is scattered across the floor, and there is a red and white sign partially visible, suggesting that the location is a commercial establishment. The text on the screen includes 연합뉴스TV (Yonhap News TV) and 제보영상 (User-Supplied Video), indicating that the footage is from a viewer and may be related to a news report or incident. The scene appears to be set in an urban area, given the storefront and signage, and there is no indication of ongoing activity or people present in the frame.",
"The storefront appears to be empty with no visible activity or people present. The broken glass is still on the floor, indicating the break-in or incident has not been addressed. The text on the screen includes 연합뉴스TV (Yonhap News TV) and 제보영상 (User-Supplied Video), confirming the footage is from a viewer and may be related to a news report or incident.",
"A group of individuals stands outdoors in a park-like setting, some in business attire and others in uniform, suggesting a formal event or gathering. The crowd is attentive, with many people facing the same direction, likely towards a speaker or focal point not visible in the frame. The environment is illuminated by natural daylight, with trees and a metal arch structure in the background, contributing to a sense of a community or organizational meeting. The text on the screen, 연합뉴스TV (Yonhap News TV) and 제보영상 (User-Supplied Video), indicates this footage is part of a news broadcast, possibly covering a public announcement or event.",
"The scene transitions to a sports court area where a group of people, including children and adults, are gathered. Some are standing while others are sitting on the ground, indicating a more casual and varied setting. The group appears engaged, likely in a discussion or listening to someone off-camera. The environment, with its green flooring and fencing, suggests a recreational area. The text 연합뉴스TV (Yonhap News TV) and 제보영상 (User-Supplied Video) continues to indicate that this footage is part of a news broadcast, possibly covering a community event or activity involving local residents. The transition from the formal gathering to this more relaxed setting implies a broader coverage of public life and community interactions.",
"The scene shifts to a larger gathering, possibly in a park or open space, with numerous people standing and congregating. The diverse group, including adults and younger individuals, appears engaged in various activities, such as walking, talking, and interacting with their phones. The atmosphere is lively, suggesting a community event or public gathering. The text 연합뉴스TV (Yonhap News TV) and 제보영상 (User-Supplied Video) confirms that this is part of a news broadcast. The presence of the text 기상청 \"여진 등 안전에 주의해주세요...\" (\"Meteorological Agency: 'Please be cautious of aftershocks and safety...'\") indicates a message of caution related to safety, likely due to recent or potential seismic activity."
] |
_HN3DpC6m6I
|
The video appears to be a news broadcast from 연합뉴스 TV (Yonhap News TV) covering various scenes and events, possibly related to a significant incident or series of incidents in Pohang, Gyeongbuk, South Korea. The footage includes an aerial view of the city, a parking area, a water jug in an indoor setting, a storefront with a shattered glass window indicating a break-in, and several community gatherings in outdoor settings such as parks and sports courts. The gatherings seem to involve a mix of formal and casual events, with people engaged in discussions, listening to speakers, or participating in community activities. The presence of a message from the Meteorological Agency warning about aftershocks and safety suggests that the events might be related to an earthquake or seismic activity. Overall, the video provides a snapshot of community life and responses to potential natural disasters or incidents in the region.
|
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.
|
[
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching for trapped people in rubble after the 2017 Pohang earthquake in Heunghae, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in open spaces after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks forming in roads and sidewalks as the ground shakes during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders searching for survivors in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cars and debris scattered on the streets after earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in safe zones after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders rushing to the scene in ambulances and fire trucks during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Rescue teams searching for trapped people in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks and damage to roads and buildings caused by the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=bADRfbUZewY",
"video_description": "산림청은 오는 4일 포항산림조합 목재유통센터에서 국유림에서 생산된 임산 연료를 지진피해를 입은 포항 주민들에게 무상으로 공급하는 행사를 갖기로 했습니다. ◀ＥＮＤ▶ 지진피해 주민과 홀몸노인, 기초생활보장 수급자 등을 대상으로 가구당 1톤씩 모두 21가구를 지원합니다. 이번에 공급하는 장작은 봉화군 장군봉 선도산림경영단지 내 금강소나무 육성사업지에서 생산된 참나무와 벚나무, 박달나무 등입니다.",
"video_id": "bADRfbUZewY"
}
| 8
|
[
"The image shows a modern building with a sign in Korean that reads \"Sanlim Town, Public Hall\" in English. There is a banner above the entrance with additional Korean text. The building appears to be a community center or public facility, with solar panels mounted on a pole outside. A clear blue sky is visible in the background.",
"The current frame shows a group of people in red uniforms and helmets working outside, handling a pile of chopped wood in front of a building. They appear to be gathering and organizing the wood, possibly as part of a community service or cleanup activity. The text at the bottom of the image is in Korean, but it is not described in the current frame description.",
"The group of people in red uniforms and helmets is actively engaged in moving and organizing the chopped wood. One individual is bending over to pick up a piece of wood, while others are seen transporting and stacking the wood. The setting suggests they are conducting a cleanup or maintenance activity related to the building, as indicated by their coordinated effort and the visible Korean text which likely provides additional context about their task.",
"The group of people in red uniforms and helmets continues to actively work with the chopped wood. They are seen moving and organizing the wood, with some individuals handling pieces and others stacking them. The ongoing activity suggests they are still engaged in their cleanup or maintenance task around the building. The visible Korean text reinforces the context of their coordinated effort.",
"The scene shows a large pile of chopped wood outdoors, indicating the group's progress in their wood chopping activity. The chopped wood is scattered and stacked, suggesting that the group has been actively working to clear and organize the wood. The background includes part of a building with a brick wall and a window, reinforcing the setting of a coordinated effort around the building. The visible Korean text, which translates to \"Self-organization, with active participation, the group is working together,\" underscores the ongoing activity and teamwork of the group.",
"The current frame shows a person standing in front of the large pile of chopped wood, with the surrounding area indicating an outdoor setting. The person appears to be interacting with the wood, possibly organizing or inspecting it. The background still features a building with a brick wall, consistent with the previous frame, reinforcing the setting of a coordinated effort. The visible Korean text, \"산림청, 포항 지진피해 가구에 장작 지원,\" translates to \"Forestry Agency, providing firewood to households affected by the Pohang earthquake,\" indicating that this activity is part of a relief effort to help those affected by the earthquake. The scene suggests that the group's work is ongoing and is aimed at providing support to those in need.",
"The current frame depicts a large pile of chopped wood in an outdoor setting, consistent with the previous frame. The background still features a building with a brick wall, reinforcing the setting. The visible Korean text, \"산림청, 포항 지진피해 가구에 장작 지원,\" translates to \"Forestry Agency, providing firewood to households affected by the Pohang earthquake,\" indicating the activity is part of a relief effort. The pile of wood is substantial, suggesting significant preparation and organization.",
"In the current frame, a group of individuals wearing red jackets and safety helmets are seen working together to clear the area of fallen trees and branches. One person is using a chainsaw to cut through a large branch, while others are handling the logs and loading them onto a truck. The background shows a building with a white exterior and windows, and there is a wooden fence in the vicinity. The scene suggests a coordinated effort to clean up and provide relief after a disaster, in line with the previous frame's description of a relief operation."
] |
bADRfbUZewY
|
A group of people in red uniforms and helmets are engaged in a community service activity outside a public hall in Sanlim Town, which appears to be a community center or public facility. They are gathering, organizing, and stacking chopped wood as part of a cleanup or maintenance task. The activity is later revealed to be a relief effort by the Forestry Agency to provide firewood to households affected by the Pohang earthquake. The group works together, using tools such as chainsaws, to clear the area of fallen trees and branches, and load the wood onto a truck. The setting is outdoors, with a building and a brick wall visible in the background, and the group's efforts suggest a coordinated and organized approach to providing support to those in need.
|
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.
|
[
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching for trapped people in rubble after the 2017 Pohang earthquake in Heunghae, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in open spaces after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks forming in roads and sidewalks as the ground shakes during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders searching for survivors in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cars and debris scattered on the streets after earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in safe zones after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders rushing to the scene in ambulances and fire trucks during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Rescue teams searching for trapped people in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks and damage to roads and buildings caused by the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=4eNANKub4NE",
"video_description": "7000미라클_포항 지진 피해 돕기 특집방송 1부 본방 2017년 11월 28일(화) 오전 10시 10분 재방 2017년 11월 28일(화) 밤 11시 10분 삼방 2017년 11월 29일(수) 오후 2시 50분 ----------------------------------------------------------------------------------------- 7000미라클_포항 지진 피해 돕기 특집방송 2부 본방 2017년 11월 29일(화) 오전 10시 10분 재방 2017년 11월 29일(화) 밤 11시 10분 삼방 2017년 11월 30일(수) 오후 2시 50분",
"video_id": "4eNANKub4NE"
}
| 8
|
[
"The image shows a damaged structure with debris scattered around it, indicating a collapse or significant structural damage. The text in Korean reads \"마음 돌 곳도 없어버렸습니다,\" which translates to \"There is nowhere for the heart to rest,\" suggesting emotional distress or loss. The setting appears to be a residential area, with a blue gate and a cross visible, indicating a possible religious or community center nearby. The overall scene conveys a sense of devastation and loss.",
"The image continues to depict the aftermath of significant structural damage, with debris scattered around the collapsed building. The setting remains consistent with the previous frame, showing a residential area with signs of devastation. The Korean text reads \"7000 MIRACLES\" and \"CTS 기독교TV,\" indicating a connection to a religious or community channel. The presence of a tarp-covered structure and various materials suggests ongoing efforts to clear or rebuild the area. The overall atmosphere remains one of loss and the struggle to recover from the destruction.",
"In the current frame, the focus remains on a middle-aged man with gray hair standing on the sidewalk, appearing to be observing his surroundings. He is dressed in a blue and black plaid shirt and a black vest, looking contemplative. The background shows a residential area with a white wall and a brick structure, indicating a neighborhood setting. The presence of utility meters and a partially visible sign reinforces the urban environment. The text \"7000 MIRACLES\" and \"CTS 기독교TV\" suggests a religious or community context, potentially indicating that the scene is part of a program or news segment related to recovery or community support following a significant event.",
"The scene shifts to an interior view of a vehicle, where a person with curly hair and wearing glasses is seen from behind. They are dressed in a pink patterned jacket and are looking out of the passenger window. The environment outside the window suggests a residential area with some buildings and possibly a fence visible. The text \"7000 MIRACLES\" and \"CTS 기독교TV\" is still present, reinforcing the religious or community context. The individual's contemplative posture and the stationary vehicle imply a moment of reflection or observation, continuing the theme of community or recovery from the previous frame.",
"The scene shows an indoor setting with a person wearing a black jacket sitting against a wooden wall. The environment includes a row of empty chairs, suggesting a waiting area. Text on the screen in Korean reads \"지진이 난날, 제일 많이 기울어진곳에 가니까 그날 눈물밖에 안 나옴니다,\" indicating a reflection or conversation about a personal experience related to an earthquake. The presence of the text \"7000 MIRACLES\" and \"CTS 기독교TV\" suggests a religious or community context, continuing the theme of support or recovery from the previous frames.",
"The current frame shows a group of people indoors, gathered closely around a person lying down, surrounded by blankets and personal belongings, indicating a makeshift or temporary living situation. The individuals are holding hands and appear to be engaged in a supportive gesture, suggesting a moment of collective emotional connection or prayer. The presence of the text \"7000 MIRACLES\" and \"CTS 기독교TV\" reinforces the religious or community support context, possibly indicating that this group is part of a recovery or relief effort following an event like an earthquake.",
"The current frame shows the exterior of a church building with a sign reading \"7000 MIRACLES\" and \"CTS 기독교TV.\" The church has a prominent cross on top and is situated in an urban setting with other buildings nearby. The text overlay in the image suggests a focus on the church's role or involvement, likely related to the support and recovery efforts mentioned in the previous frame. The overall context implies that the church is part of a broader community response to an event, providing assistance and support to those affected.",
"The current frame shows a close-up of the top section of a church building featuring a large, weathered cross against a clear sky. The cross appears to have a star-shaped symbol affixed to it, suggesting a connection between the church and a specific group or event. The text overlay \"7000 MIRACLES\" and \"CTS 기독교TV\" remains, indicating the church's involvement or affiliation with a religious or humanitarian organization. The context implies that the church is part of a larger narrative, possibly highlighting its role in community support or disaster response."
] |
4eNANKub4NE
|
The video depicts the aftermath of a devastating event, likely an earthquake, in a residential area. The scene shows a damaged structure with debris scattered around it, indicating significant structural damage and loss. A middle-aged man is seen observing the destruction, and the video cuts to various scenes showing people reflecting on the event, including a person in a vehicle and another in a waiting area. The video also shows a group of people gathered in a supportive gesture, possibly in prayer, in a makeshift living situation. Throughout the video, the presence of a church and the text "7000 MIRACLES" and "CTS 기독교TV" suggests a religious or community context, indicating that the church is involved in support and recovery efforts. The overall context implies that the video is part of a program or news segment related to community support and recovery following a significant event, with a focus on the emotional and psychological impact on those affected.
|
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.
|
[
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching for trapped people in rubble after the 2017 Pohang earthquake in Heunghae, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in open spaces after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks forming in roads and sidewalks as the ground shakes during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders searching for survivors in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cars and debris scattered on the streets after earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in safe zones after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders rushing to the scene in ambulances and fire trucks during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Rescue teams searching for trapped people in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks and damage to roads and buildings caused by the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=QIkpgLcEWMA",
"video_description": "픽업영상|시민들이 보내 준 #포항지진_영상 한동대 외벽 무너지고, 주차장 바닥 갈라져 #JTBC는_여러분들의_제보_기다립니다 ---------------------------------------------------------------------------------------- 📌 소셜스토리 - JTBC 바로가기▼ https://www.facebook.com/JTBCstandbyyou/",
"video_id": "QIkpgLcEWMA"
}
| 8
|
[
"The video frame shows a dark smoke plume rising from a building, indicating a fire. Trees and a cloudy sky are in the foreground. The text in Korean reads, \"소셜스토리\" (Social Story) and \"무너지는 건물 외벽에 학생들 대피\" (Students taking refuge on the collapsing exterior wall of the building).",
"The current frame shows a damaged building with several boarded-up sections, indicating extensive damage possibly from a fire or other disaster. The text in Korean reads \"소셜스토리\" (Social Story) and \"시청자제보\" (Viewer Report), suggesting that this scene is part of a news report from an eyewitness account. The scene continues the context of a collapsing building, likely related to the previous frame's fire incident, with the focus now on the structural damage.",
"The current frame shows a person moving through a cluttered and disorganized room, which seems to be an office or workspace. Various items are scattered across the surfaces, and the overall appearance is one of chaos and disarray. The text in Korean \"소셜스토리\" (Social Story) and \"시청자제보\" (Viewer Report) suggests this scene is part of a news report, possibly showing the aftermath of a disruptive event or incident. The focus on the person navigating through the mess might indicate a search or attempt to restore order.",
"In the current frame, two individuals are seated at a table in what appears to be a casual dining setting. They are engaged in a conversation while one person is stirring a large bowl of food, possibly a type of Asian cuisine. The table has various items, including a cup, a phone, and a pair of scissors. The text in Korean \"소셜스토리\" (Social Story) and \"시청자제보\" (Viewer Report) indicates this scene is part of a social or lifestyle segment. The context suggests a relaxed and informal interaction between the two, with a focus on the meal being prepared or served.",
"In the current frame, the individual is still seated at the table in the casual dining setting, engaged in a conversation while holding chopsticks and looking at the large bowl of food. The table still has various items, including a cup, a phone, and a pair of scissors. The text in Korean \"소셜스토리\" (Social Story) and \"시청자제보\" (Viewer Report) continues to indicate that this scene is part of a social or lifestyle segment. The focus remains on the relaxed and informal interaction between the two individuals, with the meal being a central point of engagement.",
"The current frame shows a parked area with several cars, including a white SUV, a black SUV, and a white sedan. There is visible text \"소셜스토리\" (Social Story) and \"시청자제보\" (Viewer Report) in the top corners, indicating this scene is part of a social or lifestyle segment. The individuals from the previous frame are not visible in this image.",
"The current frame depicts a damaged building with significant structural damage, including a collapsed section of the wall and exposed bricks. Debris and broken materials are scattered around the area. The text \"현재도 여전 계속 이어져 주의 필요\" (Even now, it continues to happen; attention is necessary) suggests ongoing issues or incidents. The presence of \"시청자제보\" (Viewer Report) in the top right corner indicates that this scene is part of a viewer-reported segment, possibly highlighting ongoing problems or hazards related to the building.",
"The current frame shows a logo of JTBC, indicating a transition or a branding moment within the video."
] |
QIkpgLcEWMA
|
A video depicting various scenes, starting with a fire incident in a building where students are taking refuge on the collapsing exterior wall. The scene then shifts to show the aftermath of the disaster, with a damaged building and a cluttered office or workspace. The video then transitions to a more casual setting, showing two individuals engaged in a conversation over a meal in a dining setting. The scene changes again to a parked area with several cars, before returning to the damaged building, highlighting ongoing structural issues and hazards. The video appears to be a social story or news report, with segments possibly focusing on disaster response, lifestyle, and community issues, as indicated by the "소셜스토리" (Social Story) and "시청자제보" (Viewer Report) text throughout the frames.
|
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.
|
[
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching for trapped people in rubble after the 2017 Pohang earthquake in Heunghae, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in open spaces after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks forming in roads and sidewalks as the ground shakes during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders searching for survivors in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cars and debris scattered on the streets after earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in safe zones after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders rushing to the scene in ambulances and fire trucks during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Rescue teams searching for trapped people in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks and damage to roads and buildings caused by the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=_vMNNh-x79Q",
"video_description": "경북 포항서 규모 5.4 지진 발생…서울ㆍ부산서도 진동 [앵커] 오늘 오후 경북 포항에서 규모 5.4의 지진이 발생했습니다. 부산을 비롯해 서울에서도 흔들림이 감지됐습니다. 보도국 취재기자 연결해 자세한 내용 들어보겠습니다. 홍정원 기자. [기자] 네, 오늘 오후 2시29분 포항 북구에서 북쪽으로 6킬로미터 지역에서 규모 5.4의 지진이 발생했다고 기상청이 밝혔습니다. 진앙은 북위 36.10도, 동경 129.37도입니다. 포항에서는 창이 흔들리고 책장에서 책이 떨어지는 등 진동의 여파가 상당했던 것으로 전해지고 있는데요. 또한 포항 곳곳에선 여진도 이어진 것으로 전해지고 있습니다. 기상청은 \"이동속도가 빠른 지진파, P파만을 이용해 자동 추정한 정보\"라며 \"여진 등 안전에 주의해야 한다\"고 당부했습니다. 한수원 측은 전국의 원자력발전소는 별다른 문제 없이 가동 중이라고 밝혔습니다. 오늘 지진의 지진동은 서울 등 경기 남부는 물론, 경남권과 호남권 등 전국적으로 감지된 것으로 전해지고 있습니다. 지진 발생 직후 부산소방안전본부와 부산경찰청에는 건물이 흔들린다는 시민들의 문의 전화가 빗발친 것으로 전해졌습니다. 일부 도심 건물이 심하게 흔들리면서 관련 직장인과 시민들이 급히 대피하는 소동이 벌어졌습니다. 다시 한 번 말씀드리겠습니다. 오늘 오후 2시29분 포항 북구에서 북쪽으로 6킬로미터 지역에서 규모 5.4의 지진이 발생했다고 기상청이 밝혔습니다. 포항 곳곳에선 여진이 이어지면서 주민 대피가 속출했으며, 지진동은 서울 등 경기권과 부산 등에서도 감지되면서 전국적으로 우려를 키우고 있습니다. 원자력발전소를 관리하는 한수원 측은 현재까지 가동중인 원전에 별다른 문제가 없다고 밝혔습니다. 아직까지 전국적으로 정확한 인명, 시설 피해 상황은 집계되지 않은 상태입니다. 지금까지 보도국에서 전해드렸습니다. 연합뉴스TV : 02-398-4441(기사문의·제보) 카톡/라인 jebo23 (끝)",
"video_id": "_vMNNh-x79Q"
}
| 8
|
[
"The image shows a news broadcast featuring a chandelier with white lampshades. The headline text reads \"뉴스속보 교육부 '내일 가능 평형 등 전국서 예정대로 진행'\" which translates to \"Breaking News: Ministry of Education 'Tomorrow's possible balance, etc., to proceed as planned nationwide.'\" A phone number and additional text are visible in the upper right corner, suggesting the news is broadcast by \"연합뉴스 TV\" (Yonhap News TV) and includes a call-in segment. There is also a small inset image of a person, likely a news anchor or reporter, in the same area.",
"The image displays another news broadcast segment. The headline text reads \"뉴스속보 교육부 '규모 5.4, 경주 강진 이후 역대 두번째 위력'\" which translates to \"Breaking News: Ministry of Education 'Scale 5.4, second largest power after Gyeongju earthquake'.\" The broadcast appears to be from \"연합뉴스 TV\" (Yonhap News TV) as indicated by the logo. There is a small inset image of a person, possibly a news anchor or reporter, in the upper right corner, continuing the call-in segment. The main background of the frame shows an indoor setting with a clock, suggesting the focus is on the timing or impact of the event being reported.",
"The current frame is a continuation of the news broadcast segment, focusing on the aftermath of a significant earthquake. The text at the top of the frame reads \"뉴스특보 포항시 규모 5.4 지진\" which translates to \"Breaking News: Pohang City, Magnitude 5.4 Earthquake.\" The broadcast logo \"연합뉴스TV\" (Yonhap News TV) remains visible, indicating the source of the news. The inset image in the upper right corner continues to feature a person, likely the same news anchor or reporter, engaged in a call-in segment. The main background still shows an indoor setting, with a large light fixture in view, suggesting the focus is on the impact of the earthquake on infrastructure or daily life. The time \"14:58\" is displayed at the bottom, providing the timestamp for the news report.",
"The current frame continues the news broadcast segment, focusing on the aftermath of the significant earthquake in Pohang City. The text at the top of the frame reads \"뉴스특보 기상청 규모 5.4, 경주 장진 이후 역대 두번째 위력\" which translates to \"Breaking News: Meteorological Office Magnitude 5.4, Second Most Powerful Since the Gyeongju Jangjin Earthquake.\" The broadcast logo \"연합뉴스TV\" (Yonhap News TV) is visible, indicating the source of the news. The inset image in the upper right corner features a person, likely a news anchor or reporter, engaged in a call-in segment. The main background shows an indoor setting with a large water bottle, suggesting the focus is on the impact of the earthquake on daily life and infrastructure. The time \"14:58\" is displayed at the bottom, providing the timestamp for the news report.",
"The scene is an outdoor cityscape with multiple buildings and a crowd of people gathered on the street, possibly responding to the earthquake mentioned in the previous frame. The text overlay \"뉴스특보 포항시 규모 5.4 지진\" translates to \"Breaking News: Pohang City Magnitude 5.4 Earthquake,\" confirming the event. The ongoing news coverage suggests a focus on the earthquake's impact on urban areas, with emergency response activities likely taking place. The inset image continues to feature the reporter, indicating the news segment's continuation. The timestamp \"14:59\" at the bottom confirms the sequence of events within the broadcast.",
"The video continues with an indoor view, showing a kitchen setting with a prominent hanging light fixture in the center of the image. The text overlay \"뉴스특보 전국 각지서 지진 신고전화 폭주\" translates to \"Breaking News: Earthquake Reports Flood Nationwide,\" indicating that the earthquake is not limited to Pohang City but has affected various locations across the nation. The inset image still features the reporter, suggesting the news segment remains ongoing. The timestamp \"14:59\" remains consistent, suggesting continuity in the broadcast's timeline. The focus on the kitchen environment may imply that the earthquake's impact is being discussed in the context of household safety or the everyday lives of individuals affected by the event.",
"The scene transitions to an interior view of a retail store, specifically focusing on an iPhone X display with a sign indicating \"Apple iPhone X.\" The sign is in Korean, and the store appears to be well-lit with various electronic products on display. There is a noticeable glare on the glass, likely from the store's lighting, which creates a reflection on the surface. The text overlay \"뉴스특보 교육부 '내일 수능 평가 전국서 예정대로 진행'\" translates to \"Breaking News: Ministry of Education 'Tomorrow's College Scholastic Ability Test to Proceed as Scheduled Nationwide,'\" indicating that despite the earthquakes, the government has decided to continue with the national exam. The timestamp \"14:59\" suggests that this information is being reported in real-time, and the presence of the reporter in the inset image reinforces the ongoing nature of the news coverage.",
"The video captures the aftermath of an earthquake as evidenced by the shattered glass on the ground. The scene is set in a retail store, likely the same one from the previous frame, as indicated by the consistent environment and the recognizable \"Apple iPhone X\" display. The broken glass is scattered across the floor, suggesting the force of the earthquake was significant enough to cause structural damage within the store. The text overlay \"뉴스특보 새울원전 '신고리 3호기 이상 없어...지진값 분석중'\" translates to \"Breaking News: Seoul Nuclear Power Plant 'No abnormalities in Shin Gorri 3...Earthquake analysis in progress,'\" indicating that while the retail store suffered damage, there are no immediate concerns at the nuclear power plant. The presence of the reporter in the inset image continues to provide real-time updates on the situation, maintaining the continuity of the news coverage. The timestamp \"14:59\" remains consistent, suggesting that these events are unfolding within a short time frame."
] |
_vMNNh-x79Q
|
A news broadcast on Yonhap News TV reports on a magnitude 5.4 earthquake in Pohang City, which is the second most powerful since the Gyeongju earthquake. The earthquake has prompted a flood of reports nationwide, with the Ministry of Education announcing that the College Scholastic Ability Test will proceed as scheduled the next day. The news coverage shows the impact of the earthquake on daily life, including damage to a retail store with shattered glass on the ground. Despite the damage, there are no reported abnormalities at the Seoul Nuclear Power Plant, with analysis of the earthquake's effects ongoing. The news segment features a reporter providing real-time updates and a call-in segment, with timestamps indicating the events are unfolding rapidly, all within the same minute, 14:58-14:59.
|
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.
|
[
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching for trapped people in rubble after the 2017 Pohang earthquake in Heunghae, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in open spaces after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks forming in roads and sidewalks as the ground shakes during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders searching for survivors in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cars and debris scattered on the streets after earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in safe zones after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders rushing to the scene in ambulances and fire trucks during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Rescue teams searching for trapped people in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks and damage to roads and buildings caused by the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=k_iUdIJKUUc",
"video_description": "포항 시민들은 눈앞에서 아파트 외벽이 갈라지는 현장을 목격하며 하루종일 공포에 떨었습니다. 시민 700여명은 지금도 집에 돌아가지 못하고 대피소에 머물고 있습니다. [Ch.19] 사실을 보고 진실을 말합니다. ★홈페이지 : http://news.tvchosun.com/ * 뉴스제보 : 이메일([email protected]), 카카오톡(tv조선제보), 전화(1661-0190)",
"video_id": "k_iUdIJKUUc"
}
| 8
|
[
"The image shows a news anchor dressed in a suit, standing in front of a large screen displaying footage of a group of people gathered around some vehicles outside a building. The screen's background includes a brick wall and a window. The text at the bottom of the image, in Korean, translates to: \"Now reporting: 'Due to the storm,' it couldn't be done.\" The number '9' is also visible, likely indicating a news channel or segment.",
"The video shows a reporter in a gymnasium filled with people, some sitting and some standing, likely affected by the storm mentioned in the previous frame. The reporter, holding a microphone with a TV logo, is providing a live update or report on the situation. The text at the bottom of the image is partially visible, likely indicating the channel or segment, with the number '9' visible.",
"The video depicts two individuals walking at night in what appears to be a dark, possibly deserted area. The person on the left is wearing a dark jacket and is holding a microphone with a TV logo, suggesting that they might be a reporter continuing the live update or report on the storm situation. The individual on the right is dressed in a dark outfit and carrying a backpack, possibly accompanying the reporter. The text in the top right corner, \"TV조선 LIVE,\" indicates that this is a live broadcast, and the number '9' in the bottom right corner likely refers to the channel number.",
"The current frame shows the exterior of a building with visible structural damage. A portion of the building's balcony is hanging precariously, and there are large cracks and holes in the wall, indicating significant structural compromise. The scene is set at night, and the damage suggests that the building has been severely affected, possibly by the storm mentioned in the previous frame. The text \"아파트 외벽 금가고 철근까지 노출...건물 붕괴 우려\" translates to \"Apartment exterior wall cracked, rebar exposed... Concerns of building collapse,\" reinforcing the severity of the situation. The text \"이 시각 폭우 | '불안' 귀가도 못해\" translates to \"At this time, heavy rain | 'Unsure' even unable to return home,\" indicating the challenging conditions due to the storm. The text \"TV조선 LIVE\" and the number '9' are still present, indicating that this is a live broadcast from the same channel.",
"The current frame shows a close-up of a shattered glass window, with visible cracks and broken pieces, indicating damage. The scene is set at night, and the damage suggests that the window has been severely affected, possibly by the storm mentioned in the previous frame. The text \"이재민 730명 발생...생필품조차 못챙긴채 긴급대피\" translates to \"730 displaced people occurred...Even unable to take emergency supplies,\" indicating the challenging conditions due to the storm. The text \"TV조선 LIVE\" and the number '9' are still present, indicating that this is a live broadcast from the same channel.",
"The current frame shows a person walking, carrying a pink blanket and a blue package in their hands. They are wearing a blue jacket and black pants, and the scene is set at night. The person appears to be in a hurry, possibly fleeing from a situation. The text \"TV조선 LIVE\" and the number '9' are still present, indicating that this is a live broadcast from the same channel. The text \"이재민 730명 발생...생필품조차 못챙긴채 긴급대피\" translates to \"730 displaced people occurred...Even unable to take emergency supplies,\" indicating the challenging conditions due to the storm.",
"The scene is indoors, likely in a gymnasium, where people are seated on the floor with blankets and personal belongings, suggesting a shelter or temporary housing situation due to an emergency. The text \"TV조선 LIVE\" and the number '9' are visible, indicating this is a live broadcast. The text \"이 시각 포항 | '불안' 귀가도 못해\" translates to \"At this time in Pohang | 'Anxiety' can't even return home,\" suggesting that people are facing difficulties due to an ongoing issue, possibly a storm or disaster, and are unable to return to their homes.",
"The scene continues in the same gymnasium setting with individuals seated on the floor. One person is using a mobile device, while another is resting with a blanket. The presence of personal items and the ongoing broadcast from \"TV조선 LIVE\" maintains the context of a shelter situation. The text \"이 시각 포항 | '불안' 귀가도 못해\" is not visible in this frame, but the setting and activities suggest that people are still dealing with the aftermath of an emergency."
] |
k_iUdIJKUUc
|
A severe storm has caused significant damage and disruption in an area, possibly Pohang, leading to 730 people being displaced and forced to take emergency shelter. The storm has resulted in structural damage to buildings, with cracked walls, exposed rebar, and shattered windows, making it unsafe for people to return home. A news team from TV조선 (Channel 9) is providing live updates from the affected area, showing the damage and speaking with those affected. The displaced individuals have taken shelter in a gymnasium, where they are waiting with their personal belongings, unable to return home due to the ongoing situation. The live broadcast aims to inform the public about the severity of the situation and the challenges faced by those affected.
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=Be0D3w0LKSg",
"video_description": "(서울=뉴스1) 문동주 기자 = 지난 18일 한국보다 먼저 일본에 상륙한 제14호 태풍 난마돌. 난마돌로 인해 일본에는 엄청난 강풍과 호우 피해가 이어졌다. 사람도 서 있기 힘든 정도의 위력의 비바람에 건물 외장재들이 날아다니고 대중교통 일부도 마비됐다. 동해에 접한 일본 서부 연안을 따라 이동한 난마돌의 위력을 영상으로 확인해보자. #난마돌 #태풍 #일본",
"video_id": "Be0D3w0LKSg"
}
| 8
|
[
"The frame shows a flooded area with muddy water flowing onto the floor. There is a partially visible door on the left, and a machine or box with a control panel on the right. The text at the bottom asks, \"일본의 모습?\" which translates to \"The appearance of Japan?\"",
"The current frame shows a scene with trees and vegetation, likely affected by a typhoon or storm, as indicated by the blurry and foggy atmosphere. The text \"일본에 엄청난 강풍과 호우 피해가 이어졌는데\" translates to \"Japan has been hit by strong winds and heavy rain.\" This suggests that the video is covering the aftermath of a severe weather event in Japan, depicting the environmental impact and the conditions affecting the area.",
"The current frame depicts a view of a cityscape through a rain-streaked window, with heavy rainfall and a stormy atmosphere evident. The text \"건물 외장재들이 날아다니기까지\" translates to \"Even the building's exterior materials are flying around,\" indicating the severity of the storm's impact on structures. The scene shows buildings in the background with apparent damage or debris, highlighting the extent of the storm's effects on the urban environment.",
"The current frame shows the interior of a vehicle, likely a bus, with floodwaters inundating the lower sections of the cabin. The dashboard and seats are partially submerged in water, suggesting that the vehicle is either stationary or moving slowly through the flooded area. A driver is visible in the foreground, possibly navigating or assessing the situation. The text \"연기나 폭우에 대중교통 일부도 마비\" translates to \"Public transportation is also paralyzed due to smoke or heavy rain,\" indicating that the storm's impact extends to disrupting public transport services.",
"The current frame shows a street view with heavy rainfall and a flooded road, where a vehicle is seen driving through the water. The scene suggests ongoing severe weather conditions impacting urban infrastructure. A traffic light is visible in the background, indicating the vehicle is moving through a city intersection. The text \"트위터 @run_udon\" and \"뉴스1TV\" indicates the source of the footage, suggesting it's a news report on the weather event. The text \"우리나라 경상권 대부분 역시 태풍의 강풍 반경 내\" translates to \"Most of the Gyeongsang region in our country is also within the strong wind range of the typhoon,\" highlighting the widespread impact of the typhoon on the region.",
"The current frame shows the interior of a train, where the seats are empty and the windows are closed, indicating a lack of passengers. The text \"한국도 각별한 주의 필요\" translates to \"Special attention is needed in Korea,\" suggesting a warning or caution related to the ongoing weather event. The scene may be showing the effects of the typhoon on public transportation and the precautions being taken. The presence of the text \"뉴스1TV\" indicates that this is part of a news report covering the situation in Korea.",
"The current frame depicts a flooded area inside a vehicle, likely a train, with murky water covering the floor. The water appears to be moving, possibly due to the vehicle's motion, indicating a significant water accumulation. The text \"구독하기\" suggests that the viewer should subscribe, which is likely part of a call to action at the end of the news segment. The focus on the flooded interior underscores the severity of the situation and the impact of the weather event on public transportation, aligning with the previous frame's emphasis on the need for special attention in Korea.",
"The current frame shows a blue screen with the text \"뉴스 TV\" prominently displayed, indicating the end of the news segment. The text suggests the conclusion of the broadcast, aligning with the previous frame's context of a severe weather event affecting public transportation. The focus on the text reinforces the call to action for viewers to subscribe, emphasizing the importance of staying informed about such critical situations."
] |
Be0D3w0LKSg
|
The video depicts the aftermath of a severe weather event, specifically a typhoon, that has hit Japan and is also affecting Korea. The footage shows flooded areas, damaged buildings, and disrupted public transportation, including buses and trains inundated with water. The storm's strong winds and heavy rainfall have caused significant damage to structures and infrastructure, with debris and exterior materials flying around. The video, which appears to be a news report, highlights the widespread impact of the typhoon on both countries, with a focus on the need for special attention and precautions in Korea. The report features footage of empty trains, flooded roads, and damaged cityscapes, emphasizing the severity of the situation and the importance of staying informed.
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=AXoJU3hRho0",
"video_description": "월요일인 오늘(19일)은 태풍 난마돌 의 영향으로 경상권과 강원영동 지역에 강한 비바람이 불겠습니다. 태풍14호 난마돌은 오늘(19일) 오전 3시 현재 일본 가고시마 북북서쪽 약 140km 해상에서 시속 17km로 북진할 것으로 예측되는데요.",
"video_id": "AXoJU3hRho0"
}
| 8
|
[
"The image is a weather map showing a storm system moving over the East Asian region, including parts of North Korea and Japan. The map indicates that the storm is currently about 140 kilometers north of Hakodate, Japan, and is moving southwest at a speed of 17 kilometers per hour. The temperatures range from 13°C to 27°C across various regions.",
"The current frame shows a powerful storm surge hitting a coastal area with a large wave crashing over a breakwater. Several fishing boats are anchored in the harbor, and a red lighthouse is visible on the left side. The text in the image provides information in Korean about the storm's strength and direction: \"오늘 오전 9시 세력이 '강' 상태로 다소 약화되며, 부산 남동쪽 약 220km 부근 육상으로 진출 후,\" which translates to \"This morning at 9 AM, the force slightly weakened to 'strong' status, and is moving towards the land near about 220km southeast of Busan.\" The weather condition appears severe, indicating the storm's impact on the coastal region.",
"The current frame is a satellite image of a coastal region, with detailed geographic markings in Korean. The map highlights various islands and coastal areas, indicating a focus on the geographical layout and possibly the impact of the storm mentioned in the previous frame. The image likely serves as a context or reference point to show the areas affected by the storm surge. The text in the image is not directly visible, so it does not provide specific details about the current weather condition or storm status. The map shows the relative positions of islands and mainland areas, providing a broader perspective on the coastal geography.",
"The current frame continues to display a satellite image of a coastal region with detailed geographic markings in Korean. This map provides a broader perspective on the coastal geography, highlighting various islands and coastal areas. The image serves as a reference point to show the areas affected by the storm surge. The text in the image is not directly visible, so it does not provide specific details about the current weather condition or storm status.",
"The current frame shows a massive wave crashing onto the shore, likely illustrating the impact of a storm surge or strong wave activity. The scene depicts the power of the ocean, with the wave forming a crest and spray, suggesting strong wind conditions and significant water displacement. The text in Korean indicates heavy rain, strong winds, and expected rain and wind conditions (50~100mm), reinforcing the severe weather conditions depicted. This frame connects to the previous map by visualizing the actual effects of the storm mentioned on the coastal areas.",
"The current frame features a clear sky with scattered clouds, suggesting a calm and sunny day. A road is visible with streetlights along the side and a barrier on the right, indicating an urban or suburban setting. The text in Korean at the bottom of the frame indicates a context of an ASMR video with a one-minute interval, implying a focus on audio experiences. This frame seems unrelated to the severe weather conditions depicted in the previous frame, possibly serving as a contrast to illustrate different weather states.",
"The image shows a weather map highlighting severe weather conditions with wind and temperature data across different regions. The text at the bottom provides information about the expected highest and lowest temperatures from the 25th, indicating a forecast for the upcoming weather. This frame contrasts with the previous frame, which showed a calm day, to illustrate the diverse weather states being discussed in the video.",
"In this frame, a woman appears to be presenting or speaking, as indicated by the text next to her which suggests a formal or educational context. The setting is simple, with a plain background, focusing attention on her and the text. The video may be transitioning from discussing severe weather conditions to addressing a different topic or providing additional information relevant to the audience."
] |
AXoJU3hRho0
|
A severe storm system is moving over the East Asian region, affecting parts of North Korea and Japan, bringing powerful storm surges and strong winds to coastal areas. The storm's impact is visualized through satellite images and footage of massive waves crashing onto shores, with text providing updates on the storm's strength, direction, and expected weather conditions. The video also contrasts the severe weather with a calm and sunny day, before transitioning to a discussion or educational segment featuring a woman presenter, possibly providing more information on the weather or a related topic.
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=MYkG8SmCWNo",
"video_description": "국제우주정거장에서 포착된 제14호 태풍 '난마돌'의 모습이 공개됐습니다. 소용돌이치는 거대한 구름 덩어리 한가운데로 뚜렷한 태풍의 눈이 보입니다. 미국 항공우주국, 나사 소속 우주 비행사인 밥 하인스가 18일, 트위터에 공개한 사진들인데요. 하인스는 국제우주정거장에서 찍은 난마돌의 사진 3장을 올리며, \"태풍 난마돌 경로에 있는 모든 사람들의 안전을 위해 기도한다\"고 적었습니다. https://imnews.imbc.com/replay/2022/nwtoday/article/6408956_35752.html #태풍, #난마돌, #국제우주정거장",
"video_id": "MYkG8SmCWNo"
}
| 8
|
[
"The frame shows a news broadcast screen with a world map in the background. The focus is on a headline that reads \"이 시각 세계\" (World at This Moment). Additional text indicates a segment on North Korea's 'Nanmadol' missile launch and a global temperature overview. The date and time, \"19 월 6:49,\" are displayed, and there's mention of a news channel with the ID \"mbc.\" A scrolling news ticker at the bottom discusses China and a temperature indicator showing \"26°\" with a sunny icon.",
"The current frame shows a news broadcast in progress, featuring a female news anchor standing in a newsroom. The background is filled with desks, computers, and office equipment, indicating a busy newsroom setting. The headline at the bottom of the screen reads \"우주에서 본 태풍 '난마돌'\" (Typhoon Nanmadol as seen from space), suggesting the news segment is discussing the typhoon. The date and time in the top right corner are \"19 월 6:49,\" and there is a news ticker with the text \"뉴스 투데이\" (News Today), along with a weather update showing \"29°\" and a sunny icon.",
"The news broadcast continues, now showing a dramatic view of Typhoon Nanmadol as seen from space. The image captures the massive storm system, with its eye clearly visible against the backdrop of Earth's curvature. The headline at the bottom of the screen reiterates \"우주에서 본 태풍 '난마돌'\" (Typhoon Nanmadol as seen from space). The date and time have changed to \"19 (월) 6:49,\" and the weather update now shows \"서울 23°\" (Seoul 23°) with a partly cloudy icon. The news ticker at the bottom continues to display \"뉴스 투데이\" (News Today) and additional information about the typhoon's impact and weather conditions.",
"The video presents a detailed aerial view of Typhoon Nanmadol, focusing on its swirling cloud formations and the central eye of the storm. The headline remains \"우주에서 본 태풍 '난마돌'\" (Typhoon Nanmadol as seen from space). The date and time are displayed as \"19 (월) 6:49,\" and the weather update still shows \"서울 23°\" (Seoul 23°) with a partly cloudy icon. The news ticker at the bottom continues to provide updates, indicating the typhoon's speed as 15 km/h and its impact on SSG, with details on power outages and LG's response.",
"The current frame features a tweet by Bob \"Farmer\" Hines, an astronaut, displaying images of Typhoon Nanmadol from space. The tweet reads, \"It's incredible how something that seems so beautiful from space can be so terrible on Earth...Praying for the safety of those in the path of Typhoon Nanmadol.\" The visuals show the storm's eye and cloud patterns, highlighting the contrast between its serene appearance from above and its destructive potential on the ground. The headline \"국제우주정거장서 포착한 난마돌 모습 공개\" (Images of Nanmadol captured from the International Space Station) is visible, along with the date and time \"19 (월) 6:50.\" The weather ticker indicates a slight increase in temperature to \"25°\" in Changwon, with a rain icon. The frame continues to emphasize the typhoon's impact and the importance of monitoring and preparedness.",
"The current frame features a tweet by Bob \"Farmer\" Hines, an astronaut, displaying images of Typhoon Nanmadol from space. The tweet reads, \"It's incredible how something that seems so beautiful from space can be so terrible on Earth...Praying for the safety of those in the path of Typhoon Nanmadol.\" The visuals show the storm's eye and cloud patterns, highlighting the contrast between its serene appearance from above and its destructive potential on the ground. The headline \"국제우주정거장서 포착한 난마돌 모습 공개\" (Images of Nanmadol captured from the International Space Station) is visible, along with the date and time \"19 (월) 6:50.\" The weather ticker indicates a slight increase in temperature to \"27°\" in Jinju, with a rain icon. The frame continues to emphasize the typhoon's impact and the importance of monitoring and preparedness.",
"The current frame shows a satellite view of Typhoon Nanmadol from the International Space Station, capturing the storm's vast and swirling cloud patterns. The image highlights the typhoon's eye, which is a key indicator of the storm's strength. The text in the frame, \"난마돌, 일본 상륙\" (Nanmadol, landfall in Japan), indicates that the typhoon is making landfall in Japan, emphasizing its ongoing impact. The date and time \"19 (월) 6:50\" are visible, along with a weather update showing a temperature of \"26°\" with a cloud icon, suggesting cloudy weather conditions. The visuals continue to stress the importance of monitoring and preparedness for those affected by the typhoon.",
"The current frame shows a ceremonial event taking place inside a grand hall, featuring guards in traditional red and gold uniforms standing at attention. A coffin draped in a purple cloth with a golden emblem is placed on a red carpet, suggesting the presence of a high-ranking individual. The text in the frame reads \"서해5도 강풍주의보\" (Yellow Sea 5th Island, strong wind warning) and \"제보 카톡ID: mbc 제보\" (Report Kakao ID: mbc report), indicating that the footage is being broadcast by MBC News. The date and time \"19 (월) 6:50\" are visible, along with a news update about a sports event, \"프로축구 '김영빈 2골·김대원 2도움' 강원FC, 3년 만의 파이널A 진출\" (Pro Soccer 'Kim Young-bin 2 goals, Kim Dae-won 2 assists' Gangwon FC, advancing to Final A after 3 years). The scene captures the solemnity and formality of the event, set against a backdrop of ongoing news coverage."
] |
MYkG8SmCWNo
|
A news broadcast on MBC News covers multiple stories, including the launch of North Korea's 'Nanmadol' missile and a global temperature overview. The main focus, however, is on Typhoon Nanmadol, with footage of the storm from space, showing its massive size and swirling cloud formations. The news anchor provides updates on the typhoon's progress, including its speed, impact, and landfall in Japan. The broadcast also features a tweet from astronaut Bob "Farmer" Hines, highlighting the contrast between the storm's beauty from space and its destructive potential on Earth. Additionally, the broadcast cuts to a ceremonial event, possibly a state funeral, with a coffin and guards in traditional uniforms, before returning to news updates, including a strong wind warning for the Yellow Sea and a sports report on Gangwon FC's advancement to Final A. The video provides a snapshot of current events, emphasizing the importance of monitoring and preparedness for natural disasters like Typhoon Nanmadol.
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=waVeQcHP3f0",
"video_description": "\"우리나라에 미치는 영향은 그대로\"…강한 비바람 태풍 ’난마돌’, 매우 강한 위력 유지한 채 북상 비보다는 바람 강한 태풍…영남 해안에 집중호우 제주도와 영남 해안, 울릉도·독도에 35㎧ 돌풍 [앵커] 북상 중인 14호 태풍 '난마돌'의 진로가 동쪽으로 조금 더 치우치는 것으로 분석됐습니다. 하지만 태풍의 세력이 워낙 강해 제주도와 해안가에는 여전히 비바람 피해가 우려됩니다. 취재 기자 연결해 자세한 태풍 상황 알아보겠습니다. 김진두 기자! 태풍이 일본 쪽으로 더 치우쳐 이동한다는 건데, 그래도 강한 비바람은 그대로 유지된다는 거죠? [기자] 네, 그렇습니다. 기상청은 오늘 오전 브리핑에서 태풍 진로가 미세하게 조정됐다고 밝혔습니다. 태풍이 내일 새벽쯤 일본 규슈 북부에 상륙하는 건 그대로지만, 진로가 약간 더 동쪽으로 움직인다는 겁니다. 우리나라로부터 거리가 더 멀어지는 것이지만, 비바람 예보는 그대로 유지됐습니다. 태풍이 '매우 강한' 위력을 지닌 채 북상하기 때문인데요, 우선 바람이 무척 강하게 불겠고 영남 해안과 영동에는 집중호우도 예상되고 있습니다. 기상청은 제주도와 영남 해안, 그리고 울릉도·독도에 순간 최대 풍속이 35m에 달하는 돌풍이 불겠다고 밝혔습니다. 그 밖의 해안가와 경남 내륙에도 최고 초속 25m, 내륙 지방에도 초속 15m의 순간적인 강풍이 예상됩니다. 비는 영남 해안과 영동지방, 그리고 울릉도, 독도에 50~100mm가 오겠고, 특히 영남 해안에는 150mm가 넘는 호우가 쏟아질 것으로 보입니다. 기상청은 이번 태풍의 고비가 오늘 밤부터 내일 오전 사이가 되겠고, 제주도와 해안가에는 폭풍해일이나 월파 가능성도 있다며 철저한 대비를 당부했습니다. 지금까지 YTN 김진두입니다. YTN 김진두 ([email protected]) ※ '당신의 제보가 뉴스가 됩니다' [카카오톡] YTN 검색해 채널 추가 [전화] 02-398-8585 [메일] [email protected] ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0108_202209181259028146 ▶ 제보 하기 : https://mj.ytn.co.kr/mj/mj_write.php ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN 무단 전재 및 재배포금지",
"video_id": "waVeQcHP3f0"
}
| 8
|
[
"The current frame shows two news anchors sitting at a news desk, delivering a weather report. Behind them is a graphic of a satellite image showing a hurricane or typhoon, suggesting that the topic is a tropical cyclone. The text at the bottom of the screen in Korean translates to \"Typhoon 'Namtheun' moves further east... 'We are watching the situation closely'\". The news channel is YTN, and the program is \"News Wide\".",
"The current frame shows the two news anchors continuing their weather report, with the satellite image of the typhoon still prominently displayed behind them. The text at the bottom of the screen remains the same, indicating ongoing updates about Typhoon 'Namtheun'. The anchors appear focused on providing detailed information about the typhoon's movements and potential impacts.",
"The current frame continues with the weather report, now showing two maps highlighting the typhoon's projected path. The left map illustrates Typhoon 'Namtheun' moving eastward, with a path marked and a red 'X' indicating its forecasted trajectory. The text above the map reads '태풍 '난마돌' 동쪽으로 '우리나라 영향은 비슷'' ('Typhoon 'Namtheun' moving eastward, similar impact on our country'). The right map details the typhoon's anticipated changes, with a pink and blue path and arrows indicating shifts. Below, the text states '14호 태풍 '난마돌' 예상 진로' ('Forecasted path of Typhoon 'Namtheun' No. 14'). The 'YTN' logo is visible in the top right corner, indicating the news channel. The focus is on the detailed analysis of the typhoon's path and potential effects.",
"The current frame shows a weather station or coastal observation area, capturing the effects of the approaching Typhoon 'Namtheun'. The scene depicts rough seas with waves crashing against the rocky shore, illustrating the storm's impact. A few people are seen standing near the edge, observing the stormy conditions. The text above the image reiterates that Typhoon 'Namtheun' is moving eastward and will have a similar impact on the country. The 'YTN' logo is still visible, suggesting the news channel is continuing to cover the storm's developments.",
"The video shows a white SUV driving on a wet road amidst heavy rainfall. The windshield wipers are in motion, and raindrops are visible on the windshield, indicating severe weather conditions. The background shows a hilly landscape with trees and a fence. Text at the top of the frame reads, \"태풍 '난미돌' 동쪽으로 '우리나라 영향은 비슷'\" which translates to \"Typhoon 'Namtheun' moving eastward, impact on our country is similar.\" Text at the bottom of the frame reads, \"비보다는 바람 강한 태풍...영남 해안에 집중호우\" which translates to \"A typhoon with stronger wind than rain...Heavy rain concentrated on the southeastern coast.\" The 'YTN' logo is visible in the upper right corner, indicating the news channel covering the storm's impact.",
"The video shows a scene of heavy rainfall in an area with boats docked at a harbor. The boats are secured with ropes and equipped with floats, indicating they are moored in place due to the severe weather conditions. The background shows a hilly landscape with trees and buildings. Text at the top of the frame reads, \"태풍 '난미돌' 동쪽으로 '우리나라 영향은 비슷'\" which translates to \"Typhoon 'Namtheun' moving eastward, impact on our country is similar.\" Text at the bottom of the frame reads, \"강한\" which translates to \"strong.\" The 'YTN' logo is visible in the upper right corner, indicating the news channel covering the storm's impact.",
"The scene continues to depict the severe weather conditions, with heavy rain and wind affecting an urban area. Trees are being tossed around by the powerful gusts, and red traffic lights are visible, suggesting the area is experiencing disruptions due to the storm. The text at the top of the frame reads, \"태풍 '난미돌' 동쪽으로 '우리나라 영향은 비슷'\" which translates to \"Typhoon 'Namtheun' moving eastward, impact on our country is similar.\" The text at the bottom of the frame reads, \"'힌남노' 피해 쌓인 영남 해안에 최고 150mm 호우\" which translates to \"'Hinnamno' accumulation of damage, highest 150mm rainfall in Yeongnam coast.\" The 'YTN' logo is visible in the upper right corner, indicating the news channel covering the storm's impact.",
"The current frame shows a group of people, likely seeking shelter from the ongoing heavy rain, huddled under a large blue umbrella marked \"Energy Group.\" They appear to be taking cover behind a protective barrier near a building. The wet ground and the heavy downpour suggest the storm's intensity is continuing to affect the urban area, as indicated in the previous frames. The 'YTN' logo remains visible, maintaining the continuity of the news report on the storm's impact."
] |
waVeQcHP3f0
|
A news report on YTN's "News Wide" program covers Typhoon 'Namtheun' as it moves eastward, with the anchors providing detailed updates on its projected path and potential impacts. The typhoon brings severe weather conditions, including heavy rainfall and strong winds, affecting various areas, particularly the southeastern coast. The report shows rough seas, waves crashing against the shore, and people observing the storm. It also captures the typhoon's impact on urban areas, with heavy rain, strong winds tossing trees, and disruptions to daily life. The news channel continues to monitor the situation, providing updates on the storm's trajectory and the accumulation of damage, especially in the Yeongnam coast region, where the highest rainfall is expected to reach 150mm. Throughout the report, the focus remains on the typhoon's effects, the news channel's ongoing coverage, and the public's response to the severe weather conditions.
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=umbAs-igFhc",
"video_description": "역대급 세력을 지닌 14호 태풍 '난마돌'이 일본에 상륙하면서 우리나라 남해와 동해 상은 물론 영남 해안에도 태풍 경보가 내려졌습니다. 현재 부산과 울산 등 태풍 특보 지역에는 초속 30m 안팎의 돌풍이 불고 있어 강풍 피해가 우려됩니다. 또 포항과 경주에는 산사태 주의보가 발령 중 입니다. 기상청은 14호 태풍 '난마돌'이 어제 저녁 일본 가고시마 남쪽에 상륙한 뒤 태풍의 세력이 매우 강에서 강한 강도로 한 단계 약화했다고 밝혔습니다. 하지만 중심 기압은 여전히 955 헥토파스칼로 강한 세력을 유지하고 있고, 중심 부근에는 초속 40m 돌풍이 몰아치고 있습니다. 특히 강풍 반경이 400km로 넓어 우리나라 남해와 동해상은 물론, 부산과 울산, 포항, 경주 등 영남 해안에도 태풍경보가 발령 중입니다. 기상청은 오늘 영남 해안에는 초속 25에서 35m의 돌풍이 불고, 영남 해안과 영동, 울릉도 독도에는 최고 100mm의 호우가 예상된다고 밝혔습니다. 특히 해상에는 최고 10m의 높은 파도가 일겠고, 해안가에는 월파나 폭풍해일 가능성이 크다며 철저한 대비를 당부했습니다. YTN 정혜윤 ([email protected]) ※ '당신의 제보가 뉴스가 됩니다' [카카오톡] YTN 검색해 채널 추가 [전화] 02-398-8585 [메일] [email protected] ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0108_202209190411440551 ▶ 제보 하기 : https://mj.ytn.co.kr/mj/mj_write.php ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN 무단 전재 및 재배포금지",
"video_id": "umbAs-igFhc"
}
| 8
|
[
"The frame shows a nighttime urban scene with a street and crosswalk. The area is dimly lit, primarily by streetlights. There's text in Korean at the bottom of the screen, which appears to provide information or context about the scene. A building with stone walls and a gate can be seen in the background, and there are trees lining the street. The scene is quiet with no visible people or vehicles.",
"The scene continues at night in the same urban setting, still dimly lit by streetlights. The camera angle slightly shifts to the right, revealing more of the street and sidewalk. The Korean text at the bottom of the screen continues to provide context. In the foreground, a road sign is visible, indicating caution for a sharp turn. A building with a yellowish facade is now more prominent on the right side. The area remains quiet, without any visible pedestrians or vehicles, suggesting a tranquil night in the city.",
"The scene remains set at night in the urban area, with the camera maintaining a focus on the road and sidewalk illuminated by streetlights. The Korean text at the bottom of the screen persists, offering ongoing context. The road sign indicating a sharp turn is still visible in the foreground, and the building with a yellowish facade continues to be prominent on the right. The tranquility of the night remains, with no pedestrians or vehicles in sight.",
"The scene continues in the urban night setting, featuring a residential area with multiple illuminated windows on buildings. The camera is positioned to show a gated area with a prominent red gate. Korean text appears at the bottom of the screen, providing context. The presence of light fixtures and windows suggests a typical urban residential environment, maintaining the nocturnal ambiance without showing any pedestrians or vehicles.",
"The current frame features emergency personnel in a nighttime setting. The individuals, dressed in uniform and helmets, are actively working on a task, likely related to an emergency response. Korean text at the bottom of the screen provides context, although it is not fully clear. The scene indicates a coordinated effort in a potentially urgent situation, with the focus on the emergency workers' actions.",
"In this frame, emergency personnel are seen actively working on a structure at night. They are using tools, possibly cutting or breaking through a material, as indicated by the bright light source and their focused actions. The Korean text at the bottom of the screen provides context, mentioning the '기상청 영남 해안 초속 35m 돌풍, 최고 100mm 호우' which translates to 'Meteorological Agency, Gyeongsang region coastal area, 35 m/s wind gusts, up to 100mm heavy rain.' This suggests that the emergency response is likely related to severe weather conditions. The scene continues to highlight the coordinated effort of the emergency workers in addressing the situation.",
"The current frame shows emergency personnel continuing their work on the structure at night. They are using tools, likely cutting or breaking through a material, as suggested by the bright light source and their focused actions. The Korean text at the bottom of the screen remains, translating to 'Meteorological Agency, Gyeongsang region coastal area, 35 m/s wind gusts, up to 100mm heavy rain.' This reinforces that the emergency response is related to the severe weather conditions previously mentioned. The scene maintains the depiction of the coordinated effort of the emergency workers in addressing the situation.",
"The current frame depicts a building with a large tear in its side, indicating significant damage. Emergency personnel are not visible in this frame. The Korean text at the bottom of the screen continues to read '기상청 영남 해안 초속 35m 돌풍, 최고 100mm 호우,' which translates to 'Meteorological Agency, Gyeongsang region coastal area, 35 m/s wind gusts, up to 100mm heavy rain.' This suggests that the damage to the building is likely a result of the severe weather conditions. The scene focuses on the aftermath of the storm, highlighting the extent of the damage caused by the heavy rain and strong winds."
] |
umbAs-igFhc
|
The video depicts a nighttime urban scene in a residential area that transitions from a tranquil setting to an emergency response situation due to severe weather conditions. Initially, the scene shows a quiet, dimly lit street with no visible pedestrians or vehicles, setting a peaceful ambiance. As the video progresses, it cuts to emergency personnel actively working on a task, likely related to an emergency response, with a focus on their coordinated efforts. The context provided by the Korean text at the bottom of the screen indicates that the emergency response is due to severe weather conditions, specifically 35 m/s wind gusts and up to 100mm of heavy rain in the Gyeongsang region coastal area. The emergency workers are seen using tools to cut or break through a material, suggesting they are addressing damage caused by the storm. The final frame shows a building with significant damage, a large tear in its side, which is likely a result of the severe weather conditions. Overall, the video captures the impact of severe weather on an urban area and the subsequent emergency response efforts.
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=fxLzed6AI2Q",
"video_description": "제14호 태풍 난마돌이 일본 규슈 남부에 상륙했습니다. 일본 기상청은 어제 저녁 7시쯤 태풍이 규슈 남부 가고시마 시 부근에 상륙했다고 발표했습니다. 기상청은 이번 태풍이 규슈 서부 내륙을 따라 북상해 오늘 오전 규슈 북부에서 북동쪽으로 방향을 꺾어 이동할 것으로 예보했습니다. 태풍은 일본 열도를 관통해 오는 21일 오후 홋카이도 동쪽 해역으로 빠져나갈 전망입니다. 일본 기상청은 이번 태풍이 \"지금까지 경험한 적 없는 위험한 태풍\"으로 수십 년에 한 번 있을 만한 대규모 재해가 발생할 가능성이 있다며 각별한 대비를 당부했습니다. 오늘 낮까지 하루 동안 규슈 남부에 최고 500mm, 규슈 북부와 시코쿠에 최고 400mm의 많은 비가 예보돼 있습니다. 한편 가장 먼저 태풍 영향권에 들어선 일본 규슈 남부 지역을 중심으로 10여 명이 강풍에 넘어져 다치는 등 피해가 이어지고 있습니다. 규슈 지역 각 지자체는 주민들을 대상으로 안전한 곳으로 신속히 이동할 것을 권하는 '피난 지시'를 내리는 등 만일의 사태에 대비하고 있습니다. 일본 정부는 재해대책본부를 설치하고 태풍의 움직임과 주민 대피 상황, 그리고 피해 집계 등에 나섰습니다. 기시다 총리는 관계 각료회의를 소집해 국민에게 \"최신 기상 정보와 피난 정보에 주의해 신속히 생명을 지키는 행동을 해달라\"고 촉구했습니다. YTN 이경아 ([email protected]) ※ '당신의 제보가 뉴스가 됩니다' [카카오톡] YTN 검색해 채널 추가 [전화] 02-398-8585 [메일] [email protected] ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0104_202209190251207843 ▶ 제보 하기 : https://mj.ytn.co.kr/mj/mj_write.php ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN 무단 전재 및 재배포금지",
"video_id": "fxLzed6AI2Q"
}
| 8
|
[
"A news anchor is presenting a report on a weather-related event. The background displays an animated image of turbulent ocean waves and a storm, along with a map of Japan highlighted in red. The text at the bottom indicates a typhoon named Nanmadol and its impact on Japan, with specific weather conditions like strong winds and heavy rain.",
"The current frame shows a foggy, overcast landscape with dense clouds, suggesting adverse weather conditions. The text at the bottom reads \"난마돌 日규슈 상륙...기록적 강풍·호우 피해 속출,\" which translates to \"Nanmadol makes landfall in Japan...Record-breaking strong winds and heavy rain causing widespread damage.\" The weather conditions depicted are consistent with the severe impact of Typhoon Nanmadol mentioned in the previous frame.",
"The current frame shows a view of a building with parts of its roof and debris scattered around, indicating damage likely caused by strong winds. The surrounding environment includes trees and a road, with the weather still appearing overcast. The text at the bottom reads \"난마돌 日규슈 상륙...기록적 강풍·호우 피해 속출,\" translating to \"Nanmadol makes landfall in Japan...Record-breaking strong winds and heavy rain causing widespread damage.\" The damage to the building and the debris align with the severe impact of Typhoon Nanmadol described in the previous frames.",
"The current frame shows a building with significant structural damage, with broken debris scattered around. The surrounding area appears to be under a yellow caution tape, indicating restricted access due to the damage. The text at the bottom reads \"난마돌 日규슈 상륙...기록적 강풍·호우 피해 속출,\" translating to \"Nanmadol makes landfall in Japan...Record-breaking strong winds and heavy rain causing widespread damage.\" The damage to the building and the presence of caution tape align with the severe impact of Typhoon Nanmadol described in the previous frames.",
"The video displays a scene of trees and utility poles heavily affected by strong winds. The trees are bent and the poles are swaying, indicating the force of the wind. The text at the bottom reads \"난마돌 日규슈 상륙...기록적 강풍·호우 피해 속출,\" which translates to \"Nanmadol makes landfall in Japan...Record-breaking strong winds and heavy rain causing widespread damage.\" This reinforces the severity of the typhoon's impact as seen in the previous frames.",
"The current frame captures a heavily affected urban street scene, likely due to a typhoon. The scene is shrouded in heavy rain and strong winds, creating a misty and chaotic atmosphere. The street is empty, with no visible pedestrians or vehicles, suggesting a state of emergency or evacuation. Utility poles and wires are visible, some appearing to be damaged or bent, indicating the destructive power of the storm. Buildings are partially obscured by the rain and mist, emphasizing the intensity of the weather conditions. The text at the bottom of the image reiterates the impact of the typhoon, \"난마돌 日규슈 상륙...기록적 강풍·호우 피해 속출,\" which translates to \"Nanmadol makes landfall in Japan...Record-breaking strong winds and heavy rain causing widespread damage,\" reinforcing the severity of the situation and connecting it to the previous frames.",
"The current frame continues to depict the aftermath of a severe typhoon on an urban street, maintaining the chaotic and misty atmosphere. The street remains empty, reinforcing the sense of emergency or evacuation. The focus shifts to the impact on residential buildings and infrastructure, as seen by the large, closed shutters of a storefront, likely a business that has been forced to close due to the storm. Several bags and possibly debris are scattered on the wet pavement, hinting at the destructive force of the typhoon. The presence of a bicycle leaning against the building indicates a temporary halt in activity, possibly due to the storm. The text at the bottom of the image, \"난마돌 日규슈 상륙...기록적 강풍·호우 피해 속출,\" remains consistent, reiterating the widespread damage and the record-breaking nature of the storm, tying the current scene to the ongoing narrative of the typhoon's impact.",
"The current frame depicts the aftermath of a severe typhoon in a residential area, maintaining the chaotic and misty atmosphere. The scene shows a building with windows, likely a residential home, with visible damage. A tree is leaning precariously, indicating the force of the storm. Debris, including a fallen roof or part of a structure, is scattered on the ground, highlighting the destructive impact of the typhoon. The text at the top of the image, \"영상출처: 트위터@fudousanou,\" suggests that this footage is sourced from a Twitter account, providing context to the authenticity of the video."
] |
fxLzed6AI2Q
|
A news report covers the impact of Typhoon Nanmadol making landfall in Japan, causing record-breaking strong winds and heavy rain that result in widespread damage. The video depicts the storm's effects on various locations, including a building with its roof torn off, trees bent by the wind, and utility poles swaying or broken. Urban streets are shown empty and shrouded in heavy rain and mist, with damaged infrastructure and debris scattered around. Residential areas are also affected, with closed businesses, damaged homes, and fallen trees. The footage, sourced from social media, showcases the severity and destructive power of the typhoon, emphasizing the emergency situation and the significant damage caused by Nanmadol's landfall in Japan.
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=tVUSMdbETuE",
"video_description": "오늘도 맑은 하늘 보긴 어렵겠습니다. 중국으로 향하는 태풍 '무이파'의 간접영향으로 오전까지 서쪽 지방에는 약한 비가 내리겠는데요, 비의 양이 적어서 낮 동안 활동하시는 데 큰 불편함은 없겠습니다. 때아닌 늦더위도 계속되겠습니다. 오늘 서울이 한낮에 28도, 광주가 31도까지 오르는 등 어제보다 높아 다소 덥겠습니다. 서울 등 수도권은 낮부터 비가 그치고 점차 갤 것으로 보입니다. 오늘 낮 기온은 예년보다 1∼4도가량 높겠고, 특히, 호남 지방을 중심으로 기온이 크게 오르겠습니다. 서울 28도, 전주 30도, 광주 31도가 예상됩니다. 다가오는 주말에는 서울 낮 기온이 30도까지 오르는 등 늦더위가 기승을 부리겠고요, 제주도와 동쪽 지방을 중심으로 비가 내릴 전망입니다. 한편, 오늘 오전 3시쯤, 일본 오키나와 동쪽 해상에서 제14호 태풍 '난마돌'이 발생했습니다. 이 태풍은 세력이 강해지면서 느리게 북상해 다음 주 월요일, 서귀포 남동쪽 약 280km 부근 해상까지 올라오겠습니다. 이후 진로는 유동적이지만, 일본 규슈 부근이나 대한해협으로 이동할 가능성이 있습니다. 앞으로 발표되는 태풍 정보를 잘 확인해주시기 바랍니다. 현재, 태풍 '무이파'의 간접 영향으로, 제주도와 남해안에는 '강풍주의보'가, 대부분 해상에는 '풍랑주의보'가 발효 중입니다. 내륙은 비가 대부분 그쳤지만 동해안과 제주도에는 비가 더 내릴 가능성 있는 만큼 시설물 관리와 해안가 안전사고에 각별히 유의하시기 바랍니다. 지금까지 YTN 원이다입니다. YTN 원이다 ([email protected]) ※ '당신의 제보가 뉴스가 됩니다' [카카오톡] YTN 검색해 채널 추가 [전화] 02-398-8585 [메일] [email protected] ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0108_202209141027402664 ▶ 제보 하기 : https://mj.ytn.co.kr/mj/mj_write.php ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN 무단 전재 및 재배포금지",
"video_id": "tVUSMdbETuE"
}
| 8
|
[
"A woman in a purple dress is holding a microphone labeled \"YTN NEWS.\" She appears to be reporting outdoors, with trees and a street in the background. The text on the screen indicates that she is reporting on a topic related to a new 14-hour program called \"Randoms.\"",
"The woman continues to report, maintaining her position outdoors with trees and a street visible in the background. The text on the screen now highlights that the new 14-hour program \"Randoms\" is being released. The context suggests she is delivering news or updates about the program's launch.",
"The scene shifts to a bustling outdoor area where people are walking and sitting, possibly a public space or plaza. A large, colorful cartoon character stands in the foreground, while weather information is displayed on the screen. The text indicates temperatures across different locations in the country. The context suggests the video is providing a weather update for various regions.",
"The video now shows a busy street intersection with numerous pedestrians crossing and walking along the sidewalks. In the background, buildings and a green bus can be seen. The weather information continues to be displayed, showing temperatures and conditions for different days, indicating a focus on the forecast for the upcoming week. The scene suggests a typical day in a city with people going about their daily activities, while the video provides ongoing weather updates.",
"The video shows a rainy street scene with a focus on a large tree in the foreground. A white SUV is visible driving through the rain on the road. The weather map in the background continues to display information about Typhoon Nanmadol's path and trajectory, with red and blue overlays indicating different areas affected. The text on the map includes details such as \"제14호 태풍 난마돌\" and \"현재,\" suggesting that the video is providing an update on the typhoon's impact and movement. The scene captures the rainy conditions and the ongoing weather forecast, maintaining the focus on the typhoon's trajectory and its effects on the area.",
"The video presents a view of the ocean with waves crashing against the rocks, indicating the impact of the weather. A weather map overlay is prominently displayed, showing the path of Typhoon Nanmadol. The text on the map reads \"제14호 태풍 난마돌\" and \"현재,\" indicating the typhoon's current status and path. The background features the ocean and the rocky coastline, with no people or vehicles visible, focusing entirely on the natural elements affected by the typhoon. The scene maintains the theme of the typhoon's impact, transitioning from urban to natural settings.",
"A news anchor in a pink dress stands outdoors, holding a microphone with the YTN logo, reporting on a news story. The background shows a street with trees and vehicles, indicating an urban environment. Text on the screen reads \"제주도 남해안 '강풍주의보' 해상 '풍랑주의보'\" (Jeju Island and the southern coast 'Strong Wind Warning,' maritime 'Marine Wind Warning'), suggesting the news is about weather warnings. A small image of a white vehicle with the YTN logo is also visible at the bottom left.",
"The news anchor continues to report outdoors, maintaining her stance with the microphone. The urban environment remains the backdrop, with visible trees and vehicles. The text on the screen still reads \"제주도 남해안 '강풍주의보' 해상 '풍랑주의보',\" indicating the ongoing weather warnings in Jeju Island and the southern coast. The small image of the white vehicle with the YTN logo is still present at the bottom left."
] |
tVUSMdbETuE
|
A news reporter from YTN NEWS delivers an update on a new 14-hour program called "Randoms" from an outdoor location. The video then transitions to provide a weather update, showing various scenes such as a public space, a busy street intersection, and a rainy street, while displaying temperatures and forecasts for different regions. The focus shifts to Typhoon Nanmadol, with the video showing its impact on both urban and natural environments, including a rainy street and the ocean. A news anchor reports on weather warnings issued for Jeju Island and the southern coast, specifically strong wind and marine wind warnings, as the typhoon affects the area. Throughout the video, the news team provides ongoing updates and information about the weather and its consequences.
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=d6fZyZvF88k",
"video_description": "어젯밤 일본 규슈에 상륙한 태풍 난마돌의 영향으로 수십 명이 다치는 등 피해가 잇따르고 있습니다. NHK는 이번 태풍으로 현재까지 강풍에 넘어져 다치는 등 40여 명이 부상을 입은 것으로 집계됐다고 전했습니다. 이와 함께 태풍 영향권에 있는 지역 주민 약 960만 명에게는 신속한 안전 확보를 요청하는 최고 수준의 재해 경보와 피난 지시 등이 발령됐습니다. 순간최대풍속 50m/s에 이르는 강풍으로 공사용 대형 크레인이 꺾이고 지붕이 날아가는 등 물적 피해도 속출했습니다. 규슈 미야자키에는 지난 15일 이후 1,000mm에 이르는 비가 내리는 등 집중 호우로 인한 도로와 주택 침수도 잇따랐습니다. 많은 비로 하천 수위가 올라가 현재 30여 곳이 범람 위험 수위를 넘어선 것으로 나타났습니다. 일본 국토교통성은 댐 100여 곳의 수문을 미리 열어 범람을 막기 위해 방류를 실시했는데 이런 대규모 방류는 사상 처음입니다. 이와 함께 규슈부터 시코쿠 지역까지 약 31만 가구가 정전됐습니다. 항공과 선박, 철도 등 교통편도 태풍의 영향에서 벗어날 때까지 운행이 대부분 중단됩니다. 규슈 지역을 중심으로 큰 피해를 남긴 태풍 난마돌은 내일 일본 혼슈를 관통해 홋카이도 남쪽 바다로 빠져나갈 전망입니다. 일본 재해 당국은 많은 비가 내린 뒤 토사 붕괴 등 추가 피해가 발생할 가능성에 대비하며 태풍 움직임을 주시하고 있습니다. YTN 이경아 ([email protected]) ※ '당신의 제보가 뉴스가 됩니다' [카카오톡] YTN 검색해 채널 추가 [전화] 02-398-8585 [메일] [email protected] ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0104_202209191047268893 ▶ 제보 하기 : https://mj.ytn.co.kr/mj/mj_write.php ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN 무단 전재 및 재배포금지",
"video_id": "d6fZyZvF88k"
}
| 8
|
[
"The image shows a scene with heavy rain and strong winds. There are palm trees swaying violently, indicating a severe storm. The sky is very cloudy, and visibility is low due to the rain and wind. There is a sheltered area with a roof on the left, where a few people are standing. In the background, there are tall buildings partially obscured by the storm. The text in the image is in Korean, mentioning a typhoon and the rapid increase in wind speed, suggesting dangerous conditions.",
"The scene continues to depict heavy rain and strong winds. The focus is now on a metal structure, possibly part of a construction site, being severely affected by the storm. The structure appears to be damaged, with debris visible around it. In the background, there are more tall buildings, and the overall atmosphere remains stormy. The text in the image reiterates the severe conditions caused by the typhoon, emphasizing the rapid increase in wind speed and the resulting dangers.",
"In the current frame, the severe weather conditions persist, with a person holding a blue umbrella for protection from the heavy rain and strong winds. They are walking near a building entrance, carrying a beige bag, indicating the ongoing impact of the typhoon on daily activities. The environment remains stormy, and the text in the image highlights the rapid increase in wind speed and the potential dangers associated with the typhoon, emphasizing the urgency and severity of the situation.",
"The current frame depicts a nighttime scene with strong wind conditions, as evidenced by the dark, stormy sky and the motion of the camera, suggesting high wind speeds. A person in a reflective vest stands near a fence, possibly a construction worker or a guard, who is attempting to maintain their position despite the weather. The text overlay mentions the rapid increase in wind speed and the potential dangers associated with the typhoon, emphasizing the urgency and severity of the situation. The video highlights the challenges faced by individuals in such harsh weather conditions.",
"The current frame shows a nighttime scene with a vehicle’s perspective driving through heavy floodwaters on a road. The water appears to be rapidly rising, posing a significant danger to the vehicle and its occupants. A submerged green object, likely a car, is seen partially submerged and tilted to the side, indicating the force of the flood. The road is surrounded by a fence and is marked with yellow directional signs, some of which are partially obscured by the water. The text overlay mentions the rapid increase in water levels and the urgency of the situation, highlighting the severe impact of the typhoon.",
"The current frame depicts the aftermath of a severe storm, showing a damaged structure with parts of the roof and walls collapsed. The scene is viewed through what appears to be a metal fence or barrier, indicating the perspective is from a secure location observing the destruction. The text overlay references a typhoon impact, emphasizing the rapid progression of destruction and the urgency of the situation, with mentions of urgency and the potential for further damage.",
"The current frame shows a view from inside a building through a metal fence, looking out at a courtyard where a severe storm, specifically Typhoon Nanmadol, has caused significant damage. The roof of the structure in the courtyard has collapsed, with debris scattered around. The text overlay in Korean discusses the rapid progression of the typhoon's impact, emphasizing the urgency and potential for further destruction.",
"The scene depicts the aftermath of severe flooding caused by Typhoon Nanmadol in a city. The view is from an elevated angle, showing a large body of water rushing through a normally dry urban area, including a bridge and surrounding structures. Palm trees and buildings are visible in the background, with the water level reaching dangerously high, submerging lower areas and posing a significant threat to infrastructure and safety. Streetlights are on, casting a warm glow amidst the overcast and stormy conditions. The text overlay in Korean highlights the severity of the situation and the immediate danger faced by residents and infrastructure."
] |
d6fZyZvF88k
|
The video depicts the severe impact of Typhoon Nanmadol on a city, showing the storm's progression and aftermath. The event begins with heavy rain and strong winds, causing damage to structures and disrupting daily activities. As the storm intensifies, the video shows a person struggling to navigate through the harsh weather, and a construction worker or guard attempting to maintain their position despite the conditions. The typhoon leads to severe flooding, with vehicles driving through rising waters and submerged cars, posing a significant danger to occupants. The video then transitions to the aftermath, showing damaged structures, collapsed roofs, and debris-filled courtyards. The final scenes depict the city's infrastructure severely affected, with large bodies of water rushing through urban areas, submerging lower areas, and threatening safety. Throughout the video, text overlays emphasize the rapid increase in wind speed, the urgency of the situation, and the potential for further destruction, highlighting the severe impact of Typhoon Nanmadol on the city and its residents.
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=ItDO3MSUQRQ",
"video_description": "힌남노의 상처가 채 가시기도 전에 이번에는 제 14호 태풍 '난마돌'이 북상하고 있습니다. 아직 경로는 유동적이지만 기상청은 다음주 월요일쯤 제주도를 향해 북진할 가능성이 있다고 보고 상황을 예의주시하고 있습니다. #가을태풍#태풍#태풍경로#힌남노#난마돌#태풍난마돌#제14호태풍#기상청#므르복#기상정보#이슈픽#자막뉴스 ☞MBN NEWS 구독하기 : https://www.youtube.com/channel/UCG9aFJTZ-lMCHAiO1KJsirg?sub_confirmation=1 ☞MPLAY 구독하기 : https://www.youtube.com/channel/UC84IlgY5HIzxKBZOt8XM5UA?sub_confirmation=1 ☞MBN Entertainment 구독하기 : https://www.youtube.com/channel/UCYyLIlOJyqkAFKlVjzX5img?sub_confirmation=1 ☞MBN 공식 홈페이지 : https://www.mbn.co.kr",
"video_id": "ItDO3MSUQRQ"
}
| 8
|
[
"The image shows a rocky shoreline with turbulent waves crashing against the rocks. The text in Korean at the bottom reads \"제주도에 간접 영향을 주고 있는 상황,\" which translates to \"The situation is indirectly affecting Jeju Island.\"",
"The image shows a calm body of water with a large rope in the foreground. The text in Korean at the bottom reads \"우리나라에 영향을 주진 않을 전망,\" which translates to \"It is expected that it will not have a significant impact on our country.\"",
"The current frame depicts turbulent ocean waves crashing against rocks, indicating a stormy or rough sea. The text in Korean reads \"미국으로네시아 유명 유적지의 이름을 따온 '난마돌'은,\" which translates to \"The famous historical site in Micronesia, 'Nanmadol,' has taken its name.\" This suggests that the video is discussing the influence of a natural phenomenon or event, possibly related to weather or ocean conditions, on a place called Nanmadol in Micronesia.",
"The current frame shows a street filled with debris and dust, likely after an explosion or similar destructive event, suggesting a powerful force at play. The text in Korean reads \"강도 '강은 기차를 탈선시킬 수 있을 정도의 위력,\" which translates to \"The intensity 'Kang' is capable of derailing a train.\" This indicates that the video is discussing a severe weather event or natural phenomenon with significant destructive power, potentially impacting infrastructure such as trains, possibly in relation to the previously mentioned Nanmadol.",
"The current frame is a map depicting the projected path of Typhoon Nanmadol, indicating its expected trajectory and potential impact areas. The map shows the typhoon's path moving towards Japan, with specific times and distances marked for key points such as Kagoshima and Okinawa. The text \"태풍 '난마돌' 예상 경로\" translates to \"Typhoon Nanmadol's projected path,\" and the distances provided highlight the typhoon's approach to various locations in Japan. This frame suggests that the video is continuing its focus on the typhoon, emphasizing its movement and potential risks to affected regions.",
"The current frame shows a rainy night scene on a street with visible snowflakes falling. A news anchor is on the right, wearing a dark blazer and light-colored shirt, appearing to be reporting on the weather conditions. The text in the image mentions a weather forecast for the 19th, indicating that the northwestern part of Japan is expected to have heavy snowfall. The image suggests that the video is providing updates on weather conditions, particularly focusing on the expected snowfall in Japan.",
"The current frame shows a snowy urban street at night, covered in fallen debris and with visible tire tracks, suggesting recent traffic. The text in the image, written in Korean, translates to \"It is said that Nami Island's waves have caused flooding.\" The image indicates the aftermath of a storm with heavy rainfall and possibly strong winds, resulting in debris accumulation and flooding on the streets. The scene is chaotic, reflecting the severe impact of the weather conditions on the area.",
"The current frame depicts a scene of flooding near a bridge, with turbulent water levels reaching up to the railing, indicating severe flooding. The atmosphere is misty, suggesting ongoing heavy rainfall and possibly strong winds. The visible text in the image, \"MBN,\" likely indicates the news channel reporting the event. The scene conveys the aftermath of severe weather conditions, with the flooding significantly impacting the area."
] |
ItDO3MSUQRQ
|
The video depicts the impact and progression of Typhoon Nanmadol, a severe weather event affecting various locations. The typhoon indirectly affects Jeju Island and is expected to have minimal impact on the country, but its influence is significant in other areas, such as Micronesia, where it is named after a famous historical site, Nanmadol. The storm's powerful force is capable of causing destruction similar to derailing a train, as seen in a street filled with debris. The video tracks the typhoon's projected path, showing its trajectory towards Japan, with specific attention to its approach to locations like Kagoshima and Okinawa. As the typhoon moves towards Japan, it brings heavy snowfall to the northwestern part of the country, with news reports covering the weather forecast. The aftermath of the storm is marked by severe flooding, debris-covered streets, and chaotic conditions, significantly impacting areas like Nami Island, where waves cause flooding, and other regions near bridges, where water levels rise dramatically. Overall, the video provides an update on the typhoon's movement and its effects on various regions, highlighting the destructive power of natural phenomena like Typhoon Nanmadol.
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=ZuMemCoZIUY",
"video_description": "북상 중인 제14호 태풍 '난마돌'이 일본 규슈에 상륙할 것으로 보입니다. 기상청은 '난마돌'이 서귀포 남동쪽 먼바다까지 북상한 뒤 급격히 방향을 틀어 다음 주 월요일쯤 일본 규슈에 상륙할 것으로 내다봤습니다. 이후 일본 열도를 따라 계속 북동진할 것으로 보입니다. 따라서 우리나라에 큰 피해를 줄 가능성은 낮아졌지만, 제주도와 남해안, 영남 동해안은 태풍의 직간접적인 영향권에 들어 비바람이 강하게 불 것으로 보입니다. 기상청은 태풍의 진로가 아직은 유동적인 만큼 앞으로 발표되는 태풍 진로에 주의를 기울여 달라고 당부했습니다. YTN 김진두 ([email protected]) #태풍난마돌 #난마돌 #규슈 [YTN 사이언스 기사원문] https://science.ytn.co.kr/program/program_view.php?s_mcd=0082&s_hcd=&key=202209151243393568 [프로그램 제작 문의] [email protected]",
"video_id": "ZuMemCoZIUY"
}
| 8
|
[
"The image shows a news anchor in a studio, presenting a segment titled \"사이언스 투데이\" (Science Today). The text on the screen reads \"기상청 '제14호 태풍 '난마돌' 일본으로 갈 듯'\" which translates to \"Meteorological Agency: 'Typhoon No. 14 'Nanmadol' likely to head towards Japan'\". The background appears to depict a digital interface or control room, suggesting the news topic is related to meteorology or science.",
"The current frame shows a coastal scene with waves crashing against rocky shores. The text in the image repeats the information from the previous frame, \"기상청 '제14호 태풍 '난마돌' 일본으로 갈 듯',\" which indicates that the footage is likely illustrating the impact or path of Typhoon No. 14 'Nanmadol' as it approaches or moves towards Japan. The scene suggests a focus on the weather conditions and the potential effects of the typhoon on the coastline.",
"The current frame continues to depict a coastal scene with waves crashing against large, dark, cylindrical concrete structures. These structures are likely breakwaters designed to protect the shore from the force of the sea. The text in the image, \"기상청 '제14호 태풍 '난마돌' 일본으로 갈 듯',\" reiterates that the footage is illustrating the impact or path of Typhoon No. 14 'Nanmadol' as it approaches or moves towards Japan. The scene maintains a focus on the weather conditions and the potential effects of the typhoon on the coastline, showing the strong waves and turbulent sea that suggest the typhoon's influence on the area.",
"The current frame shows a coastal street scene with cars and buildings, indicating a typical urban environment near the shore. The sky is overcast, suggesting cloudy weather conditions. Palm trees are visible, adding a tropical ambiance to the setting. The text \"기상청 '제14호 태풍 '난마돌' 일본으로 갈 듯'\" is displayed, reinforcing the narrative that Typhoon No. 14 'Nanmadol' is expected to move towards Japan. The presence of palm trees and the calmness of the street suggest that the immediate effects of the typhoon have not yet impacted this area.",
"The current frame displays a close-up view of a palm tree's fronds swaying in the wind, set against an overcast sky. The text on the screen reads \"제주 남해안 태풍 직격 타격 영향권... 강한 비바람 예상,\" indicating that Jeju Island and the southern coast are expected to be directly hit by Typhoon No. 14 'Nanmadol' and that strong winds and heavy rain are anticipated. This reinforces the narrative from the previous frame that the typhoon is approaching the region, and its impact is becoming more imminent.",
"The current frame shows a person in a blue shirt walking near a beach area with a colorful mural in the background. The text on the screen reads \"제주 남해안 태풍 직격 타격 영향권... 강한 비바람 예상,\" indicating that Jeju Island and the southern coast are expected to be directly hit by Typhoon No. 14 'Nanmadol' and that strong winds and heavy rain are anticipated. This reinforces the narrative that the typhoon is approaching the region, and its impact is becoming more imminent.",
"The current frame shows two individuals walking on a street with a blue tarpaulin structure in the background. The text on the screen reads \"진로 아직 유동적...태풍에 대한 경계 유지해야,\" indicating that the trajectory of the typhoon is still uncertain and that people need to maintain their alertness regarding the typhoon. This suggests that despite the earlier anticipation of direct impact, the situation remains unpredictable, and caution is advised.",
"The video presents a scene at a seaside location with a statue of a fisherman in the foreground, suggesting a coastal or maritime theme. The presence of a person sitting and another standing nearby indicates that the location is a public space, possibly a park or a plaza, where people can relax and enjoy the view. The text in the image is not visible, but the context suggests it might be related to the location or the significance of the statue. The overcast sky and the waves crashing against the rocks in the background add to the serene yet dynamic atmosphere of the scene. The overall description of the video is not provided, but the current frame indicates a peaceful moment at a scenic spot by the sea."
] |
ZuMemCoZIUY
|
A news segment titled "Science Today" reports on Typhoon No. 14 'Nanmadol' likely heading towards Japan, as announced by the Meteorological Agency. The video shows various coastal scenes, including waves crashing against rocky shores and breakwaters, illustrating the potential impact of the typhoon. It also depicts urban areas near the shore with overcast skies and palm trees, suggesting a tropical region. As the typhoon approaches, the video shows the effects on the environment, such as strong winds causing palm tree fronds to sway. The narrative warns of a direct hit on Jeju Island and the southern coast, with anticipated strong winds and heavy rain. People are shown going about their daily activities, but with an air of caution, as the trajectory of the typhoon remains uncertain. The video concludes with a serene scene at a seaside location, contrasting with the earlier ominous warnings, highlighting the unpredictable nature of the typhoon's path.
|
On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.
|
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022",
"Cars and vehicles submerged in floodwater during the Seoul floods in Gangnam District, South Korea on 8 August 2022",
"Emergency responders rescuing individuals from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and property damage from floodwaters in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing out flooded homes and businesses in Seoul's Gangnam District after floods on 8 August 2022"
] |
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022 during floods",
"Cars and buses submerged in floodwater during the 8 August 2022 floods in Seoul's Gangnam District, South Korea",
"Emergency responders rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing debris and damaged belongings from their homes after floods in Gangnam District, Seoul, South Korea on 8 August 2022",
"Floodwaters overflowing from rivers and streams in Gangnam District, Seoul, South Korea during the floods on 8 August 2022"
] |
[
"People wading through floodwaters in the streets of Gangnam District Seoul South Korea during the floods on 8 August 2022",
"Cars and buses submerged in water on flooded roads in Gangnam District, Seoul, South Korea during the floods on August 8, 2022",
"Residents evacuating their homes and seeking higher ground in Seoul, South Korea, Gangnam District due to floods on 8 August 2022",
"Emergency responders, such as firefighters and police, rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and damaged furniture floating in the floodwaters during the 8 August 2022 floods in Gangnam District, Seoul, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2022%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A4%91%EB%B6%80_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District, it makes sense to extract events that are commonly associated with flooding in urban areas, such as people evacuating, floodwaters rising, and damage to infrastructure. These events are likely to be visualized in a video capturing the aftermath of the flood.\n\nEVENTS:\n1. People wading through floodwaters in the streets of Gangnam District\n2. Cars and buses submerged in water on flooded roads\n3. Residents evacuating their homes and seeking higher ground\n4. Emergency responders, such as firefighters and police, rescuing people from flooded areas\n5. Debris and damaged furniture floating in the floodwaters",
"en_article_excerpt": "On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.",
"en_article_url": "https://en.wikipedia.org/wiki/2022_South_Korean_floods",
"event_category": "disasters",
"event_name": "2022_floods",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, particularly the Gangnam District and surrounding areas, it makes sense to extract events that are directly related to flooding and its immediate consequences, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visually captured in a video documenting the floods and their impact on the affected areas.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and vehicles submerged in floodwater\n3. Emergency responders rescuing individuals from flooded areas\n4. Debris and property damage from floodwaters\n5. Residents clearing out flooded homes and businesses",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District and surrounding areas, it makes sense to extract events that are commonly associated with flooding, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visualized in a video capturing the aftermath and response to the flooding in Seoul.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and buses submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Residents clearing debris and damaged belongings from their homes\n5. Floodwaters overflowing from rivers and streams in the affected areas",
"video_URL": "http://twitter.com/i/status/1556640821054787588",
"video_description": "I just found out about the subway floods in Korea, 모두 건강 유의하세요 ! 아무쪼록 인명피해는 없게 해주세요.",
"video_id": "1556640821054787588"
}
| 8
|
[
"The image shows a subway or metro station with water pouring down from the ceiling, creating a shower-like effect. The station's walls are tiled, and there is a sign with an \"i\" indicating information, as well as a map on the wall. The floor is wet, and the water flow is significant, suggesting a possible leak or flooding situation.",
"The current frame shows the continuation of the water pouring down from the ceiling, maintaining the shower-like effect in the subway or metro station. The station's walls remain tiled, and the sign with an \"i\" and the map are still visible. The floor continues to be wet, with the water flow appearing unchanged, reinforcing the ongoing leak or flooding situation.",
"The video shows a subway station with a ceiling leak, where water is continuously pouring down in a shower-like manner. The wet floor and visible water flow indicate an ongoing leakage or flooding situation. The station's walls are tiled, and signs, including one with an \"i\" and a map, are visible, indicating the station's infrastructure and navigation aids.",
"Water is still pouring down from the ceiling in the subway station, causing the floor to remain wet. The continuous water flow suggests the leakage problem persists. Signs with directional information and a map are still visible on the walls, providing navigation assistance to passengers amidst the ongoing flooding situation.",
"Water continues to pour down from the ceiling in the subway station, maintaining the wet conditions on the floor. The persistent water flow indicates the leakage issue remains unresolved. Signs with directional information and a map are still visible on the walls, offering navigation assistance to passengers despite the ongoing flooding situation.",
"The situation in the subway station remains dire as large chunks of the ceiling continue to fall, accompanied by a significant stream of water pouring down. This further exacerbates the flooding on the floor, creating a hazardous environment for any potential passengers. The continued collapse of the ceiling and the unrelenting water flow suggest that the structural integrity of the station is severely compromised, with the leakage issue persistently unresolved.",
"The situation in the subway station remains dire as large chunks of the ceiling continue to fall, accompanied by a significant stream of water pouring down. This further exacerbates the flooding on the floor, creating a hazardous environment for any potential passengers. The continued collapse of the ceiling and the unrelenting water flow suggest that the structural integrity of the station is severely compromised, with the leakage issue persistently unresolved.",
"The catastrophic scenario in the subway station intensifies as more substantial portions of the ceiling disintegrate, plummeting to the ground. The torrential flow of water from the ceiling persists, contributing to the rapidly worsening flooding. The escalating damage indicates a critical and dangerous situation, with the station's structural integrity in dire peril and no immediate signs of relief or stabilization."
] |
1556640821054787588
|
A subway or metro station experiences a severe flooding situation due to a persistent ceiling leak, with water continuously pouring down, creating a hazardous environment. The station's infrastructure, including signs with directional information and a map, remains visible throughout the ordeal. As the situation worsens, the ceiling begins to collapse, with large chunks falling to the ground, exacerbating the flooding and compromising the station's structural integrity. The escalating damage and unrelenting water flow create a critical and dangerous situation, posing a significant risk to potential passengers, with no immediate signs of relief or stabilization.
|
On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.
|
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022",
"Cars and vehicles submerged in floodwater during the Seoul floods in Gangnam District, South Korea on 8 August 2022",
"Emergency responders rescuing individuals from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and property damage from floodwaters in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing out flooded homes and businesses in Seoul's Gangnam District after floods on 8 August 2022"
] |
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022 during floods",
"Cars and buses submerged in floodwater during the 8 August 2022 floods in Seoul's Gangnam District, South Korea",
"Emergency responders rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing debris and damaged belongings from their homes after floods in Gangnam District, Seoul, South Korea on 8 August 2022",
"Floodwaters overflowing from rivers and streams in Gangnam District, Seoul, South Korea during the floods on 8 August 2022"
] |
[
"People wading through floodwaters in the streets of Gangnam District Seoul South Korea during the floods on 8 August 2022",
"Cars and buses submerged in water on flooded roads in Gangnam District, Seoul, South Korea during the floods on August 8, 2022",
"Residents evacuating their homes and seeking higher ground in Seoul, South Korea, Gangnam District due to floods on 8 August 2022",
"Emergency responders, such as firefighters and police, rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and damaged furniture floating in the floodwaters during the 8 August 2022 floods in Gangnam District, Seoul, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2022%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A4%91%EB%B6%80_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District, it makes sense to extract events that are commonly associated with flooding in urban areas, such as people evacuating, floodwaters rising, and damage to infrastructure. These events are likely to be visualized in a video capturing the aftermath of the flood.\n\nEVENTS:\n1. People wading through floodwaters in the streets of Gangnam District\n2. Cars and buses submerged in water on flooded roads\n3. Residents evacuating their homes and seeking higher ground\n4. Emergency responders, such as firefighters and police, rescuing people from flooded areas\n5. Debris and damaged furniture floating in the floodwaters",
"en_article_excerpt": "On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.",
"en_article_url": "https://en.wikipedia.org/wiki/2022_South_Korean_floods",
"event_category": "disasters",
"event_name": "2022_floods",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, particularly the Gangnam District and surrounding areas, it makes sense to extract events that are directly related to flooding and its immediate consequences, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visually captured in a video documenting the floods and their impact on the affected areas.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and vehicles submerged in floodwater\n3. Emergency responders rescuing individuals from flooded areas\n4. Debris and property damage from floodwaters\n5. Residents clearing out flooded homes and businesses",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District and surrounding areas, it makes sense to extract events that are commonly associated with flooding, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visualized in a video capturing the aftermath and response to the flooding in Seoul.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and buses submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Residents clearing debris and damaged belongings from their homes\n5. Floodwaters overflowing from rivers and streams in the affected areas",
"video_URL": "http://twitter.com/i/status/1556678909436932096",
"video_description": "This is absolutely insane video in South Korea. Extreme flooding that hasn’t been seen in 80 years or more. Very extreme flooding, causing massive problems in Seoul and the entirety of the country. #SouthKorea #flooding #weather",
"video_id": "1556678909436932096"
}
| 8
|
[
"The image depicts a flooded urban street at night, with heavy rain and large waves of water visible. Buses and other vehicles are seen navigating through the water, struggling to maintain control. The environment is dark, illuminated by streetlights, and there are street signs visible, one of which is a pedestrian crossing sign. The Korean text on the image suggests a humorous commentary about the situation.",
"The image shows the aftermath of a flood on an urban street, with the water level significantly lower compared to the previous frames. The street is still wet, and the same buses and vehicles are visible, now navigating through the reduced water. The environment remains dark with streetlights illuminating the scene. The pedestrian crossing sign is still visible. The Korean text continues the humorous commentary on the situation, indicating a lighter mood now that the water has receded.",
"The image captures a flooded urban street at night, with a significant amount of water flowing across it. Vehicles, including a white car and a bus, are seen moving through the water, creating splashes. The scene is illuminated by streetlights and the headlights of the vehicles. The Korean text on the image suggests a humorous tone about the flooding, indicating that the water has receded somewhat, but there is still a sense of inconvenience or frustration with the situation. The street signs and urban environment remain visible, emphasizing the extent of the flooding.",
"The video shows a flooded urban street at night, with water flowing across it. Vehicles, including a white car and a bus, are seen moving through the water, creating splashes. The scene is illuminated by streetlights and vehicle headlights. The Korean text on the image suggests a humorous tone about the flooding, indicating that the water has receded somewhat, but there is still a sense of inconvenience or frustration with the situation. The street signs and urban environment remain visible, emphasizing the extent of the flooding.",
"The video continues to depict the flooded urban street at night. A significant amount of water is still flowing across the street, creating waves and splashes. A white car and a green bus are visible, navigating through the flooded area. The green traffic light is illuminated, indicating that vehicles are still moving despite the flooding. The Korean text overlaying the image adds a humorous tone, noting that the water has receded somewhat, but there is still a sense of inconvenience or frustration with the situation. The street signs and urban environment are clearly visible, emphasizing the extent of the flooding.",
"The current frame continues to depict the urban street at night during the flood. The water level has significantly risen, almost reaching the height of the street lamps and utility boxes, which are partially submerged. Vehicles, including a green bus and a white car, are still navigating through the water, which creates large waves and splashes around them. The green traffic light remains illuminated, indicating ongoing vehicle movement. The Korean text overlaying the image adds a humorous tone, noting that the water level has increased, but there's still a sense of inconvenience or frustration with the situation. The street signs and urban environment are clearly visible, emphasizing the extent of the flooding and the impact on traffic.",
"The current frame continues to depict the urban street at night during the flood. The water level remains high, almost reaching the height of the street lamps and utility boxes, which are partially submerged. Vehicles, including a green bus and a white car, are still navigating through the water, which creates large waves and splashes around them. The Korean text overlaying the image continues to add a humorous tone, noting that the water level has increased, but there's still a sense of inconvenience or frustration with the situation. The street signs and urban environment are clearly visible, emphasizing the extent of the flooding and the impact on traffic.",
"The current frame shows a person walking through the flooded urban street at night, holding an umbrella. The water level is high, reaching above the ankles of the person walking. The person is moving towards a utility pole partially submerged in the water. Vehicles, including a green bus, are still visible in the background, navigating through the water, which continues to create waves and splashes. The Korean text overlaying the image adds a humorous tone, mentioning that the water level has increased and there's still a sense of inconvenience or frustration with the situation. The street signs and urban environment are clearly visible, emphasizing the extent of the flooding and its impact on traffic."
] |
1556678909436932096
|
The video depicts a flooded urban street at night, with heavy rain and large waves of water visible. Vehicles, including buses and cars, are seen navigating through the water, creating splashes and struggling to maintain control. Despite the challenging conditions, traffic continues to move, with green traffic lights indicating that vehicles are still allowed to proceed. The water level fluctuates throughout the video, at times reaching the height of street lamps and utility boxes, and partially submerging them. Pedestrians are also present, with one person seen walking through the flooded street, holding an umbrella and navigating through water above their ankles. The overall tone of the video, as indicated by the Korean text overlays, is one of inconvenience and frustration with the situation, but also a sense of humor and resilience in the face of the flooding. The video showcases the impact of the flood on urban traffic and daily life, with vehicles and pedestrians adapting to the challenging conditions.
|
On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.
|
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022",
"Cars and vehicles submerged in floodwater during the Seoul floods in Gangnam District, South Korea on 8 August 2022",
"Emergency responders rescuing individuals from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and property damage from floodwaters in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing out flooded homes and businesses in Seoul's Gangnam District after floods on 8 August 2022"
] |
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022 during floods",
"Cars and buses submerged in floodwater during the 8 August 2022 floods in Seoul's Gangnam District, South Korea",
"Emergency responders rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing debris and damaged belongings from their homes after floods in Gangnam District, Seoul, South Korea on 8 August 2022",
"Floodwaters overflowing from rivers and streams in Gangnam District, Seoul, South Korea during the floods on 8 August 2022"
] |
[
"People wading through floodwaters in the streets of Gangnam District Seoul South Korea during the floods on 8 August 2022",
"Cars and buses submerged in water on flooded roads in Gangnam District, Seoul, South Korea during the floods on August 8, 2022",
"Residents evacuating their homes and seeking higher ground in Seoul, South Korea, Gangnam District due to floods on 8 August 2022",
"Emergency responders, such as firefighters and police, rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and damaged furniture floating in the floodwaters during the 8 August 2022 floods in Gangnam District, Seoul, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2022%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A4%91%EB%B6%80_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District, it makes sense to extract events that are commonly associated with flooding in urban areas, such as people evacuating, floodwaters rising, and damage to infrastructure. These events are likely to be visualized in a video capturing the aftermath of the flood.\n\nEVENTS:\n1. People wading through floodwaters in the streets of Gangnam District\n2. Cars and buses submerged in water on flooded roads\n3. Residents evacuating their homes and seeking higher ground\n4. Emergency responders, such as firefighters and police, rescuing people from flooded areas\n5. Debris and damaged furniture floating in the floodwaters",
"en_article_excerpt": "On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.",
"en_article_url": "https://en.wikipedia.org/wiki/2022_South_Korean_floods",
"event_category": "disasters",
"event_name": "2022_floods",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, particularly the Gangnam District and surrounding areas, it makes sense to extract events that are directly related to flooding and its immediate consequences, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visually captured in a video documenting the floods and their impact on the affected areas.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and vehicles submerged in floodwater\n3. Emergency responders rescuing individuals from flooded areas\n4. Debris and property damage from floodwaters\n5. Residents clearing out flooded homes and businesses",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District and surrounding areas, it makes sense to extract events that are commonly associated with flooding, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visualized in a video capturing the aftermath and response to the flooding in Seoul.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and buses submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Residents clearing debris and damaged belongings from their homes\n5. Floodwaters overflowing from rivers and streams in the affected areas",
"video_URL": "http://twitter.com/i/status/1556973165556903939",
"video_description": "Visuals after yesterday's floods... Rains continue in S. Korea on Tuesday; \"level 3\" warning in operation to prevent damage. Be careful.. stay Safe.. #SouthKorea #flooding #flood #Seoul #climate #rain",
"video_id": "1556973165556903939"
}
| 8
|
[
"A person is skateboarding on a wet street during a heavy rainstorm. They are navigating down a narrow, bustling street lined with shops, illuminated by bright lights and signage. Other pedestrians are visible in the background, some taking cover under awnings.",
"The scene shows a storefront covered in a rain-soaked plastic sheet with neon signage above it. The rain continues heavily, and the street remains wet. There are no visible people or skateboarders, suggesting a momentary lull in activity amidst the ongoing rainstorm.",
"The scene depicts a bustling urban setting during heavy rainfall. Pedestrians are walking hurriedly, some with umbrellas to shield themselves from the rain. The street is wet, reflecting the bright lights of the surrounding buildings and signage. A bright, illuminated signboard with Korean text is visible in the background, suggesting this may be a commercial area in South Korea. The rain continues to pour heavily, creating a dynamic and busy atmosphere despite the wet conditions.",
"The scene continues in the bustling urban setting during heavy rainfall. Pedestrians are walking hurriedly, some with umbrellas to shield themselves from the rain. The street remains wet, reflecting the bright lights of the surrounding buildings and signage. A bright, illuminated signboard with Korean text is still visible in the background, suggesting this is a commercial area in South Korea. The rain continues to pour heavily, creating a dynamic and busy atmosphere despite the wet conditions. The presence of the signboard with Korean text reinforces the location as being in South Korea.",
"The rain continues to pour heavily in this urban setting, maintaining the wet conditions. The street remains busy with pedestrians moving quickly, likely due to the weather, some holding umbrellas. The bright lights from the surrounding buildings and signage continue to reflect off the wet pavement, creating a lively atmosphere despite the rain. The illuminated signboard with Korean text in the background remains visible, further indicating the location in South Korea.",
"The rain persists, keeping the urban area wet. A few people are seen outside an establishment, some moving quickly, possibly to avoid the rain, while others stand near the entrance. The wet pavement still reflects the bright lights from the nearby signs and buildings. The illuminated signboard with Korean text remains prominent, reinforcing the setting in South Korea. There is some scattered debris on the ground, possibly from the impact of the rain.",
"The rain continues, maintaining the wet conditions in the urban area. Several individuals, including one holding an umbrella, are seen walking along the street, navigating the wet pavement. The wet ground continues to reflect the bright lights from surrounding signs and buildings, with the illuminated signboard with Korean text still visible, indicating the setting is in South Korea. The presence of debris on the ground persists, likely a result of the ongoing rain.",
"The rain persists, keeping the urban area wet. Several individuals, including one wearing a green raincoat and another holding an umbrella, continue to walk along the wet street. The wet pavement reflects the bright lights from surrounding signs and buildings. The illuminated signboard with Korean text is still visible, reinforcing the setting in South Korea. Debris remains on the ground, likely due to the ongoing rain. A white car with the license plate '1458 493' is also present, driving through the street, contributing to the urban scene."
] |
1556973165556903939
|
The video depicts a scene of a bustling urban area in South Korea during a heavy rainstorm. The event involves various participants, including pedestrians navigating the wet streets, some using umbrellas for protection, and vehicles, such as a white car, driving through the flooded roads. The context is set in a commercial area, as indicated by the presence of shops, bright signage, and an illuminated signboard with Korean text. A person is initially seen skateboarding down the street, but they are not present in subsequent frames. Throughout the video, the rain persists, creating a dynamic and busy atmosphere, with pedestrians moving quickly to avoid the downpour. The wet conditions cause the pavement to reflect the bright lights of the surrounding buildings and signs, adding to the lively ambiance of the scene. Despite the inclement weather, the urban area remains active, with people going about their business and vehicles moving through the streets.
|
On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.
|
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022",
"Cars and vehicles submerged in floodwater during the Seoul floods in Gangnam District, South Korea on 8 August 2022",
"Emergency responders rescuing individuals from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and property damage from floodwaters in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing out flooded homes and businesses in Seoul's Gangnam District after floods on 8 August 2022"
] |
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022 during floods",
"Cars and buses submerged in floodwater during the 8 August 2022 floods in Seoul's Gangnam District, South Korea",
"Emergency responders rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing debris and damaged belongings from their homes after floods in Gangnam District, Seoul, South Korea on 8 August 2022",
"Floodwaters overflowing from rivers and streams in Gangnam District, Seoul, South Korea during the floods on 8 August 2022"
] |
[
"People wading through floodwaters in the streets of Gangnam District Seoul South Korea during the floods on 8 August 2022",
"Cars and buses submerged in water on flooded roads in Gangnam District, Seoul, South Korea during the floods on August 8, 2022",
"Residents evacuating their homes and seeking higher ground in Seoul, South Korea, Gangnam District due to floods on 8 August 2022",
"Emergency responders, such as firefighters and police, rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and damaged furniture floating in the floodwaters during the 8 August 2022 floods in Gangnam District, Seoul, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2022%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A4%91%EB%B6%80_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District, it makes sense to extract events that are commonly associated with flooding in urban areas, such as people evacuating, floodwaters rising, and damage to infrastructure. These events are likely to be visualized in a video capturing the aftermath of the flood.\n\nEVENTS:\n1. People wading through floodwaters in the streets of Gangnam District\n2. Cars and buses submerged in water on flooded roads\n3. Residents evacuating their homes and seeking higher ground\n4. Emergency responders, such as firefighters and police, rescuing people from flooded areas\n5. Debris and damaged furniture floating in the floodwaters",
"en_article_excerpt": "On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.",
"en_article_url": "https://en.wikipedia.org/wiki/2022_South_Korean_floods",
"event_category": "disasters",
"event_name": "2022_floods",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, particularly the Gangnam District and surrounding areas, it makes sense to extract events that are directly related to flooding and its immediate consequences, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visually captured in a video documenting the floods and their impact on the affected areas.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and vehicles submerged in floodwater\n3. Emergency responders rescuing individuals from flooded areas\n4. Debris and property damage from floodwaters\n5. Residents clearing out flooded homes and businesses",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District and surrounding areas, it makes sense to extract events that are commonly associated with flooding, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visualized in a video capturing the aftermath and response to the flooding in Seoul.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and buses submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Residents clearing debris and damaged belongings from their homes\n5. Floodwaters overflowing from rivers and streams in the affected areas",
"video_URL": "http://twitter.com/i/status/1556659852054634496",
"video_description": "Dorimcheon stream in #Seoul's Gwanak District right now. People are now asking where President Yoon Suk-yeol is and what he's doing. Mayor Oh has just returned to office to deal with disaster, but it's not just Seoul. #SouthKorea #flooding #floodsituation",
"video_id": "1556659852054634496"
}
| 8
|
[
"A flooded road is shown at night, with strong currents and water rushing over it. There are streetlights lining the road, and trees and shrubs are visible on both sides. The water appears turbulent and high, suggesting heavy rainfall or flooding. A metal railing is in the foreground, indicating the viewer is likely observing from a bridge or overpass.",
"The scene continues to depict a flooded area at night, with water flowing rapidly. The strong currents persist, and the turbulent water is clearly visible. The metal railing remains in the foreground, suggesting the viewer is still on a bridge or overpass. Streetlights are still illuminating the scene, and the visibility of trees and shrubs indicates the same location as the previous frame. The water level seems high, consistent with the previous description, indicating ongoing heavy rainfall or flooding.",
"The scene continues to depict the flooded area at night with water flowing rapidly. The metal railing in the foreground indicates the viewer is still on a bridge or overpass. Streetlights illuminate the scene, and the visibility of trees and shrubs suggests the same location as before. The water level remains high, consistent with ongoing heavy rainfall or flooding. The perspective from a higher vantage point shows the extent of the floodwaters covering the ground.",
"The video maintains its focus on the flooded area at night, with water flowing rapidly. The metal railing in the foreground continues to indicate that the viewer is still on a bridge or overpass. The streetlights illuminate the scene, and the visibility of buildings and trees suggests the location remains the same. The water level remains high, consistent with ongoing heavy rainfall or flooding. The perspective from a higher vantage point shows the extent of the floodwaters covering the ground.",
"The scene continues to depict the flooded area at night. The view from the bridge or overpass shows water still flowing rapidly beneath the railing. The presence of streetlights and the unchanged visibility of buildings and trees suggest the location has not shifted. The ongoing heavy rainfall or flooding is evident from the high water level. The perspective from a higher vantage point persists, indicating the floodwaters still significantly cover the ground.",
"The scene continues to depict the flooded area at night. The view from the bridge or overpass shows water still flowing rapidly beneath the railing. The presence of streetlights and the unchanged visibility of buildings and trees suggest the location has not shifted. The ongoing heavy rainfall or flooding is evident from the high water level. The perspective from a higher vantage point persists, indicating the floodwaters still significantly cover the ground.",
"The video continues to show the nighttime scene of the flooded area. The focus shifts slightly to a different section where a bicycle is seen, partially submerged in the water, near a building entrance. The streetlights remain on, and the ongoing heavy rainfall or flooding is evident from the high water level. The perspective from a higher vantage point persists, indicating the floodwaters still significantly cover the ground.",
"The current frame depicts a nighttime street scene during a heavy rainfall or flood. The view shows a wet, reflective street with visible crosswalk markings. Several people are walking on the street, holding umbrellas to shield themselves from the rain. A bicycle is partially submerged in the water, leaning against the side of a building. The building in the background has illuminated signs, one of which reads \"FRESH.\" The streetlights are on, and the overall ambiance is dim due to the nighttime setting and the heavy rain."
] |
1556659852054634496
|
The video depicts a nighttime scene of a flooded area, likely due to heavy rainfall, observed from a bridge or overpass. The floodwaters are high and turbulent, covering the ground and flowing rapidly. The scene remains consistent throughout, with streetlights illuminating the area and trees, shrubs, and buildings visible in the background. As the video progresses, a partially submerged bicycle is seen near a building entrance, and later, people are shown walking on a wet street, holding umbrellas and navigating through the flooded area. The video captures the extent of the flooding, showing the significant impact of the heavy rainfall on the environment and the people in it.
|
On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.
|
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022",
"Cars and vehicles submerged in floodwater during the Seoul floods in Gangnam District, South Korea on 8 August 2022",
"Emergency responders rescuing individuals from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and property damage from floodwaters in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing out flooded homes and businesses in Seoul's Gangnam District after floods on 8 August 2022"
] |
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022 during floods",
"Cars and buses submerged in floodwater during the 8 August 2022 floods in Seoul's Gangnam District, South Korea",
"Emergency responders rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing debris and damaged belongings from their homes after floods in Gangnam District, Seoul, South Korea on 8 August 2022",
"Floodwaters overflowing from rivers and streams in Gangnam District, Seoul, South Korea during the floods on 8 August 2022"
] |
[
"People wading through floodwaters in the streets of Gangnam District Seoul South Korea during the floods on 8 August 2022",
"Cars and buses submerged in water on flooded roads in Gangnam District, Seoul, South Korea during the floods on August 8, 2022",
"Residents evacuating their homes and seeking higher ground in Seoul, South Korea, Gangnam District due to floods on 8 August 2022",
"Emergency responders, such as firefighters and police, rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and damaged furniture floating in the floodwaters during the 8 August 2022 floods in Gangnam District, Seoul, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2022%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A4%91%EB%B6%80_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District, it makes sense to extract events that are commonly associated with flooding in urban areas, such as people evacuating, floodwaters rising, and damage to infrastructure. These events are likely to be visualized in a video capturing the aftermath of the flood.\n\nEVENTS:\n1. People wading through floodwaters in the streets of Gangnam District\n2. Cars and buses submerged in water on flooded roads\n3. Residents evacuating their homes and seeking higher ground\n4. Emergency responders, such as firefighters and police, rescuing people from flooded areas\n5. Debris and damaged furniture floating in the floodwaters",
"en_article_excerpt": "On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.",
"en_article_url": "https://en.wikipedia.org/wiki/2022_South_Korean_floods",
"event_category": "disasters",
"event_name": "2022_floods",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, particularly the Gangnam District and surrounding areas, it makes sense to extract events that are directly related to flooding and its immediate consequences, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visually captured in a video documenting the floods and their impact on the affected areas.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and vehicles submerged in floodwater\n3. Emergency responders rescuing individuals from flooded areas\n4. Debris and property damage from floodwaters\n5. Residents clearing out flooded homes and businesses",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District and surrounding areas, it makes sense to extract events that are commonly associated with flooding, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visualized in a video capturing the aftermath and response to the flooding in Seoul.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and buses submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Residents clearing debris and damaged belongings from their homes\n5. Floodwaters overflowing from rivers and streams in the affected areas",
"video_URL": "http://twitter.com/i/status/1556995436052873218",
"video_description": "Heavy rain in Seoul floods train stations, submerges vehicles. #Seoul #flooding #floods #SouthKorea",
"video_id": "1556995436052873218"
}
| 8
|
[
"The image shows a flooded staircase in an indoor setting. Water is cascading down the stairs, filling the lower level with murky water. The staircase has handrails on either side and the walls are tiled. The scene suggests a significant amount of water accumulation, possibly due to flooding or a plumbing issue.",
"The current frame continues to show the flooded staircase in an indoor setting. Water is still cascading down the stairs, maintaining the level of murky water at the lower level. The staircase's handrails on either side and tiled walls remain visible. The scene persists with a significant amount of water accumulation, reinforcing the idea of flooding or a plumbing issue.",
"The current frame continues to depict the flooded staircase in an indoor setting. The water remains cascading down the stairs, with a consistent level of murky water at the lower level. The staircase's handrails on both sides and the tiled walls are still visible. The scene continues to emphasize a significant amount of water accumulation, suggesting ongoing flooding or a plumbing issue.",
"The video shows a flooded indoor staircase, with water cascading down the steps. The water appears to be dirty, indicating it might be from a flood or plumbing issue. The handrails on both sides of the staircase and tiled walls are visible, emphasizing the indoor setting. The consistent level of water at the lower level suggests that the flooding is ongoing.",
"The water continues to cascade down the indoor staircase, maintaining the same level of flooding as before. The handrails and tiled walls remain visible, with no change in the scene, indicating the ongoing nature of the flooding issue.",
"The water continues to flow down the stairs at the same level, with no change in the scene, indicating the ongoing flooding issue. The handrails and tiled walls are visible, with no visible activity or movement from people or objects.",
"The water continues to flow down the stairs at a higher level, indicating the ongoing flooding issue. The handrails and tiled walls are visible, with no visible activity or movement from people or objects.",
"The water is still flowing down the stairs, indicating the flooding issue continues. The handrails and tiled walls are visible, with no visible activity or movement from people or objects."
] |
1556995436052873218
|
A video depicts a flooded indoor staircase with water continuously cascading down the steps, resulting in a significant accumulation of murky water at the lower level. The scene persists throughout, with no visible change or resolution to the flooding issue, suggesting an ongoing problem likely caused by flooding or a plumbing issue. The setting remains consistent, with handrails on either side of the staircase and tiled walls, but there are no people or moving objects visible throughout the video.
|
On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.
|
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022",
"Cars and vehicles submerged in floodwater during the Seoul floods in Gangnam District, South Korea on 8 August 2022",
"Emergency responders rescuing individuals from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and property damage from floodwaters in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing out flooded homes and businesses in Seoul's Gangnam District after floods on 8 August 2022"
] |
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022 during floods",
"Cars and buses submerged in floodwater during the 8 August 2022 floods in Seoul's Gangnam District, South Korea",
"Emergency responders rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing debris and damaged belongings from their homes after floods in Gangnam District, Seoul, South Korea on 8 August 2022",
"Floodwaters overflowing from rivers and streams in Gangnam District, Seoul, South Korea during the floods on 8 August 2022"
] |
[
"People wading through floodwaters in the streets of Gangnam District Seoul South Korea during the floods on 8 August 2022",
"Cars and buses submerged in water on flooded roads in Gangnam District, Seoul, South Korea during the floods on August 8, 2022",
"Residents evacuating their homes and seeking higher ground in Seoul, South Korea, Gangnam District due to floods on 8 August 2022",
"Emergency responders, such as firefighters and police, rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and damaged furniture floating in the floodwaters during the 8 August 2022 floods in Gangnam District, Seoul, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2022%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A4%91%EB%B6%80_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District, it makes sense to extract events that are commonly associated with flooding in urban areas, such as people evacuating, floodwaters rising, and damage to infrastructure. These events are likely to be visualized in a video capturing the aftermath of the flood.\n\nEVENTS:\n1. People wading through floodwaters in the streets of Gangnam District\n2. Cars and buses submerged in water on flooded roads\n3. Residents evacuating their homes and seeking higher ground\n4. Emergency responders, such as firefighters and police, rescuing people from flooded areas\n5. Debris and damaged furniture floating in the floodwaters",
"en_article_excerpt": "On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.",
"en_article_url": "https://en.wikipedia.org/wiki/2022_South_Korean_floods",
"event_category": "disasters",
"event_name": "2022_floods",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, particularly the Gangnam District and surrounding areas, it makes sense to extract events that are directly related to flooding and its immediate consequences, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visually captured in a video documenting the floods and their impact on the affected areas.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and vehicles submerged in floodwater\n3. Emergency responders rescuing individuals from flooded areas\n4. Debris and property damage from floodwaters\n5. Residents clearing out flooded homes and businesses",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District and surrounding areas, it makes sense to extract events that are commonly associated with flooding, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visualized in a video capturing the aftermath and response to the flooding in Seoul.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and buses submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Residents clearing debris and damaged belongings from their homes\n5. Floodwaters overflowing from rivers and streams in the affected areas",
"video_URL": "http://twitter.com/i/status/1556833205671456768",
"video_description": "After heavy rain and #flashflood hit South Korea, water started coming inside the apartment as well. #Gangnam #Seoul #flooding #SouthKorea",
"video_id": "1556833205671456768"
}
| 8
|
[
"The current frame shows an elevator with the number \"29\" displayed at the top, indicating the current floor. The elevator is situated in a hallway with marble walls, and there is a sign indicating \"B2.\" The floor is tiled with a yellow section near the bottom, and the text in Korean, \"서초아크로비스타,\" is visible at the bottom of the frame.",
"The scene shows an elevator lobby with a marble wall and the number \"B2\" displayed, indicating the basement level. There are two elevator doors, one open and one closed, with panels and signs on the wall. The floor is partially tiled with a yellow section visible. The text in Korean, \"서초아크로비스타,\" is visible, continuing from the previous frame.",
"The scene continues in the elevator lobby with a focus on the elevator doors, which remain closed. The marble wall and the number \"B2\" are still visible, maintaining the setting of the basement level. The Korean text \"서초아크로비스타\" is consistent with the previous frame, suggesting this is part of the same location. There is no visible movement or change in the scene, indicating a moment of stillness or pause within the video.",
"The focus remains on the closed elevator doors in the same lobby, with the marble wall and the \"B2\" number still in view, maintaining the setting at the basement level. The Korean text \"서초아크로비스타\" is still present, indicating the continuity of the location. There is no visible movement or change, emphasizing a moment of stillness or pause in the video.",
"The elevator doors remain closed, and the setting appears unchanged, still showing the marble wall and \"B2\" label. The Korean text \"서초아크로비스타\" is still present, suggesting that there is still a moment of pause or stillness in the video.",
"The elevator doors remain closed with the \"B2\" label and \"서초아크로비스타\" text still visible, indicating the elevator is stationary. The setting remains consistent with the marble wall and no visible movement, maintaining the stillness observed in the previous frame.",
"The elevator doors are still closed, with the \"B2\" label and \"서초아크로비스타\" text remaining visible, suggesting the elevator continues to be stationary. The marble wall and lack of movement persist, indicating no change in the scene from the previous frame.",
"The elevator doors are still closed, with the \"B2\" label and \"서초아크로비스타\" text remaining visible, indicating that the elevator continues to be stationary. The marble wall is still visible, and there is no change in the scene from the previous frame."
] |
1556833205671456768
|
The video depicts a stationary scene of an elevator lobby at the basement level, denoted as "B2", of a building identified by the Korean text "서초아크로비스타". The elevator doors remain closed throughout the video, with no visible movement or change in the scene, suggesting a prolonged moment of stillness or pause. The setting is consistently shown with marble walls and a partially tiled floor with a yellow section. There are no participants or actions observed in the video, only the static image of the elevator lobby.
|
On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.
|
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022",
"Cars and vehicles submerged in floodwater during the Seoul floods in Gangnam District, South Korea on 8 August 2022",
"Emergency responders rescuing individuals from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and property damage from floodwaters in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing out flooded homes and businesses in Seoul's Gangnam District after floods on 8 August 2022"
] |
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022 during floods",
"Cars and buses submerged in floodwater during the 8 August 2022 floods in Seoul's Gangnam District, South Korea",
"Emergency responders rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing debris and damaged belongings from their homes after floods in Gangnam District, Seoul, South Korea on 8 August 2022",
"Floodwaters overflowing from rivers and streams in Gangnam District, Seoul, South Korea during the floods on 8 August 2022"
] |
[
"People wading through floodwaters in the streets of Gangnam District Seoul South Korea during the floods on 8 August 2022",
"Cars and buses submerged in water on flooded roads in Gangnam District, Seoul, South Korea during the floods on August 8, 2022",
"Residents evacuating their homes and seeking higher ground in Seoul, South Korea, Gangnam District due to floods on 8 August 2022",
"Emergency responders, such as firefighters and police, rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and damaged furniture floating in the floodwaters during the 8 August 2022 floods in Gangnam District, Seoul, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2022%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A4%91%EB%B6%80_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District, it makes sense to extract events that are commonly associated with flooding in urban areas, such as people evacuating, floodwaters rising, and damage to infrastructure. These events are likely to be visualized in a video capturing the aftermath of the flood.\n\nEVENTS:\n1. People wading through floodwaters in the streets of Gangnam District\n2. Cars and buses submerged in water on flooded roads\n3. Residents evacuating their homes and seeking higher ground\n4. Emergency responders, such as firefighters and police, rescuing people from flooded areas\n5. Debris and damaged furniture floating in the floodwaters",
"en_article_excerpt": "On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.",
"en_article_url": "https://en.wikipedia.org/wiki/2022_South_Korean_floods",
"event_category": "disasters",
"event_name": "2022_floods",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, particularly the Gangnam District and surrounding areas, it makes sense to extract events that are directly related to flooding and its immediate consequences, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visually captured in a video documenting the floods and their impact on the affected areas.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and vehicles submerged in floodwater\n3. Emergency responders rescuing individuals from flooded areas\n4. Debris and property damage from floodwaters\n5. Residents clearing out flooded homes and businesses",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District and surrounding areas, it makes sense to extract events that are commonly associated with flooding, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visualized in a video capturing the aftermath and response to the flooding in Seoul.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and buses submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Residents clearing debris and damaged belongings from their homes\n5. Floodwaters overflowing from rivers and streams in the affected areas",
"video_URL": "http://twitter.com/i/status/1557013913216352258",
"video_description": "Summers in South Korea be like... #southkorea #Monsoon2022 #monsoonseason #summer2022 #flooding #summersouthkorea #여름 #침수 #summertime",
"video_id": "1557013913216352258"
}
| 8
|
[
"The current frame depicts a rainy urban scene with a few individuals holding umbrellas. In the background, there is a green and white bus with Korean text on its front and side, indicating it is likely in South Korea. A black car is driving past, creating ripples and small waves in the accumulated rainwater on the street. The street appears to be wet and reflective due to the rain.",
"The scene continues in a rainy urban environment where a white car is navigating through a flooded street, its headlights illuminating the way. The road is visibly submerged in water, with reflections of street lights and other urban lights creating a shimmering effect. A person is walking along the sidewalk, holding a phone, seemingly unaffected by the wet conditions. The background features commercial establishments with bright signs, suggesting a bustling city life despite the rain.",
"The scene remains in a rainy urban setting, with the ground still significantly submerged in water. The shimmering reflections from urban lights continue to be prominent. A person is visible, holding a green umbrella, suggesting they are trying to stay dry amidst the wet conditions. The background still features commercial establishments with bright signs, maintaining the bustling city life atmosphere despite the persistent rain.",
"The scene continues in the rainy urban setting, with the ground still significantly submerged in water. The reflections from urban lights are still prominent. Two people are visible, one holding an umbrella, indicating they are trying to stay dry amidst the wet conditions. The background still features commercial establishments with bright signs, maintaining the bustling city life atmosphere despite the persistent rain.",
"The urban environment remains wet with standing water reflecting the city lights. A single person, holding an umbrella, walks through the water, suggesting ongoing efforts to navigate the rainy conditions. The background continues to show commercial buildings with illuminated signs, maintaining the urban atmosphere.",
"The scene continues in the urban environment with significant standing water reflecting the city lights, indicating persistent rain. A person, identifiable by their head and umbrella, walks through the water, demonstrating ongoing efforts to navigate the wet conditions. The background remains consistent with commercial buildings featuring bright signs, emphasizing the urban setting.",
"The scene continues in the urban environment, showing significant standing water reflecting city lights, indicating persistent rain. A person on a motorcycle is visible navigating through the water, demonstrating ongoing efforts to move through the wet conditions. The background remains consistent with commercial buildings featuring bright signs, emphasizing the urban setting.",
"The scene shows an urban environment with a street heavily flooded with water. The water reflects the city lights, indicating that it is nighttime. The flooded street shows that rain is still persistent. A person on a motorcycle is visible navigating through the water, demonstrating ongoing efforts to move through the wet conditions. The background is consistent with commercial buildings featuring bright signs, emphasizing the urban setting."
] |
1557013913216352258
|
The video depicts a rainy urban scene in South Korea, showcasing the daily life of individuals navigating through flooded streets. The setting is a bustling city with commercial establishments and bright signs, despite the persistent rain. Throughout the video, people are seen walking, driving, or riding motorcycles through the water, using umbrellas to stay dry. The scenes feature reflections of urban lights on the flooded streets, creating a shimmering effect. The video captures the resilience of city dwellers as they go about their daily activities, undeterred by the wet conditions. The overall context is one of a rainy night in a South Korean city, with individuals adapting to the weather to continue their daily routines.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=SCkWqQ49yUQ",
"video_description": "이천 물류센터 화재와 관련해 관할 지자체가 재난안전대책본부를 구성했습니다. 경기 이천시는 엄태준 시장을 본부장으로 30명 규모의 재난안전대책본부를 편성했다고 밝혔습니다. 의료구호반과 장비지원반 등 11개 반으로 꾸려진 대책본부는 환자 이송과 현장 수색 작업 등에 참여합니다. 신준명[[email protected]] ※ '당신의 제보가 뉴스가 됩니다' YTN은 여러분의 소중한 제보를 기다립니다. [카카오톡] YTN을 검색해 채널 추가 [전화] 02-398-8585 [메일] [email protected] [온라인 제보] www.ytn.co.kr ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0103_202004292044009865 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, [email protected], #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN & YTN PLUS 무단 전재 및 재배포금지",
"video_id": "SCkWqQ49yUQ"
}
| 8
|
[
"The image shows a large building with significant fire damage, indicating a recent fire incident. Emergency services, including fire trucks and ambulances, are present on the scene. Several individuals, likely firefighters and onlookers, are gathered around the building. The text in Korean at the top suggests that the building is a plastic warehouse in Icheon-si, which has been severely affected by the fire. Additional text at the bottom translates to \"Icheon-si, plastic warehouse fire, major damage.\"",
"The image shows the aftermath of a fire at a building, with significant structural damage and burnt sections visible. The text in Korean suggests the location is Icheon-si and the building is a plastic warehouse. Additional text indicates that the fire was caused by a lightning strike. The scene includes emergency response equipment and containers nearby, implying ongoing recovery efforts.",
"The current frame shows the aftermath of a fire at a building with significant structural damage and charred sections visible. The building appears to be partially collapsed, and the roof is severely damaged. The text in Korean suggests the location is Icheon-si and indicates that the building is a \"mushroom center.\" Additional text in red shows the number of deaths and missing persons. The scene includes emergency response equipment, such as tents, and containers nearby, implying ongoing recovery efforts.",
"The current frame shows the aftermath of a fire at a building with significant structural damage and charred sections visible. The building appears to be partially collapsed, and the roof is severely damaged. The text in Korean suggests the location is Icheon-si and indicates that the building is a \"mushroom center.\" Additional text in red shows the number of deaths and missing persons. The scene includes emergency response equipment, such as tents, and containers nearby, implying ongoing recovery efforts.",
"The current frame shows a close-up of the heavily damaged window of the same building. The window frame is completely blackened and the glass is missing, suggesting the intensity of the fire. The text in Korean indicates that many residents were in the building, and additional text confirms the location as Icheon-si. The charred exterior and the absence of windows emphasize the severity of the incident, aligning with the ongoing emergency response efforts noted in the previous frame.",
"The current frame shows a close-up view of a building facade that has been significantly damaged by a fire. The exterior walls are covered in blackened residue, with portions where the material has melted or blistered, indicating high-temperature exposure. The text in Korean at the top of the image states \"2층에 사망자 가장 많아\" (The most deaths on the 2nd floor), suggesting a high casualty count on the second floor of the building. The bottom text reads \"이천시, 물류센터 참사 대책본부 구성\" (Icheon City, Logistics Center Disaster Response Headquarters formed), indicating that a response team has been established in Icheon City to address the incident. The overall scene emphasizes the severity of the fire and the ongoing efforts to manage the situation.",
"The current frame shows a close-up view of a building facade that has been significantly damaged by a fire. The exterior walls are covered in blackened residue, with portions where the material has melted or blistered, indicating high-temperature exposure. The text in Korean at the top of the image states \"뉴스특보 사망자 이천병원 등 이송\" (News Special Report: Deceased being transported to Icheon Hospital, etc.), suggesting that victims of the fire are being moved for treatment or identification. The bottom text reads \"이천시, 물류센터 참사 대책본부 구성\" (Icheon City, Logistics Center Disaster Response Headquarters formed), indicating that a response team has been established in Icheon City to address the incident. The overall scene emphasizes the severity of the fire and the ongoing efforts to manage the situation.",
"The current frame shows another section of the same building facade, further illustrating the extensive damage caused by the fire. The exterior walls exhibit similar blackened residue, with areas where the material has melted or blistered, consistent with high-temperature exposure. The text in Korean at the top of the image states \"뉴스특보 사망자 이천병원 등 이송\" (News Special Report: Deceased being transported to Icheon Hospital, etc.), reinforcing the ongoing efforts to manage the aftermath of the fire. The bottom text reads \"이천시, 물류센터 참사 대책본부 구성\" (Icheon City, Logistics Center Disaster Response Headquarters formed), indicating the establishment of a response team to address the incident. The scene continues to emphasize the severity of the fire and the coordinated response to the disaster."
] |
SCkWqQ49yUQ
|
A severe fire occurred at a logistics center, initially reported as a plastic warehouse and later identified as a mushroom center, in Icheon-si, causing significant structural damage and loss of life. The fire, attributed to a lightning strike, resulted in a high number of deaths and missing persons, with the majority of casualties reported on the second floor. Emergency services responded to the incident, with fire trucks, ambulances, and recovery equipment on the scene. A disaster response headquarters was established in Icheon City to manage the situation, and the deceased were transported to Icheon Hospital for treatment or identification. The video depicts the aftermath of the fire, showing the extensive damage to the building, including charred sections, melted materials, and collapsed structures, highlighting the intensity of the incident and the ongoing efforts to address its consequences.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=oRy1PP3KzDs",
"video_description": "29일 오후 경기도 이천 물류창고 공사현장에서 화재가 발생해 큰 인명피해를 냈습니다. 오후 7시30분 현재 확인된 사망자만 36명입니다.",
"video_id": "oRy1PP3KzDs"
}
| 8
|
[
"The image shows a large building engulfed in thick black smoke, indicating a significant fire. The smoke is billowing out of multiple windows and from the roof. There are fire hoses spraying water towards the building, suggesting that firefighters are actively trying to extinguish the fire. The text in the image is in Korean and reads \"4층짜리 창고건물 지하에서 폭발과 함께 화재 발생,\" which translates to \"Explosion and fire occurred in the basement of a four-story warehouse building.\" This indicates that the fire began in the basement of the building and has led to an explosion.",
"The building is still engulfed in thick black smoke with flames visible, indicating the fire is still active. Fire hoses continue to spray water towards the building, showing ongoing firefighting efforts. The text in the image reads \"우레탄 폼 제작 중 유증기가 폭발한 것으로 추정,\" which translates to \"It is estimated that an explosion occurred during the production of urethane foam due to a vaporizer.\" This suggests the fire and explosion were likely caused by a malfunctioning vaporizer used in the production process.",
"The building remains engulfed in thick black smoke with visible flames, indicating that the fire is still active. Fire hoses continue to spray water towards the building, showing ongoing firefighting efforts. The text in the image reads \"글자 뉴스,\" which translates to \"News Letter.\" This suggests that the video is a news report covering the incident.",
"The video continues to focus on the ongoing fire incident. Thick black smoke still billows from the building, indicating the fire remains active. Fire hoses are still directed at the structure, demonstrating the persistent firefighting efforts. The text in the image, which reads \"글자 뉴스,\" translates to \"News Letter,\" confirming that this is a news report. The additional text at the bottom reads \"현재 확인된 사망자 11명에 14명은 연락두절 상태,\" translating to \"Currently, 11 deaths confirmed, 14 are missing and uncontactable,\" providing an update on the casualties and missing persons due to the incident.",
"The video continues to focus on the ongoing fire incident. Thick black smoke still billows from the building, indicating the fire remains active. Fire hoses are still directed at the structure, demonstrating the persistent firefighting efforts. The text in the image, which reads \"글자 뉴스,\" translates to \"News Letter,\" confirming that this is a news report. The additional text at the bottom reads \"사망자 25명 이상으로 크게 늘어날 수 있어,\" translating to \"The number of deaths could increase to over 25,\" providing an update on the potential rise in casualties due to the incident.",
"The video continues to focus on the ongoing fire incident. Thick black smoke still billows from the building, indicating the fire remains active. Fire hoses are still directed at the structure, demonstrating the persistent firefighting efforts. The text in the image, which reads \"글자 뉴스,\" translates to \"News Letter,\" confirming that this is a news report. The additional text at the bottom reads \"지하 수색 과정에서 사망자 잇따라 발생되고 있어,\" translating to \"Deaths are occurring one after another during the search process in the basement,\" providing an update on the situation as the search and rescue efforts continue.",
"The video maintains its focus on the ongoing fire incident. The thick black smoke continues to billow from the building, emphasizing the active nature of the fire. Fire hoses are still directed at the structure, underscoring the ongoing firefighting efforts. The text in the image, \"뉴스,\" translates to \"News,\" confirming that this is a news report. The additional text at the bottom reads \"영상제공: 경기도소방재난본부,\" which translates to \"Video provided by the Gyeonggi Fire and Disaster Headquarters,\" indicating the source of the footage. The video continues to depict the search and rescue efforts amidst the ongoing fire.",
"The video continues to focus on the ongoing fire incident. The thick black smoke is still billowing from the building, emphasizing the active nature of the fire. Fire hoses are directed at the structure, underscoring the ongoing firefighting efforts. The text in the image, \"뉴스,\" translates to \"News,\" confirming that this is a news report. The additional text at the bottom reads \"영상제공: 경기도소방재난본부,\" which translates to \"Video provided by the Gyeonggi Fire and Disaster Headquarters,\" indicating the source of the footage. The video continues to depict the search and rescue efforts amidst the ongoing fire."
] |
oRy1PP3KzDs
|
A four-story warehouse building caught fire due to an explosion in its basement, where urethane foam was being produced, likely caused by a malfunctioning vaporizer. The fire was intense, with thick black smoke and flames, prompting a significant firefighting response. Despite ongoing efforts to extinguish the fire, it remained active throughout the video. The incident was reported as part of a news broadcast, with updates on casualties and missing persons provided throughout. Initially, 11 deaths were confirmed, with 14 people missing and uncontactable, but the number of deaths was expected to rise to over 25 as the search and rescue efforts continued. The search process in the basement was particularly hazardous, with deaths occurring during this time. The footage was provided by the Gyeonggi Fire and Disaster Headquarters, showcasing the extensive emergency response to the fire.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=rqRqdg-oxkU",
"video_description": "이번에도 샌드위치 패널... 처참한 이천 물류센터 화재현장",
"video_id": "rqRqdg-oxkU"
}
| 8
|
[
"The frame shows a large building engulfed in flames, with thick black smoke billowing from multiple parts of the structure. Firefighters are actively working to control the blaze, with visible water streams directed at the building. The situation appears to be critical, as the fire has already caused significant damage to the exterior of the building.",
"Firefighters are still actively working to control the blaze of a large building, with visible water streams directed at the building to combat the fire. The situation appears to be critical, as the fire has caused significant damage to the exterior of the building.",
"The firefighters continue to direct water at the large building, which remains engulfed in thick smoke. The situation continues to be critical as the building's exterior shows significant damage from the fire.",
"The firefighters persist in directing water towards the large building, which is still enveloped in thick smoke. The situation remains critical, with the building's exterior showing extensive damage from the fire.",
"The firefighters continue to direct water towards the large building, which remains heavily engulfed in thick smoke. The building's exterior shows extensive damage from the fire, with flames visible through some windows. The situation remains critical, with the fire appearing to be still active inside the structure.",
"The firefighters persist in their efforts to control the blaze by directing water onto the large building. The building is still heavily engulfed in thick, dark smoke, indicating that the fire remains active inside. The structure shows significant damage, with visible flames through some windows. The scene remains critical, with the fire's intensity suggesting that the firefighters are still in the process of tackling the fire.",
"Firefighters continue their efforts to manage the blaze at the large building, which remains heavily engulfed in thick, dark smoke. The building shows extensive damage, with visible flames through several windows and sections of the structure charred. Firefighters are actively directing water onto the burning building, attempting to control the fire. The scene remains critical, with the fire's intensity indicating ongoing efforts to tackle the blaze.",
"The building continues to emit dense black smoke, indicating ongoing combustion. Flames are still visible through some windows, and the structure remains significantly damaged. Firefighters persist in directing water onto the fire, focusing on areas where flames are most prominent. The situation remains critical, with no sign of the fire being extinguished yet."
] |
rqRqdg-oxkU
|
A large building is engulfed in a severe fire, with firefighters actively working to control the blaze throughout the video. The fire causes significant damage to the building's exterior, with thick black smoke billowing from multiple parts of the structure and flames visible through several windows. Despite the firefighters' persistent efforts to direct water at the building, the situation remains critical, with the fire continuing to burn intensely inside the structure. The video depicts an ongoing emergency response situation, with no indication of the fire being extinguished by the end of the sequence.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=6Z2tI74NGGQ",
"video_description": "[당시 현장 목격자 : 고개 돌리는 순간 연기가 엄청 심하게 나오더라고요. 설마 저게 불일까 그랬는데, 폭발음과 함께 불꽃이 일기 시작한 거죠.] 삽시간에 불길 번져 인명 피해 잇따라 \"우레탄 작업 중 폭발\" 추정 [서승현 / 경기 이천소방서장 : 화상 당하신 분들이 옷이 다 탄 걸로 봐서는 유증기가 폭발하면서 일어난 것으로 추정….] 완공 2개월 앞두고 참사 또 발생한 대형 화재 사상자 속출 ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0103_202004292050572443 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, [email protected], #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN & YTN PLUS 무단 전재 및 재배포금지",
"video_id": "6Z2tI74NGGQ"
}
| 8
|
[
"The image shows a large fire engulfing a building, with thick black smoke billowing from the structure. The fire appears to be intense, with visible flames on the building's facade. The building is partially obscured by the smoke. In the foreground, there is a lamppost, and some other structures are visible at the bottom of the image. The text on the image reads \"이천 물류창고에서 화재\" (Fire in the Icheon logistics warehouse), indicating that the fire is occurring in a logistics warehouse in Icheon.",
"The image shows the same building on fire, with thick black smoke continuing to billow from the structure. The fire remains intense, with visible flames still present on the building's facade. The building is still partially obscured by the smoke. In the foreground, the lamppost and other structures are still visible at the bottom of the image. The text on the image reads \"당시 현장 목격자 서울에서 불일까 그랬는데\" (At the time, a witness in the field said, \"Could this be a fire in Seoul?\"), indicating that a witness from Seoul is commenting on the fire's intensity.",
"The current frame shows a large fire with thick black smoke billowing from a building, which appears to be heavily damaged. The flames are still intense and visible. The smoke is dense and covers a significant portion of the sky. In the foreground, a person in a yellow jacket is standing on the back of a blue truck, capturing the scene with a smartphone. Another person in a white jacket is also visible, standing by the side of the road. A large industrial building with blue and white panels is visible in the background. The text on the image reads \"삼사시건에 불길 번져 인명 피해 때려\" (The fire in the Samja incident has spread, causing casualties), indicating that the fire has spread and resulted in casualties.",
"The current frame shows a large building engulfed in thick black smoke, with visible flames still present, indicating the fire is ongoing. The smoke continues to billow from the structure, obscuring parts of the sky. In the foreground, a container is visible, with a hose attached, suggesting efforts to control or extinguish the fire. The text on the image reads \"YTN,\" likely indicating the source of the footage. The focus remains on the severity of the fire and the damage to the building.",
"A large building is shown with significant fire damage and thick black smoke. A hose is spraying water onto the building to control the fire. The text \"YTN\" is visible, indicating the source of the footage.",
"Firefighters in full protective gear are gathered around a fire truck, actively engaged in operations. One firefighter is bending over, handling equipment on the truck, while another stands ready with a hose. The truck's compartments are open, revealing various firefighting tools. The setting is outdoors during the daytime with clear skies. Text on the screen provides context about a recent severe fire in Gyeonggi Province, South Korea.",
"The video continues with an aerial view of a large building engulfed in thick black smoke, indicating a severe fire. The building appears to be partially damaged, with visible flames and smoke billowing from its structure. The surrounding area is visible, showing a road and some greenery. Text in the image reads \"안동 2개월 앞두고 참사,\" suggesting a tragic event is occurring, possibly a fire.",
"The video shows firefighters in full gear, including helmets and air tanks, standing by an open window of a building that appears to be the same one from the aerial view in the previous frame. The building's exterior is charred and damaged, indicating the aftermath of a severe fire. The text in the image reads \"또 발생한 대형 화재 사상자 속출,\" which translates to \"Another major fire occurred, resulting in casualties.\" This suggests that the fire led to injuries or fatalities, and the firefighters are likely assessing the situation or preparing to enter the building."
] |
6Z2tI74NGGQ
|
A severe fire broke out at a logistics warehouse in Icheon, South Korea, engulfing the building in intense flames and thick black smoke. The fire caused significant damage and resulted in casualties. Witnesses described the fire's intensity, with one comparing it to a fire in Seoul. Firefighters responded to the scene, using hoses to try to control the blaze. Aerial views showed the extent of the damage, with the building partially destroyed and smoke billowing into the air. Firefighters in protective gear worked to assess the situation and potentially rescue those trapped, as the fire led to a tragic event with reported casualties. The incident was reported by news sources, including YTN, and was described as a major fire with severe consequences.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=JCKK0gu12zI",
"video_description": "경기 이천시 물류센터 화재가 대응 2단계로 격상한 가운데 인명피해가 속출하고 있다. 29일 경기도소방재난본부에 따르면 이날 오후 1시 32분 이천시 모가면 소고리 연면적 약 1만1043㎡인 물류센터 신축 공사현장에서 화재가 발생해 11명이 인명피해를 입었다.",
"video_id": "JCKK0gu12zI"
}
| 8
|
[
"The image shows an industrial area with a large plume of black smoke rising from a facility, indicating a fire or explosion. The smoke is thick and dark, dominating the upper part of the image. Several buildings, possibly factories or warehouses, are visible in the lower part of the frame. The surrounding area appears to be a mix of developed land with roads and industrial structures, and natural terrain with greenery. The smoke is billowing into the sky, suggesting the ongoing severity of the incident.",
"The current frame continues to depict the industrial area where the fire or explosion occurred. The smoke remains thick and dark, rising from the facility and filling the upper part of the image. Several buildings, likely factories or warehouses, are still visible, with one prominently affected by the incident, showing visible damage and signs of fire. Firefighters are actively engaged in battling the blaze, with water streams visible being directed at the building to control the fire. The surrounding area remains a mix of developed land and natural terrain, but the focus is on the firefighting efforts and the severity of the ongoing incident.",
"The scene continues to show the industrial area, now with firefighters actively working to extinguish a fire at the building. Heavy smoke billows from the structure, indicating the fire is still intense. Firefighters are using hoses to direct water streams towards the building, trying to control the flames. The surrounding environment includes several buildings, with the focus on the firefighting efforts. The image also includes text in Korean, suggesting that the incident might be newsworthy or being reported on.",
"The scene shows an industrial area with a large building on fire, with heavy smoke billowing from the structure. Firefighters are using hoses to direct water streams towards the building to control the flames. The surrounding environment includes several buildings and industrial equipment. The image also includes text in Korean, suggesting that the incident might be newsworthy or being reported on.",
"In the current frame, firefighters continue to battle the fire engulfing a large industrial building. Thick smoke is still visibly rising from the structure, indicating the ongoing intensity of the blaze. Firefighters, visible in protective gear, are actively directing powerful streams of water from hoses towards the burning sections of the building. The surrounding area remains consistent with the previous frames, including additional buildings and industrial equipment. Text in Korean is present, likely providing context or reporting on the incident.",
"Firefighters are continuing their efforts to combat the fire at the industrial building, with thick smoke still billowing from the structure. A firefighter is seen operating a hose, directing water towards the flames. The surrounding area remains unchanged, with industrial equipment and structures visible. Text in Korean is present, likely offering updates or details on the incident.",
"The firefighters persist in battling the blaze at the industrial facility, as evidenced by the continuous thick smoke emanating from the building. A firefighter is actively engaged, directing a powerful stream of water from a hose towards the flames to suppress them. The environment around the building, including industrial equipment and structures, remains unchanged. The presence of Korean text indicates ongoing updates or information regarding the incident.",
"The image shows a logo with Korean text. It is not related to the previous frames depicting firefighters battling a blaze at an industrial facility."
] |
JCKK0gu12zI
|
A fire broke out at an industrial facility in a mixed area of developed land and natural terrain, prompting a response from firefighters. The blaze was intense, with thick, dark smoke billowing from the building, and caused visible damage to at least one structure. Firefighters actively worked to control the fire, using hoses to direct powerful streams of water at the burning sections of the building. The efforts to combat the fire were ongoing, with firefighters in protective gear persisting in their attempts to suppress the flames. The incident was considered newsworthy, as indicated by the presence of Korean text suggesting it was being reported on.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=ZFWsFwpfGlE",
"video_description": "경찰 오늘 이천 물류창고 화재 중간 수사결과 발표 [전국네트워크] 경기남부지방경찰청이 오늘 오전 38명의 목숨을 앗아간 '경기도 이천 물류창고 화재' 사고에 대한 중간 수사 결과를 발표합니다. 지난 4월 29일 경기 이천시의 한 물류창고 공사현장에서 불이 나 38명이 숨지고 10명이 다친 바 있는데, 화재 원인은 지하 2층 우레탄 작업 중 발생한 미상의 화원에 의한 폭발로 추정되고 있습니다. 경찰은 4차례의 대규모 현장 감식과 함께 화재와 관련된 80여 명을 조사해 이 가운데 17명에 대해 업무상 과실치사상 혐의 등을 적용해 입건했습니다. ☞ MBN 유튜브 구독하기 ☞ https://goo.gl/6ZsJGT 📢 MBN 유튜브 커뮤니티https://www.youtube.com/user/mbn/community?disable_polymer=1 MBN 페이스북 http://www.facebook.com/mbntv MBN 인스타그램 https://www.instagram.com/mbn_news/ #MBN뉴스#전국네트워크#이천물류창고",
"video_id": "ZFWsFwpfGlE"
}
| 8
|
[
"The video clip displays a news anchor standing in front of a graphic background with Korean text and a map outline. The anchor is delivering a report or news segment, as indicated by the context and his attire. The background text reads '전국 네트워크' (Nationwide Network), suggesting the news is related to a national network or news coverage. The lower part of the screen features more text in Korean, likely detailing the specific content of the news report being presented by the anchor. The logo in the upper right corner indicates the broadcasting network, MBN.",
"The video clip transitions from the news anchor to a damaged building showing signs of fire. The building appears to be significantly charred, with blackened wooden beams and walls exposed. The damage suggests that the structure has undergone a fire event. The lower part of the screen features text in Korean, likely detailing the context of the news report related to the damage of the building.",
"The current frame continues to show the charred building, with its wooden beams and walls further exposed due to the extensive fire damage. The blackened and warped structure is evident, indicating a severe fire event. The same text in Korean is displayed at the bottom of the screen, likely providing more information or a statement related to the investigation or the situation involving the building's damage.",
"The current frame depicts a scene where individuals in white hazmat suits are walking on a road. One of them is holding a green bag and a camera is visible, suggesting that this is a situation being documented, possibly related to the investigation of the building damage shown in the previous frames. The setting appears to be an area with traffic cones and other vehicles, indicating some level of traffic control or incident response.",
"In the current frame, a person in a white hazmat suit is seen walking through a debris-filled area that appears to be the aftermath of a significant event, possibly related to a building collapse or fire. The individual is holding a green bag and walking past a wooden structure, possibly a part of a fence or barrier. There is a pile of rubble or debris next to the structure, indicating that the area has been damaged. The setting is outdoors with a concrete structure visible in the background, and the overall scene suggests an ongoing investigation or cleanup operation.",
"The scene continues to depict the aftermath of a significant event, with a person in a white hazmat suit walking through the debris-filled area. The individual is still holding a green bag and moving past the damaged wooden structure. The pile of rubble remains visible, reinforcing the extensive damage. The text in the image, \"이천 물류창고 화재 중간 수사결과 발표\" translates to \"Publishing the intermediate investigation results of the Icheon logistics warehouse fire.\" This suggests that the video is discussing the findings related to a fire incident at a logistics warehouse in Icheon. The ongoing investigation or cleanup operation is highlighted by the presence of the hazmat-suited person and the damaged surroundings.",
"The video captures the aftermath of a fire incident at a logistics warehouse in Icheon, South Korea. The scene shows a person in a white hazmat suit walking through a debris-filled area, holding a green bag. The individual is moving past a damaged wooden structure, which appears to be part of the warehouse. The pile of rubble is still visible, reinforcing the extensive damage caused by the fire. The text in the image, \"이천 물류창고 화재 중간 수사결과 발표\" translates to \"Publishing the intermediate investigation results of the Icheon logistics warehouse fire.\" This suggests that the video is discussing the findings related to the fire incident. The ongoing investigation or cleanup operation is highlighted by the presence of the hazmat-suited person and the damaged surroundings.",
"In the current frame, a group of individuals is seen walking through the area affected by the fire incident at the Icheon logistics warehouse. The group consists of several people, some of whom are wearing masks, indicating a concern for air quality or safety in the aftermath of the fire. They are dressed in casual and work attire, suggesting they might be involved in the investigation, cleanup, or inspection process. The background shows debris and charred remains, consistent with the aftermath of the fire. The presence of various pieces of equipment and the overall disarray emphasize the severity of the incident. The individuals seem to be moving purposefully, possibly inspecting the damage or searching for evidence related to the fire. The text in the image, \"이천 물류창고 화재 중간 수사결과 발표\" (Publishing the intermediate investigation results of the Icheon logistics warehouse fire), continues to suggest that the video is part of a discussion or report on the investigation findings."
] |
ZFWsFwpfGlE
|
A news report from MBN discusses a significant fire incident at a logistics warehouse in Icheon, South Korea. The video begins with a news anchor introducing the report, followed by footage of the severely damaged building, showing signs of a severe fire with charred wooden beams and walls. The scene then shifts to individuals in hazmat suits investigating the area, documenting the damage, and collecting evidence, indicating an ongoing investigation or cleanup operation. As the video progresses, it continues to show the aftermath of the fire, with debris-filled areas, rubble, and damaged structures, highlighting the extent of the damage. The investigation team, including people in casual and work attire, some wearing masks, is seen inspecting the site, searching for evidence, and possibly assessing the cause of the fire. Throughout the video, text on the screen provides context, translating to "Publishing the intermediate investigation results of the Icheon logistics warehouse fire," suggesting that the report is discussing the findings related to this incident. Overall, the video depicts the severe consequences of the fire at the logistics warehouse and the subsequent investigation efforts.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=2SCMvAXvBLM",
"video_description": "경기도 이천 모가면의 한 물류창고 공사현장에서 29일 오후 1시32분 쯤 불이 나 현재까지 5명이 사망한 것으로 확인되고 있습니다. 소방당국은 대응 2단계를 발령하고 소방대원 60명과 펌프차 등 장비 27대를 투입해 진화작업을 벌이고 있습니다. 소방 관계자에 따르면 물류창고의 지하 공사현장에서 불이 시작된 것으로 보이며, 사망자는 앞으로 더 늘어날 전망입니다. 소방 대응단계는 화재 규모에 따라 1~3단계로 나뉘어지는데, 1단계는 4개 이하 소방서가 합동 대응하며 2단계는 5~9개 소방서, 3단계는 10개 이상 소방서가 함께 진화작업을 벌입니다. https://imnews.imbc.com/original/todayfield/5749059_32167.html #경기도 #이천 #물류창고 #화재 #소방당국 #대응 2단계 #진화작업",
"video_id": "2SCMvAXvBLM"
}
| 8
|
[
"The image shows an aerial view of a large industrial facility with a significant plume of dark smoke rising from it. The smoke is thick and appears to be coming from a specific area within the facility. There are several buildings and roads visible around the facility, with vehicles and people gathered on the roads, possibly indicating an emergency response. The text on the image reads \"4월 29일\" and \"경기도 이천 물류창고 화재 현장,\" which translates to \"April 29th\" and \"Fire at a logistics warehouse in Icheon, Gyeonggi-do,\" respectively. This suggests the scene is depicting a warehouse fire incident in Icheon, Gyeonggi-do, South Korea, on April 29th.",
"The image continues to show an aerial view of the industrial facility, with a large plume of dark smoke still rising from the same area within the facility. The smoke remains thick, indicating the fire is still ongoing. There are several buildings and roads visible around the facility, with vehicles and people gathered on the roads, suggesting an ongoing emergency response. The text on the image reads \"Right Now,\" emphasizing the current nature of the incident. This frame suggests a continuation of the warehouse fire incident in Icheon, Gyeonggi-do, South Korea, captured in real-time.",
"The current frame continues to depict the ongoing warehouse fire incident in Icheon, Gyeonggi-do, South Korea, captured in real-time. It shows an aerial view of the industrial facility, with a large plume of dark smoke still rising from the same area within the facility, indicating that the fire is still actively burning. The smoke remains thick, reinforcing the severity of the incident. Several buildings and roads are visible around the facility, with vehicles and people gathered on the roads, suggesting an ongoing emergency response. The text \"Right Now\" remains on the image, emphasizing the real-time nature of the event.",
"The current frame continues to depict the ongoing warehouse fire incident in Icheon, Gyeonggi-do, South Korea, captured in real-time. It shows an aerial view of the industrial facility, with a large plume of dark smoke still rising from the same area within the facility, indicating that the fire is still actively burning. The smoke remains thick, reinforcing the severity of the incident. Several buildings and roads are visible around the facility, with vehicles and people gathered on the roads, suggesting an ongoing emergency response. The text \"Right Now\" remains on the image, emphasizing the real-time nature of the event.",
"The aerial view continues to show the industrial facility in Icheon, Gyeonggi-do, South Korea, with the warehouse fire incident still ongoing. Thick, dark smoke continues to billow from the area of the fire, indicating the fire's intensity and spread. The surrounding buildings and roads are still visible, with emergency vehicles and personnel gathered, reinforcing the active response to the incident. The text \"Right Now\" is present, emphasizing the real-time coverage of the emergency.",
"The aerial view of the industrial facility in Icheon, Gyeonggi-do, South Korea, continues to show the warehouse fire incident. Thick, dark smoke is still billowing from the area of the fire, indicating its ongoing intensity and spread. The surrounding buildings and roads remain visible, with emergency vehicles and personnel gathered, highlighting the active response to the incident. The text \"Right Now\" is present, emphasizing the real-time coverage of the emergency. The smoke is now spreading further, and the fire appears to have caused damage to the surrounding structures, adding to the urgency of the response.",
"The aerial view shows the warehouse fire incident in Icheon, Gyeonggi-do, South Korea, continuing with thick, dark smoke billowing, indicating the fire's ongoing intensity. Emergency vehicles and personnel are present, responding to the incident. The text \"Right Now\" emphasizes real-time coverage. The fire has caused significant damage to surrounding structures, increasing the urgency of the response.",
"The aerial view continues to show the warehouse fire incident in Icheon, Gyeonggi-do, South Korea, with thick, dark smoke still billowing, indicating the fire's ongoing intensity. Emergency vehicles and personnel are present, responding to the incident. The text \"Right Now\" emphasizes real-time coverage. The fire has caused significant damage to surrounding structures, increasing the urgency of the response."
] |
2SCMvAXvBLM
|
A warehouse fire broke out at a logistics facility in Icheon, Gyeonggi-do, South Korea, on April 29th. The fire was intense, producing a large plume of thick, dark smoke that continued to billow from the area. Emergency responders, including vehicles and personnel, were quickly on the scene, indicating a rapid response to the incident. The fire caused significant damage to the surrounding structures, emphasizing the urgency of the situation. Throughout the duration of the video, the fire remained ongoing, with emergency services actively responding to the incident in real-time, as emphasized by the "Right Now" text on the images. The video captures the severity and intensity of the warehouse fire incident from start to finish, highlighting the emergency response and the damage caused by the fire.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=n8dcNr14bm8",
"video_description": "38명이 숨진 경기도 이천 물류창고 공사장 화재 현장에서 경찰이 아직 수습되지 않은 유해 일부와 유류품 등을 찾기 위한 정밀 수색을 하고 있습니다. 경기남부지방경찰청 과학수사대는 오늘(2일) 오전 9시부터 중장비와 과학수사요원 15명을 투입해 이천시 모가면 물류창고 공사 현장을 정밀 수색하고 있습니다. 오늘 수색은 사고로 숨진 사망자들의 유해 가운데 아직 수습되지 않은 일부와 유류품을 찾는 데 주력한다는 방침입니다. 앞서 경찰은 국립과학수사연구원에 의뢰한 DNA 조사를 통해 신원이 확인되지 않은 9명 가운데 8명의 신원을 확인해 유가족들에게 전했습니다. 경찰은 남은 신원 미확인자 1명의 DNA 검사 결과도 오늘 안에 나올 것으로 기대하고 있습니다. ※ '당신의 제보가 뉴스가 됩니다' YTN은 여러분의 소중한 제보를 기다립니다. [카카오톡] YTN을 검색해 채널 추가 [전화] 02-398-8585 [메일] [email protected] [온라인 제보] www.ytn.co.kr ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0103_202005021020478614 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, [email protected], #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN & YTN PLUS 무단 전재 및 재배포금지",
"video_id": "n8dcNr14bm8"
}
| 8
|
[
"In the frame, two news anchors are seated at a desk, presenting a news story. The woman on the left is wearing a grey blazer and is holding a pen, while the man on the right is dressed in a dark suit with a tie. Behind them, there is a blurred image of a building, possibly indicating the location of the news report. The Korean text at the bottom of the screen reads \"경찰, 이천 물류창고 화재현장 정밀 수색,\" which translates to \"Police, precise search at the logistics warehouse fire scene in Icheon.\"",
"The video shows a group of people in white protective suits walking through a site with extensive debris and destruction, indicating a recent disaster. They are likely engaged in a search and rescue operation or investigation at the scene of a logistics warehouse fire in Icheon, as suggested by the Korean text at the bottom of the screen. The presence of the excavator and scattered materials further emphasizes the aftermath of a significant fire.",
"The group of people in white protective suits continues their movement through the heavily damaged area, now focusing more intently on the debris, possibly searching for survivors or evidence of the fire's cause. The text at the bottom of the screen remains consistent, indicating ongoing efforts related to the Icheon logistics warehouse fire. The excavator and scattered materials persist in the scene, reinforcing the scope of the disaster and the necessity of the current investigation or rescue efforts.",
"The group of people in white protective suits and helmets continues their movement through the heavily damaged area, focusing on the debris, possibly searching for survivors or evidence of the fire's cause. The text at the bottom of the screen indicates ongoing efforts related to the Icheon logistics warehouse fire. The individuals are likely conducting a search or investigation, as suggested by their careful examination of the area and the presence of protective gear.",
"The current frame shows a burnt-out structure, likely the aftermath of a fire, with significant damage evident on the building. The text at the bottom of the screen, '경찰, 이천 물류창고 화재현장 정밀 수색' (Police, Icheon Logistics Warehouse Fire Scene Detailed Search), suggests that the police are conducting a thorough search of the fire scene. This indicates that authorities are actively investigating the cause and aftermath of the fire, possibly looking for evidence or ensuring the area is safe.",
"The current frame continues to depict the aftermath of a fire with a focus on the burnt-out structure, showing significant damage to the building. There is a large excavator bucket visible, suggesting ongoing debris removal or investigation activities at the site. The same text '경찰, 이천 물류창고 화재현장 정밀 수색' (Police, Icheon Logistics Warehouse Fire Scene Detailed Search) is displayed, reinforcing the ongoing police search and investigation efforts at the fire scene. This indicates a continuation of the activities aimed at uncovering the cause of the fire and ensuring the area is secure.",
"The current frame continues to depict the aftermath of a fire with a focus on the burnt-out structure, showing significant damage to the building. There is a large excavator bucket visible, suggesting ongoing debris removal or investigation activities at the site. The same text '경찰, 이천 물류창고 화재현장 정밀 수색' (Police, Icheon Logistics Warehouse Fire Scene Detailed Search) is displayed, reinforcing the ongoing police search and investigation efforts at the fire scene. This indicates a continuation of the activities aimed at uncovering the cause of the fire and ensuring the area is secure.",
"In the current frame, the focus shifts to a group of individuals wearing protective white suits and helmets, walking through the debris-filled area. They are likely investigators or cleanup crew members, engaged in the ongoing efforts to manage the aftermath of the fire. The presence of the large excavator bucket in the background suggests that the site is still undergoing debris removal or further inspection. The text '경찰, 이천 물류창고 화재현장 정밀 수색' (Police, Icheon Logistics Warehouse Fire Scene Detailed Search) remains displayed, indicating the continuous police search and investigation at the site."
] |
n8dcNr14bm8
|
A news report covers a logistics warehouse fire in Icheon, with two anchors presenting the story. The scene then shifts to the fire site, where a group of people in white protective suits conduct a thorough search and investigation, likely looking for survivors or evidence of the fire's cause. The aftermath of the fire is evident, with extensive debris and destruction visible, and excavators are used for debris removal. Throughout the video, the police are shown to be actively involved in a detailed search of the fire scene, aiming to uncover the cause of the fire and ensure the area is secure. The video depicts the ongoing efforts of investigators and cleanup crews as they navigate the burnt-out structure and debris-filled area, with a focus on the police's continuous search and investigation at the site.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=Z1TmlndGWrg",
"video_description": "대규모 인명 피해가 발생한 경기 이천 물류센터 공사장 화재와 관련해 경찰이 전담 수사본부를 편성했습니다. 경기 남부지방경찰청은 광역수사대와 과학수사대 등 125명 규모의 전담 수사본부를 편성했다고 밝혔습니다. 수사본부는 오늘(30일) 오전 10시 반 국립과학수사연구원, 소방당국과 함께 합동으로 현장감식을 진행할 예정입니다. 또, 공사 과정에서 소방법이나 건축법을 위반한 사항이 있는지 확인할 방침입니다. 신준명[[email protected]] ※ '당신의 제보가 뉴스가 됩니다' YTN은 여러분의 소중한 제보를 기다립니다. [카카오톡] YTN을 검색해 채널 추가 [전화] 02-398-8585 [메일] [email protected] [온라인 제보] www.ytn.co.kr ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0103_202004300027155233 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, [email protected], #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN & YTN PLUS 무단 전재 및 재배포금지",
"video_id": "Z1TmlndGWrg"
}
| 8
|
[
"The image shows a large, multi-story building with visible fire damage and smoke coming from the upper floors. Several ambulances are parked in front of the building, indicating an emergency response to the incident. People are gathered around the scene, possibly emergency personnel and bystanders. The scene suggests a fire at the building, likely a chemical plant, as indicated by the text in the image.",
"The current frame shows firefighters gathered around a fire truck, with the damaged building in the background, indicating ongoing emergency response efforts. Text in the image suggests the incident is linked to a chemical plant, and today is a day of work inspections.",
"Firefighters are present near a fire truck at the scene of a chemical plant incident. The background shows a damaged building, indicating an emergency response. Text in the image refers to a hydrogen plant explosion and an inspection today.",
"The current frame shows a close-up of a building with a shattered window. The building appears damaged, likely due to the explosion mentioned in the previous frame. The text in the image still refers to a hydrogen plant explosion and mentions an inspection taking place today. The scene indicates ongoing investigation at the site of the incident.",
"The current frame shows a damaged building with blackened siding and a partially melted window frame, indicative of the aftermath of a fire. Text on the image refers to a hydrogen plant explosion and mentions an inspection taking place today. The scene suggests an ongoing investigation at the site of the incident.",
"The current frame shows a close-up view of the building's facade, which appears to be heavily damaged due to a fire. The siding is blackened and melted in places, indicating the intensity of the fire. There is visible text on the image that reads \"이천 물류센터 화재 수사본부 편성...오늘 현장검증\" (Translation: \"Establishment of the investigation team for the Icheon logistics center fire...On-site inspection today\"). The text suggests that an investigation is currently being conducted at the site of the fire. The overall scene depicts the aftermath of a fire, with the building's exterior showing significant damage.",
"The current frame continues to focus on the heavily damaged building's facade, which shows extensive blackening and melting due to the fire. The text \"이천 물류센터 화재 수사본부 편성...오늘 현장검증\" (Translation: \"Establishment of the investigation team for the Icheon logistics center fire...On-site inspection today\") remains visible, reinforcing the ongoing investigation. The scene emphasizes the aftermath of the fire, highlighting the building's significant exterior damage.",
"The scene depicts a group of emergency responders and officials gathered near a tent and a damaged structure, likely part of the response to the fire at the logistics center. Individuals in orange suits and white protective clothing are visible, with some wearing helmets and masks, suggesting a coordinated effort in assessing the situation. Ambulances are present, indicating medical assistance is available. The focus is on the response and investigation activities post-fire."
] |
Z1TmlndGWrg
|
A fire broke out at a chemical plant, specifically a hydrogen plant, resulting in significant damage to the building and prompting an emergency response. Firefighters and emergency personnel were dispatched to the scene, with ambulances present to provide medical assistance. The incident occurred on a day when work inspections were being conducted. Following the fire, an investigation was launched, with a team established to conduct an on-site inspection and assessment of the damage. The investigation is ongoing, with officials and emergency responders working together to determine the cause of the fire and extent of the damage. The scene shows the aftermath of the fire, with the building's exterior heavily damaged, including blackened and melted siding, shattered windows, and a generally charred appearance.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=tHSh4jwdIJg",
"video_description": "29일 오후 1시 반쯤 경기도 이천시 모가면의 한 물류창고 공사현장에서 불이 났습니다. 이 불로 오후 5시 기준 25명이 숨진 것으로 소방당국은 추정하고 있습니다. 불이 났을 당시 현장에서 9개 업체, 80여 명이 작업 중이던 것으로 알려져 인명 피해가 더 커질 가능성도 있는 상황입니다. 물류창고 지하 2층에서 불이 시작된 것으로 추정하며, 소방당국은 \"불이 빠르게 확산되는 것으로 봐서 가연성 물질인 우레탄폼 작업 중 화재가 난 것으로 추정한다\"고 말했습니다. 현장 영상을 전해드립니다. 이천 물류창고 화재 현장 상황…소방당국 \"우레탄폼 원인 추정\" / 비디오머그 ✔신뢰할 수 있는 재미, 비디오머그 VIDEOMUG #비디오머그 #이천 #물류창고_화재 ▶비디오머그 채널 구독하기 : https://n.sbs.co.kr/mugTube ▶Homepage : https://n.sbs.co.kr/videomug ▶Facebook : https://www.facebook.com/videomug ▶Twitter : https://twitter.com/videomug_sbs",
"video_id": "tHSh4jwdIJg"
}
| 8
|
[
"The image shows a large fire with thick, dark smoke rising into the air. Vehicles, including a construction crane, are visible on the road, indicating an urban or industrial area. There are buildings and infrastructure in the background. The text in Korean at the bottom of the image suggests that an accident occurred in the early afternoon.",
"The current frame shows a large fire still raging with thick, dark smoke billowing from a building. Several individuals, possibly emergency responders or bystanders, are present on the scene, with some appearing to be in communication or coordinating efforts. Vehicles, including a white van, are parked on the road, indicating a response to the incident. The text in Korean indicates that the fire resulted in the death of 25 people. The situation appears to be under control, with responders actively managing the scene.",
"The current frame shows a large fire still raging with thick, dark smoke billowing from a building. Several individuals, possibly emergency responders or bystanders, are present on the scene, with some appearing to be in communication or coordinating efforts. Vehicles, including a white van, are parked on the road, indicating a response to the incident. The text in Korean indicates that the fire resulted in the death of 90 people. The situation appears to be under control, with responders actively managing the scene.",
"The scene captures a large industrial building engulfed in flames, with thick, dark smoke billowing from multiple points. Emergency vehicles and personnel are visible on the street, indicating an ongoing response. A traffic light and pedestrian crossing suggest the area is a busy intersection. The text in Korean states that the fire started during the operation of an urea production facility in the second floor of a multi-story building, resulting in a fire that started in the facility.",
"A group of firefighters and emergency personnel are actively engaged in a press briefing or coordination effort outside a large, multi-story building that has been damaged by fire. Some firefighters are seen pointing and gesturing towards a large diagram or plan attached to a board, likely discussing the incident's details or response strategies. Other individuals, including media representatives with cameras and microphones, are present, capturing the event. The background reveals the damaged building with smoke still visible, indicating the fire is either ongoing or has recently been extinguished. The text overlay in Korean suggests the situation is being reviewed or discussed, potentially involving the fire's cause and management.",
"The current frame shows a large fire at an industrial or warehouse facility, with thick black smoke billowing into the sky. The fire is visible on the left side of the image, with flames and smoke clearly indicating an intense blaze. The scene includes a parking lot with numerous vehicles, suggesting the presence of personnel or bystanders. The surrounding area appears to be a mix of greenery and structures, possibly indicating a semi-urban or industrial zone. The text overlay in Korean reads, \"오전 5시 현재 불길은 거의 잡혔지만 지하에 연기가 가득 차 접근이 쉽지 않은 상황,\" which translates to \"As of 5 AM, the fire is almost under control, but smoke is densely filling the basement, making access difficult.\" This indicates that while the fire is nearly contained, the situation remains challenging due to the smoke in the basement area.",
"The video depicts a large fire at an industrial or warehouse facility, with thick black smoke billowing into the sky. The fire is visible on the left side of the image, with flames and smoke clearly indicating an intense blaze. The scene includes a parking lot with numerous vehicles, suggesting the presence of personnel or bystanders. The surrounding area appears to be a mix of greenery and structures, possibly indicating a semi-urban or industrial zone. The text overlay in Korean reads, \"구독하기\" which translates to \"Subscribe,\" indicating a call to action for viewers to subscribe to the channel.",
"The scene is a simple white background with a logo in the center. The logo features a play button icon within a circle, followed by Korean text \"비디오머그\" which translates to \"Video Mug.\" Below the logo, additional Korean text appears, likely providing information or credits related to the content creator or production team. The transition from the intense fire scene to this frame suggests the end of the video segment or an intermission, possibly prompting viewers to subscribe or offering credits before the video concludes."
] |
tHSh4jwdIJg
|
A large fire broke out at an industrial or warehouse facility, specifically at a urea production facility on the second floor of a multi-story building, resulting in significant damage and loss of life. The fire, which occurred in the early afternoon, was intense, with thick, dark smoke billowing from the building. Emergency responders, including firefighters, were quickly on the scene, working to manage the situation and extinguish the flames. Despite their efforts, the fire resulted in a substantial number of fatalities, with reports indicating 25 to 90 people lost their lives. As the situation was brought under control, responders and personnel engaged in coordination efforts, discussing the incident's details and response strategies. The fire was nearly contained by the early morning hours, but smoke in the basement area posed challenges for access. The video concludes with a call to action, prompting viewers to subscribe to the channel, and ends with a logo and credits for the content creator or production team.
|
On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.
|
[
"A person setting fire to the office building in Daegu, South Korea on 9 June 2022",
"A person setting fire to the office building during the arson attack in Daegu, South Korea on 9 June 2022",
"Flames engulfing a building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing the building during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating the office building in a state of panic due to a fire in Daegu, South Korea on 9 June 2022",
"People evacuating the office building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Firefighters arriving at the scene of a fire in Daegu, South Korea on 9 June 2022 to extinguish the blaze",
"Firefighters arriving at the scene to extinguish the fire during the arson attack in Daegu, South Korea on June 9, 2022",
"Paramedics treating injured people outside the building after fire in Daegu, South Korea on 9 June 2022",
"Paramedics treating injured people outside the building after arson attack in Daegu, South Korea on June 9, 2022"
] |
[
"Firefighters battling the blaze at the office building in Daegu, South Korea on June 9, 2022",
"Firefighters battling the blaze at the office building in Daegu, South Korea after alleged arson attack on 9 June 2022",
"People evacuating a building in a state of panic due to a fire in Daegu, South Korea on June 9, 2022",
"People evacuating the building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Emergency responders providing medical aid to injured victims of the June 9, 2022 fire in Daegu, South Korea",
"Emergency responders providing medical aid to injured victims of the June 9 2022 arson attack in Daegu, South Korea",
"Flames engulfing parts of the office building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing parts of the office building in Daegu, South Korea during the arson attack on 9 June 2022",
"Rescue teams searching for survivors in the building damaged by the fire in Daegu, South Korea on 9 June 2022",
"Rescue teams searching for survivors in the damaged building after the arson attack in Daegu, South Korea on 9 June 2022"
] |
[
"Flames engulfing the office building in Daegu, South Korea on 9 June 2022 fire incident",
"Flames engulfing the office building in Daegu, South Korea due to arson attack on 9 June 2022",
"Firefighters arriving at the scene and battling the blaze in Daegu, South Korea on 9 June 2022 during a large fire incident",
"Firefighters arriving at the scene and battling the blaze during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating building after fire in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"People evacuating building after arson attack in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"Emergency medical personnel treating injured individuals outside the building after fire in Daegu, South Korea on 9 June 2022",
"Emergency medical personnel treating injured individuals outside the building after the arson attack in Daegu, South Korea on June 9, 2022",
"Damage to the office building in Daegu, South Korea after the fire on 9 June 2022 has been extinguished",
"Damage to the office building in Daegu, South Korea after the arson attack fire was extinguished on 9 June 2022"
] |
{
"article_url": "https://namu.wiki/w/%EB%8C%80%EA%B5%AC%20%EB%B3%80%ED%98%B8%EC%82%AC%20%EC%82%AC%EB%AC%B4%EC%8B%A4%20%EB%B0%A9%ED%99%94%20%EC%82%AC%EA%B1%B4",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: To extract events from the given query, it makes sense to focus on the concrete and visual aspects of the fire and its aftermath, considering what could be reasonably captured in a video. This includes the fire itself, the response of emergency services, and the impact on the building and its occupants.\n\nEVENTS:\n1. Flames engulfing the office building in Daegu\n2. Firefighters arriving at the scene and battling the blaze\n3. People evacuating the building, some injured and covered in soot\n4. Emergency medical personnel treating injured individuals outside the building\n5. Damage to the office building after the fire has been extinguished",
"en_article_excerpt": "On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.",
"en_article_url": "https://en.wikipedia.org/wiki/Daegu_office_fire",
"event_category": "disasters",
"event_name": "daegu_office_fire",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the actions and consequences leading up to and resulting from the arson attack, such as the fire breaking out, people evacuating, and emergency responders arriving. These events are concrete, visual, and likely to be captured in a video related to the incident.\n\nEVENTS:\n1. A person setting fire to the office building\n2. Flames engulfing the building\n3. People evacuating the office building in a state of panic\n4. Firefighters arriving at the scene to extinguish the fire\n5. Paramedics treating injured people outside the building",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a fire at an office building in Daegu, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage to the building, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the office building\n2. People evacuating the building in a state of panic\n3. Emergency responders providing medical aid to injured victims\n4. Flames engulfing parts of the office building\n5. Rescue teams searching for survivors in the damaged building",
"video_URL": "http://youtube.com/watch?v=I2CxZCzE5pE",
"video_description": "지금부턴 어제(9일) 대구의 한 변호사 사무실에서 난 화재 관련해서 저희가 새롭게 취재한 내용 전해드리겠습니다. 저희 취재진이 사고가 난 건물의 내부 영상을 입수했습니다. 불이 시작된 건물 2층은 형체를 알아보기 어려울 정도로 검게 타버린 모습이었습니다. ▶ 기사 전문 https://news.jtbc.joins.com/html/151/NB12062151.html ▶ 뉴스룸 다시보기 (https://bit.ly/2nxI8jQ) #이승환기자 #JTBC뉴스룸 ☞JTBC뉴스레터 구독하기 (https://bit.ly/3IOFY5H) ☞JTBC유튜브 구독하기 (https://bit.ly/2hYgWZg) ☞JTBC유튜브 커뮤니티 (https://bit.ly/2LZIwke) #JTBC뉴스 공식 페이지 (홈페이지) https://news.jtbc.joins.com (APP) https://bit.ly/1r04W2D 페이스북 https://www.facebook.com/jtbcnews 트위터 https://twitter.com/JTBC_news 인스타그램 https://www.instagram.com/jtbcnews ☏ 제보하기 https://bit.ly/1krluzF 방송사 : JTBC (https://jtbc.joins.com)",
"video_id": "I2CxZCzE5pE"
}
| 8
|
[
"A news anchor stands in front of a screen displaying a charred and burned interior, likely from a fire incident. The text on the screen reads \"지옥이 된 '검은 사무실'...대구 화재 최초 희생\" (Hellish 'Black Office'...First Victim of Daegu Fire). Individuals in protective suits are inspecting the area, using flashlights.",
"The current frame shows a close-up view of a set of stairs with visible signs of extensive damage, including charred and blackened areas, indicating they have been affected by a fire. The text \"지옥이 된 '검은 사무실'\" (Hellish 'Black Office') is visible, emphasizing the severity of the incident. This scene continues to depict the aftermath of the fire, focusing on the damaged infrastructure, and aligns with the previous frame's description of a fire-related event and the investigation by individuals in protective suits.",
"The current frame depicts a dimly lit room with several windows in the background, allowing a small amount of light to enter. The room appears to be in disarray, with debris scattered on the floor and visible burn marks and damage to the walls and ceiling. The text \"지옥이 된 '검은 사무실'\" (Hellish 'Black Office') is visible, indicating that the scene is part of the ongoing depiction of a severely damaged office space, likely as a result of a fire. The overall atmosphere is one of devastation and abandonment.",
"The scene continues to depict the aftermath of a fire, showing a dark, damaged area with debris on the floor. The text \"황급히 대피했던 사람들은 다시 사고 현장 찾아\" (People who hastily fled are returning to the accident site) is visible, suggesting that individuals who escaped the fire are now returning to the affected area, possibly out of concern or to assess the damage. The atmosphere remains somber and reflective of the ongoing impact of the disaster.",
"A group of people walks down a hallway, with the text \"화재 건물 사무실 직원\" (Fire building office staff) indicating they are employees of the building. The somber atmosphere persists, reflecting the aftermath of a fire, as the employees return to the scene, possibly to check on the office or personal belongings.",
"In this frame, several people are gathered outside a building, with some wearing masks. They appear to be discussing something significant, possibly related to the fire mentioned earlier. The text \"화재 건물 사무실 변호사\" suggests they are now speaking with a lawyer, indicating a shift from the earlier focus on employees to legal or investigative matters. The presence of a person holding a microphone hints at media involvement, suggesting the situation is being reported or documented. The context continues to emphasize the serious aftermath of the fire.",
"The video now shifts focus to a close-up of what appears to be burnt or charred material, possibly from the fire mentioned earlier. The scene is dominated by dark, blackened substances with patches of white or lighter-colored material, suggesting areas of residue or ash. This frame likely serves to emphasize the destructive impact of the fire on the building and its contents. There are no people or identifiable text in this frame, placing the focus solely on the physical damage caused by the fire.",
"The current frame shows a news broadcast setup with a studio background depicting a cityscape at dusk. The \"JTBC News\" logo is prominently displayed in the upper left corner. The text in Korean at the bottom of the screen reads \"공식 채널에서 더 많은 뉴스를 만나보세요,\" which translates to \"See more news on the official channel.\" There are no people visible in this frame, and the focus is on promoting the JTBC News channel, emphasizing its availability for additional news content."
] |
I2CxZCzE5pE
|
A news report covers the aftermath of a severe fire incident at a location referred to as the "Black Office" in Daegu. The video shows the charred and damaged interior of the building, with individuals in protective suits inspecting the area. The news anchor presents the story in front of a screen displaying images of the fire's destruction. The footage then shifts to show the damaged infrastructure, including stairs and a room filled with debris and burn marks. As the story unfolds, it becomes clear that people who escaped the fire are returning to the scene, and employees of the building are assessing the damage. The situation evolves to include legal discussions with a lawyer and media coverage, highlighting the seriousness of the incident. The video also focuses on the physical destruction caused by the fire, showing close-ups of burnt material. Finally, the report concludes with a promotion for the news channel, inviting viewers to seek more information on the official channel. Overall, the video depicts a devastating fire incident and its consequences, including the investigation, return of survivors, and the beginning of legal and media involvement.
|
On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.
|
[
"A person setting fire to the office building in Daegu, South Korea on 9 June 2022",
"A person setting fire to the office building during the arson attack in Daegu, South Korea on 9 June 2022",
"Flames engulfing a building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing the building during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating the office building in a state of panic due to a fire in Daegu, South Korea on 9 June 2022",
"People evacuating the office building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Firefighters arriving at the scene of a fire in Daegu, South Korea on 9 June 2022 to extinguish the blaze",
"Firefighters arriving at the scene to extinguish the fire during the arson attack in Daegu, South Korea on June 9, 2022",
"Paramedics treating injured people outside the building after fire in Daegu, South Korea on 9 June 2022",
"Paramedics treating injured people outside the building after arson attack in Daegu, South Korea on June 9, 2022"
] |
[
"Firefighters battling the blaze at the office building in Daegu, South Korea on June 9, 2022",
"Firefighters battling the blaze at the office building in Daegu, South Korea after alleged arson attack on 9 June 2022",
"People evacuating a building in a state of panic due to a fire in Daegu, South Korea on June 9, 2022",
"People evacuating the building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Emergency responders providing medical aid to injured victims of the June 9, 2022 fire in Daegu, South Korea",
"Emergency responders providing medical aid to injured victims of the June 9 2022 arson attack in Daegu, South Korea",
"Flames engulfing parts of the office building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing parts of the office building in Daegu, South Korea during the arson attack on 9 June 2022",
"Rescue teams searching for survivors in the building damaged by the fire in Daegu, South Korea on 9 June 2022",
"Rescue teams searching for survivors in the damaged building after the arson attack in Daegu, South Korea on 9 June 2022"
] |
[
"Flames engulfing the office building in Daegu, South Korea on 9 June 2022 fire incident",
"Flames engulfing the office building in Daegu, South Korea due to arson attack on 9 June 2022",
"Firefighters arriving at the scene and battling the blaze in Daegu, South Korea on 9 June 2022 during a large fire incident",
"Firefighters arriving at the scene and battling the blaze during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating building after fire in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"People evacuating building after arson attack in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"Emergency medical personnel treating injured individuals outside the building after fire in Daegu, South Korea on 9 June 2022",
"Emergency medical personnel treating injured individuals outside the building after the arson attack in Daegu, South Korea on June 9, 2022",
"Damage to the office building in Daegu, South Korea after the fire on 9 June 2022 has been extinguished",
"Damage to the office building in Daegu, South Korea after the arson attack fire was extinguished on 9 June 2022"
] |
{
"article_url": "https://namu.wiki/w/%EB%8C%80%EA%B5%AC%20%EB%B3%80%ED%98%B8%EC%82%AC%20%EC%82%AC%EB%AC%B4%EC%8B%A4%20%EB%B0%A9%ED%99%94%20%EC%82%AC%EA%B1%B4",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: To extract events from the given query, it makes sense to focus on the concrete and visual aspects of the fire and its aftermath, considering what could be reasonably captured in a video. This includes the fire itself, the response of emergency services, and the impact on the building and its occupants.\n\nEVENTS:\n1. Flames engulfing the office building in Daegu\n2. Firefighters arriving at the scene and battling the blaze\n3. People evacuating the building, some injured and covered in soot\n4. Emergency medical personnel treating injured individuals outside the building\n5. Damage to the office building after the fire has been extinguished",
"en_article_excerpt": "On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.",
"en_article_url": "https://en.wikipedia.org/wiki/Daegu_office_fire",
"event_category": "disasters",
"event_name": "daegu_office_fire",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the actions and consequences leading up to and resulting from the arson attack, such as the fire breaking out, people evacuating, and emergency responders arriving. These events are concrete, visual, and likely to be captured in a video related to the incident.\n\nEVENTS:\n1. A person setting fire to the office building\n2. Flames engulfing the building\n3. People evacuating the office building in a state of panic\n4. Firefighters arriving at the scene to extinguish the fire\n5. Paramedics treating injured people outside the building",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a fire at an office building in Daegu, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage to the building, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the office building\n2. People evacuating the building in a state of panic\n3. Emergency responders providing medical aid to injured victims\n4. Flames engulfing parts of the office building\n5. Rescue teams searching for survivors in the damaged building",
"video_URL": "http://youtube.com/watch?v=oVzTD-Qy5HM",
"video_description": "대구 변호사 사무실 빌딩 방화 추정 화재…7명 사망 [앵커] 오늘(9일) 낮 대구 지법 근처의 한 변호사 사무실에서 방화로 보이는 화재가 발생해, 방화 용의자 1명을 포함해 7명이 숨지고 40여 명이 다쳤습니다. 현장 취재기자 연결해 자세한 소식 들어봅니다. 정지훈 기자. [기자] 네, 대구 변호사 사무실 빌딩 화재 현장에 나와 있습니다. 제 바로 뒤편 건물을 보시면 전면 유리창들이 깨진 걸 보실 수 있을텐데요. 신고를 받고 출동한 소방당국이 화재 진압과 구조를 위해 일부러 깨드린 겁니다. 당시 상황이 얼마나 긴박했는지를 알 수 있습니다. 이 건물은 지하 2층, 지상 5층짜리 건물로 오늘(9일) 오전 10시 55분쯤 건물 2층에서 불이 났습니다. 불은 소방 당국에 의해 20여 분만에 꺼졌지만, 남자 5명, 여자 2명 등 7명이 숨지고 40여 명이 화상 또는 연기를 흡입해 병원 치료를 받고 있습니다. 이들 사망자는 2층 203호에서 모두 발견됐는데요. 화재 발생 당시 119에는 \"건물 2층에서 검은 연기가 보이고 폭발음이 들렸다\"는 신고가 접수됐습니다. 사망자의 신원이 아직 확인되지 않았습니다. 같은 장소에서 방화 용의자도 숨진 채 발견됐습니다. 불이 나자 건물 3층에 있던 사람들은 4층 등 건물 위층으로, 일부는 건물 밖에 설치된 비상계단을 통해 옥상으로 대피하기도 했습니다. 화재 현장에 있었던 목격자의 말 들어보시겠습니다. [현장 목격자] \"어느 순간 폭발음이 팡 터지면서 유리창 깨지는 소리가 계속 나고 제가 너무 놀라서 상담실에서 뛰쳐 나와서 문을 열려고 하니 이미 뜨거웠어요. 그래서 몸으로 문을 밀쳐서 열고…\" 소방당국은 화재 진압 과정에서 급격히 연소가 확대돼 인명 피해 규모가 커졌다고 설명했습니다. 당국은 브리핑에서 \"화재 건물 지하층에만 스프링클러가 있고 지상층에는 스프링클러가 설치돼 있지 않다\"고 밝혔습니다. 화재가 발생한 빌딩은 법원 뒤쪽에 위치해 변호사 사무실이 밀집한 곳입니다. 경찰은 50대 방화 용의자가 CCTV상 주거지에서 뭔가를 들고 나오는 장면을 확인하고 자세한 화재 경위를 조사하고 있는데요. 경찰은 불이 난 변호사 사무실에 의뢰된 송사 사건의 상대인 용의자가 사무실에 불을 낸 것으로 보고, 수사전담팀을 편성해 사건 발생 경위 등을 집중 조사할 방침입니다. 지금까지 대구에서 연합뉴스TV 정지훈입니다. #대구_변호사_사무실 #폭발 #방화 연합뉴스TV 기사문의 및 제보 : 카톡/라인 jebo23 ▣ 연합뉴스TV 유튜브 채널 구독 https://goo.gl/VuCJMi ▣ 대한민국 뉴스의 시작 연합뉴스TV / Yonhap News TV http://www.yonhapnewstv.co.kr/",
"video_id": "oVzTD-Qy5HM"
}
| 8
|
[
"The image appears to be a screenshot from a news broadcast on \"연합뉴스 TV\" (Yonhap News TV). In the main frame, there are two anchors in the news studio. The male anchor is seated on the left, and the female anchor is on the right. The headline in Korean at the top reads \"방화 추정불...7명 사망,\" which translates to \"Fire suspected...7 people dead.\" On the right side, there is a smaller frame showing a reporter standing outside a building, possibly providing a live report related to the news story. The reporter is holding a microphone and a smartphone, wearing a white shirt, and has a badge or ID around his neck. In the background, there is a crowd of people and some police officers, suggesting an incident scene. The timestamp at the bottom left shows \"16:48,\" and there is additional news ticker text in Korean at the bottom of the screen.",
"The current frame continues from the news broadcast on \"연합뉴스 TV\" (Yonhap News TV). The focus is on the reporter standing outside a building, presumably delivering a live report related to the news story. The reporter, wearing a white shirt and a badge or ID, is holding a microphone and a smartphone. In the background, there are several people, including police officers, suggesting an incident scene. The headline at the top of the screen reads \"방화 추정불...7명 사망,\" indicating a fire incident resulting in seven deaths. The timestamp at the bottom left has advanced to \"16:49,\" and there is additional news ticker text in Korean at the bottom of the screen, which mentions \"9일 오전 대구지법 인근 변호사사무실 빌딩 화재,\" translating to \"Fire at a lawyer's office building near Daegu District Court on the morning of the 9th.\"",
"The current frame continues to focus on the building from the previous frames, which appears to be the site of the incident being reported. The building has multiple windows, some of which are damaged or broken, suggesting the aftermath of a fire. A ladder is positioned against the building, indicating ongoing rescue or investigation efforts. There are several people present, including police officers and emergency responders, suggesting a coordinated response to the incident. The headline at the top of the screen remains \"방화 추정불...7명 사망\" (Fire incident resulting in seven deaths). The timestamp at the bottom left is still \"16:49,\" and there is additional news ticker text in Korean at the bottom of the screen, which continues to provide context about the incident.",
"The current frame depicts a group of police officers in blue uniforms, some wearing masks, walking and communicating with each other in an outdoor setting. The focus is on the scene management and coordination of the emergency response. The headline at the top of the screen is \"방화 추정불...7명 사망\" (Fire incident resulting in seven deaths), indicating the gravity of the situation. The timestamp at the bottom left remains \"16:49,\" and there is additional news ticker text in Korean providing more context about the incident. The presence of the officers suggests that they are actively involved in the investigation and management of the fire scene.",
"The current frame shows an aerial view of a building with a large glass window reflecting the outside scene. There is a fire truck parked on the street, and several emergency personnel are visible near the building. The headline at the top of the screen remains \"방화 추정불...7명 사망\" (Fire incident resulting in seven deaths), emphasizing the severity of the event. The timestamp is now \"16:50,\" indicating the passage of one minute. The news ticker at the bottom continues to provide context about the incident, mentioning the fire at a school and the involvement of the police. The presence of the fire truck and emergency personnel suggests ongoing efforts to manage the situation and investigate the cause of the fire.",
"The current frame captures a closer view of the building, showing the extent of the damage to the windows. The timestamp has advanced to \"16:52,\" indicating further progression in the incident. The headline remains unchanged, reiterating the tragic outcome of the fire incident. The news ticker provides additional details about the school fire, including the location of the fire at \"정치훈 기자 대구 변호사빌딩 방화 현장\" (Daegu Lawyer Building arson site) and the involvement of the police. The ongoing presence of emergency personnel and the fire truck suggests that rescue and investigation efforts are still underway.",
"The scene shows individuals in protective suits exiting a building, indicating an ongoing investigation or emergency response. The timestamp is \"16:50,\" and a banner at the bottom mentions \"경찰 '방화 여부 조사중'...정확한 범행 동기 조사\" (Police 'Investigating Arson'...Investigating Accurate Motive). The presence of emergency personnel and the text suggest that authorities are investigating a possible arson case at a building.",
"The scene continues outside the same building with individuals in protective suits present, suggesting the investigation or emergency response is ongoing. The timestamp is \"16:50,\" and text at the bottom reads \"국방연구원 '북, 울해 미' 코스닥 877.18 2.23.\" This indicates that the ongoing investigation is linked to the National Defense Research Institute, and there is an update on the KOSDAQ index. The presence of security personnel and the ongoing nature of their activities suggest that authorities are still investigating, possibly related to a security or intelligence matter involving North Korea and U.S. military cooperation."
] |
oVzTD-Qy5HM
|
A news broadcast on Yonhap News TV reports a fire incident at a lawyer's office building near Daegu District Court, resulting in seven deaths. The incident is suspected to be arson, with police investigating the cause and motive. Emergency responders and police officers are on the scene, managing the situation and conducting an investigation. The news broadcast provides live updates, with reporters on the ground and aerial views of the building, showing damaged windows and a fire truck present. Authorities in protective suits are seen exiting the building, indicating an ongoing investigation. The police are working to determine if the fire was indeed arson and are investigating the motive behind the incident.
|
On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.
|
[
"A person setting fire to the office building in Daegu, South Korea on 9 June 2022",
"A person setting fire to the office building during the arson attack in Daegu, South Korea on 9 June 2022",
"Flames engulfing a building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing the building during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating the office building in a state of panic due to a fire in Daegu, South Korea on 9 June 2022",
"People evacuating the office building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Firefighters arriving at the scene of a fire in Daegu, South Korea on 9 June 2022 to extinguish the blaze",
"Firefighters arriving at the scene to extinguish the fire during the arson attack in Daegu, South Korea on June 9, 2022",
"Paramedics treating injured people outside the building after fire in Daegu, South Korea on 9 June 2022",
"Paramedics treating injured people outside the building after arson attack in Daegu, South Korea on June 9, 2022"
] |
[
"Firefighters battling the blaze at the office building in Daegu, South Korea on June 9, 2022",
"Firefighters battling the blaze at the office building in Daegu, South Korea after alleged arson attack on 9 June 2022",
"People evacuating a building in a state of panic due to a fire in Daegu, South Korea on June 9, 2022",
"People evacuating the building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Emergency responders providing medical aid to injured victims of the June 9, 2022 fire in Daegu, South Korea",
"Emergency responders providing medical aid to injured victims of the June 9 2022 arson attack in Daegu, South Korea",
"Flames engulfing parts of the office building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing parts of the office building in Daegu, South Korea during the arson attack on 9 June 2022",
"Rescue teams searching for survivors in the building damaged by the fire in Daegu, South Korea on 9 June 2022",
"Rescue teams searching for survivors in the damaged building after the arson attack in Daegu, South Korea on 9 June 2022"
] |
[
"Flames engulfing the office building in Daegu, South Korea on 9 June 2022 fire incident",
"Flames engulfing the office building in Daegu, South Korea due to arson attack on 9 June 2022",
"Firefighters arriving at the scene and battling the blaze in Daegu, South Korea on 9 June 2022 during a large fire incident",
"Firefighters arriving at the scene and battling the blaze during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating building after fire in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"People evacuating building after arson attack in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"Emergency medical personnel treating injured individuals outside the building after fire in Daegu, South Korea on 9 June 2022",
"Emergency medical personnel treating injured individuals outside the building after the arson attack in Daegu, South Korea on June 9, 2022",
"Damage to the office building in Daegu, South Korea after the fire on 9 June 2022 has been extinguished",
"Damage to the office building in Daegu, South Korea after the arson attack fire was extinguished on 9 June 2022"
] |
{
"article_url": "https://namu.wiki/w/%EB%8C%80%EA%B5%AC%20%EB%B3%80%ED%98%B8%EC%82%AC%20%EC%82%AC%EB%AC%B4%EC%8B%A4%20%EB%B0%A9%ED%99%94%20%EC%82%AC%EA%B1%B4",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: To extract events from the given query, it makes sense to focus on the concrete and visual aspects of the fire and its aftermath, considering what could be reasonably captured in a video. This includes the fire itself, the response of emergency services, and the impact on the building and its occupants.\n\nEVENTS:\n1. Flames engulfing the office building in Daegu\n2. Firefighters arriving at the scene and battling the blaze\n3. People evacuating the building, some injured and covered in soot\n4. Emergency medical personnel treating injured individuals outside the building\n5. Damage to the office building after the fire has been extinguished",
"en_article_excerpt": "On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.",
"en_article_url": "https://en.wikipedia.org/wiki/Daegu_office_fire",
"event_category": "disasters",
"event_name": "daegu_office_fire",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the actions and consequences leading up to and resulting from the arson attack, such as the fire breaking out, people evacuating, and emergency responders arriving. These events are concrete, visual, and likely to be captured in a video related to the incident.\n\nEVENTS:\n1. A person setting fire to the office building\n2. Flames engulfing the building\n3. People evacuating the office building in a state of panic\n4. Firefighters arriving at the scene to extinguish the fire\n5. Paramedics treating injured people outside the building",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a fire at an office building in Daegu, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage to the building, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the office building\n2. People evacuating the building in a state of panic\n3. Emergency responders providing medical aid to injured victims\n4. Flames engulfing parts of the office building\n5. Rescue teams searching for survivors in the damaged building",
"video_URL": "http://twitter.com/i/status/1534839444830044161",
"video_description": "대구 변호사 사무실 화재",
"video_id": "1534839444830044161"
}
| 8
|
[
"A reporter is standing outdoors holding a microphone with a news channel logo, providing a report in front of a building. In the background, there's a red truck, a police officer, and a barricaded area, indicating some form of emergency or investigation. The scene appears to be a news segment covering an incident.",
"The current frame shows a building engulfed in smoke, indicating an ongoing fire. The smoke is thick, obscuring part of the building and the surrounding area. The presence of smoke suggests that emergency services may be involved in addressing the situation, consistent with the previous frame's indication of an emergency. The scene appears to be from a news broadcast, as suggested by the visible text overlay, which provides context to the unfolding incident.",
"The video captures a dramatic scene on a building rooftop, where a person is suspended on a ledge. A bystander in a white shirt is seen reaching out to the person, likely attempting to offer assistance. The background reveals other individuals who appear to be observing the situation, possibly concerned or involved in the emergency. The thick smoke from the previous frame has significantly reduced, suggesting that the immediate danger may have lessened. The KBS11 logo in the corner indicates that this is live coverage of an unfolding event, with text overlays providing additional context, such as the time and details about a nearby incident involving a police officer. This suggests that the incident on the rooftop is part of a broader emergency response situation.",
"The image shows a group of emergency responders, likely firefighters or police officers, on a rooftop with a person in a protective suit and helmet climbing a ladder. The responders are seen on a rooftop with visible signs of damage or debris, indicating an ongoing emergency situation. The KBS11 logo and text suggest live news coverage, with the emergency involving a collapsed building and a missing person, possibly a police officer. The responders seem to be working together to address the incident, highlighting the critical nature of the situation.",
"The image depicts two individuals in high-visibility vests, likely emergency responders, walking near a building at night. The scene is illuminated by emergency lights, and a sense of urgency is conveyed through their actions. The text in the image indicates a news broadcast about a collapsed building and a missing person, suggesting that the responders are involved in a rescue or investigation effort. The ongoing emergency situation is reinforced by the visible damage or debris around the area.",
"The current frame shows a close-up view of a shattered glass window, with large holes indicating significant damage. The scene suggests ongoing investigation or rescue efforts at the location of the building collapse mentioned in the previous frame. The presence of emergency responders, as indicated by the high-visibility vests in the earlier frame, implies they are assessing the damage or searching for the missing person. The broken glass is a critical element, highlighting the severity of the collapse and the potential danger to those involved in the rescue or investigation efforts.",
"Emergency responders are gathered outside a building, likely investigating a building collapse as indicated by the previous frame's shattered window. They are dressed in white protective suits, suggesting a hazardous situation, possibly involving chemicals or other dangerous materials. The responders are engaged in a discussion, likely coordinating their efforts to address the incident. A ladder is leaning against the building, indicating access to higher floors, and a fire truck is visible, reinforcing the emergency nature of the situation. The text on the screen in Korean translates to \"Confirmed: Inadequate support led to building collapse\" and \"A person inside the building is missing,\" providing context to the ongoing investigation and rescue efforts.",
"The current frame depicts a news broadcast scene. The reporter is standing outside a building, likely the site of the building collapse, holding a microphone with the KBS logo. The building in the background has a shattered window, confirming the collapse incident. The reporter is likely providing updates on the situation, including the ongoing investigation and rescue efforts. The text on the screen in Korean translates to \"Inadequate support led to building collapse\" and \"A person inside the building is missing,\" continuing the narrative of the previous frame."
] |
1534839444830044161
|
A news report covers an emergency incident involving a building collapse, with a person reported missing. The scene unfolds with a reporter providing live coverage in front of the building, where a fire is initially visible, and emergency responders are present. As the situation develops, a person is seen on the rooftop ledge, and bystanders attempt to assist. Emergency responders, including firefighters and police officers, work together to address the incident, searching for the missing person and investigating the cause of the collapse. The investigation reveals inadequate support as the cause of the collapse, and responders in protective suits assess the damage and search for the missing individual. Throughout the video, the news broadcast provides updates on the situation, including the rescue efforts and the ongoing investigation into the building collapse.
|
On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.
|
[
"A person setting fire to the office building in Daegu, South Korea on 9 June 2022",
"A person setting fire to the office building during the arson attack in Daegu, South Korea on 9 June 2022",
"Flames engulfing a building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing the building during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating the office building in a state of panic due to a fire in Daegu, South Korea on 9 June 2022",
"People evacuating the office building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Firefighters arriving at the scene of a fire in Daegu, South Korea on 9 June 2022 to extinguish the blaze",
"Firefighters arriving at the scene to extinguish the fire during the arson attack in Daegu, South Korea on June 9, 2022",
"Paramedics treating injured people outside the building after fire in Daegu, South Korea on 9 June 2022",
"Paramedics treating injured people outside the building after arson attack in Daegu, South Korea on June 9, 2022"
] |
[
"Firefighters battling the blaze at the office building in Daegu, South Korea on June 9, 2022",
"Firefighters battling the blaze at the office building in Daegu, South Korea after alleged arson attack on 9 June 2022",
"People evacuating a building in a state of panic due to a fire in Daegu, South Korea on June 9, 2022",
"People evacuating the building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Emergency responders providing medical aid to injured victims of the June 9, 2022 fire in Daegu, South Korea",
"Emergency responders providing medical aid to injured victims of the June 9 2022 arson attack in Daegu, South Korea",
"Flames engulfing parts of the office building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing parts of the office building in Daegu, South Korea during the arson attack on 9 June 2022",
"Rescue teams searching for survivors in the building damaged by the fire in Daegu, South Korea on 9 June 2022",
"Rescue teams searching for survivors in the damaged building after the arson attack in Daegu, South Korea on 9 June 2022"
] |
[
"Flames engulfing the office building in Daegu, South Korea on 9 June 2022 fire incident",
"Flames engulfing the office building in Daegu, South Korea due to arson attack on 9 June 2022",
"Firefighters arriving at the scene and battling the blaze in Daegu, South Korea on 9 June 2022 during a large fire incident",
"Firefighters arriving at the scene and battling the blaze during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating building after fire in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"People evacuating building after arson attack in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"Emergency medical personnel treating injured individuals outside the building after fire in Daegu, South Korea on 9 June 2022",
"Emergency medical personnel treating injured individuals outside the building after the arson attack in Daegu, South Korea on June 9, 2022",
"Damage to the office building in Daegu, South Korea after the fire on 9 June 2022 has been extinguished",
"Damage to the office building in Daegu, South Korea after the arson attack fire was extinguished on 9 June 2022"
] |
{
"article_url": "https://namu.wiki/w/%EB%8C%80%EA%B5%AC%20%EB%B3%80%ED%98%B8%EC%82%AC%20%EC%82%AC%EB%AC%B4%EC%8B%A4%20%EB%B0%A9%ED%99%94%20%EC%82%AC%EA%B1%B4",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: To extract events from the given query, it makes sense to focus on the concrete and visual aspects of the fire and its aftermath, considering what could be reasonably captured in a video. This includes the fire itself, the response of emergency services, and the impact on the building and its occupants.\n\nEVENTS:\n1. Flames engulfing the office building in Daegu\n2. Firefighters arriving at the scene and battling the blaze\n3. People evacuating the building, some injured and covered in soot\n4. Emergency medical personnel treating injured individuals outside the building\n5. Damage to the office building after the fire has been extinguished",
"en_article_excerpt": "On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.",
"en_article_url": "https://en.wikipedia.org/wiki/Daegu_office_fire",
"event_category": "disasters",
"event_name": "daegu_office_fire",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the actions and consequences leading up to and resulting from the arson attack, such as the fire breaking out, people evacuating, and emergency responders arriving. These events are concrete, visual, and likely to be captured in a video related to the incident.\n\nEVENTS:\n1. A person setting fire to the office building\n2. Flames engulfing the building\n3. People evacuating the office building in a state of panic\n4. Firefighters arriving at the scene to extinguish the fire\n5. Paramedics treating injured people outside the building",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a fire at an office building in Daegu, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage to the building, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the office building\n2. People evacuating the building in a state of panic\n3. Emergency responders providing medical aid to injured victims\n4. Flames engulfing parts of the office building\n5. Rescue teams searching for survivors in the damaged building",
"video_URL": "http://twitter.com/i/status/1534851387024359424",
"video_description": "흰 천 덮은 물건 든 방화 용의자…CCTV로 본 화재 순간 (출처 : JTBC) http://naver.me/xtqfdWvA 대구 방화 용의자 현장에서 숨져...\"재판 결과에 \\’앙심\\’” / YTN https://youtu.be/Msh294y6bO8 재개발투자 8억 반환소송 패소…2심 앞두고 범행",
"video_id": "1534851387024359424"
}
| 8
|
[
"The image shows a news broadcast with two anchors sitting at a desk in a studio. Behind them, a large screen displays an image of emergency responders at an incident scene. The background includes a police officer and a firefighter next to an emergency vehicle, suggesting a recent emergency or accident. The text \"YTN\" is visible in the top right corner, indicating the news channel.",
"The current frame shows a news broadcast with a split screen. On the left side, two anchors are sitting at a desk in a studio. The background behind the anchors displays a close-up of an elevator door with text in Korean: \"누워있어 방화 용의자 현장사망\" (which translates to \"Lying down, arson suspect dies at the scene\"). On the right side of the screen, there is an image of a staircase in a building with a door at the top. The text \"YTN\" is visible in the top right corner, indicating the news channel.",
"The current frame continues the news broadcast, focusing on an image of a staircase within a building. The text in Korean at the bottom of the frame reads: \"변호사 사무실에서 불...직원 6명 등 7명 숨져\" (which translates to \"Fire in lawyer's office... 7 people including 6 employees died\"). The image shows the staircase with a door at the top, maintaining the continuity of the previous frame which highlighted the incident's location. The video appears to be detailing the aftermath of a fire at a lawyer's office, emphasizing the number of fatalities.",
"The video continues with the news broadcast about the fire in the lawyer's office, showing the aftermath of the incident. The current frame features a person in a blue shirt, likely a witness or a relative of the victims, speaking to the media. In the background, there are firefighters and other emergency personnel gathered, indicating that the scene is still under investigation. The text in Korean at the bottom of the frame reads: \"정부 관계자 '불은 스토브 불씨가 원인으로 보인다.'\" (which translates to \"Government official says 'The fire is believed to have been caused by a stove ember.'\") The video seems to be providing an update on the cause of the fire and the ongoing investigation.",
"The scene shifts to an exterior view of a building entrance where police officers in protective suits are present, suggesting an ongoing investigation or forensic activity. A police van is parked nearby. The text in Korean at the top reads: \"법원 용의자 현장서 사망\" (which translates to \"Suspect died at the scene of the court\") and at the bottom: \"용의자 A씨 현장에서 숨져...분신 가능성\" (which translates to \"Suspect A died at the scene... possibility of self-immolation\"). The presence of police officers and the context of the text indicate that a suspect has died at a location associated with a legal or judicial matter, possibly by self-immolation.",
"A man in a grey blazer speaks to the camera, with emergency responders and onlookers in the background. The text on the screen reads \"정현욱 대구경찰청 강력계장\" (Jeong Hyun-wook, Chief of the Strong Force Division, Daegu Police Agency) and \"용의자 한 명의 단독 범행으로 일단 추정되는데 만약 이 용의자가 화학물질을 사용한 것이라면\" (It is initially estimated as a solo act by one suspect. However, if the suspect used a chemical substance). This suggests an ongoing investigation into a crime possibly involving a chemical substance.",
"The video captures an interior scene, likely a stairwell or hallway, with a person moving quickly through the area. The individual is wearing a green jacket and appears to be in a hurry, possibly indicating a sense of urgency or panic. The surroundings include a staircase with a handrail and a door at the end of the hallway, suggesting that this location is part of a larger building structure. The lighting in the scene is subdued, contributing to a somewhat tense atmosphere. The text \"뉴스 나이트\" (News Night) and \"방화 용의자 현장서 사망\" (Suspect of arson died at the scene) is visible, indicating that this footage is part of a news report covering the aftermath of an arson incident.",
"The current frame shifts to an exterior view of a building, focusing on the shattered windows of what appears to be a damaged or vandalized structure. The damage is severe, with large holes and jagged edges visible in the glass, suggesting significant force was used. The building is multi-storied, with reflections of other buildings visible in the intact glass sections. There is a ladder positioned against the building, indicating that some form of repair or investigation may be underway. The lighting is natural, indicating daytime, and the overall scene conveys a sense of aftermath and potential danger."
] |
1534851387024359424
|
A news broadcast reports on a fire incident at a lawyer's office, where 7 people, including 6 employees, died. The fire is believed to have been caused by a stove ember, according to government officials. The video footage shows emergency responders at the scene, including firefighters and police officers, as well as witnesses and relatives of the victims. An investigation is ongoing, with police in protective suits collecting evidence and a police van present. A suspect, possibly related to the incident, died at the scene, with speculation about the possibility of self-immolation. Authorities, including the Chief of the Strong Force Division of the Daegu Police Agency, discuss the investigation, considering the potential use of chemical substances. The footage also shows interior and exterior scenes of the building, including damaged windows and emergency responders. Overall, the video depicts a tragic incident with an ongoing investigation into its cause and circumstances.
|
On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.
|
[
"A person setting fire to the office building in Daegu, South Korea on 9 June 2022",
"A person setting fire to the office building during the arson attack in Daegu, South Korea on 9 June 2022",
"Flames engulfing a building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing the building during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating the office building in a state of panic due to a fire in Daegu, South Korea on 9 June 2022",
"People evacuating the office building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Firefighters arriving at the scene of a fire in Daegu, South Korea on 9 June 2022 to extinguish the blaze",
"Firefighters arriving at the scene to extinguish the fire during the arson attack in Daegu, South Korea on June 9, 2022",
"Paramedics treating injured people outside the building after fire in Daegu, South Korea on 9 June 2022",
"Paramedics treating injured people outside the building after arson attack in Daegu, South Korea on June 9, 2022"
] |
[
"Firefighters battling the blaze at the office building in Daegu, South Korea on June 9, 2022",
"Firefighters battling the blaze at the office building in Daegu, South Korea after alleged arson attack on 9 June 2022",
"People evacuating a building in a state of panic due to a fire in Daegu, South Korea on June 9, 2022",
"People evacuating the building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Emergency responders providing medical aid to injured victims of the June 9, 2022 fire in Daegu, South Korea",
"Emergency responders providing medical aid to injured victims of the June 9 2022 arson attack in Daegu, South Korea",
"Flames engulfing parts of the office building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing parts of the office building in Daegu, South Korea during the arson attack on 9 June 2022",
"Rescue teams searching for survivors in the building damaged by the fire in Daegu, South Korea on 9 June 2022",
"Rescue teams searching for survivors in the damaged building after the arson attack in Daegu, South Korea on 9 June 2022"
] |
[
"Flames engulfing the office building in Daegu, South Korea on 9 June 2022 fire incident",
"Flames engulfing the office building in Daegu, South Korea due to arson attack on 9 June 2022",
"Firefighters arriving at the scene and battling the blaze in Daegu, South Korea on 9 June 2022 during a large fire incident",
"Firefighters arriving at the scene and battling the blaze during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating building after fire in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"People evacuating building after arson attack in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"Emergency medical personnel treating injured individuals outside the building after fire in Daegu, South Korea on 9 June 2022",
"Emergency medical personnel treating injured individuals outside the building after the arson attack in Daegu, South Korea on June 9, 2022",
"Damage to the office building in Daegu, South Korea after the fire on 9 June 2022 has been extinguished",
"Damage to the office building in Daegu, South Korea after the arson attack fire was extinguished on 9 June 2022"
] |
{
"article_url": "https://namu.wiki/w/%EB%8C%80%EA%B5%AC%20%EB%B3%80%ED%98%B8%EC%82%AC%20%EC%82%AC%EB%AC%B4%EC%8B%A4%20%EB%B0%A9%ED%99%94%20%EC%82%AC%EA%B1%B4",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: To extract events from the given query, it makes sense to focus on the concrete and visual aspects of the fire and its aftermath, considering what could be reasonably captured in a video. This includes the fire itself, the response of emergency services, and the impact on the building and its occupants.\n\nEVENTS:\n1. Flames engulfing the office building in Daegu\n2. Firefighters arriving at the scene and battling the blaze\n3. People evacuating the building, some injured and covered in soot\n4. Emergency medical personnel treating injured individuals outside the building\n5. Damage to the office building after the fire has been extinguished",
"en_article_excerpt": "On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.",
"en_article_url": "https://en.wikipedia.org/wiki/Daegu_office_fire",
"event_category": "disasters",
"event_name": "daegu_office_fire",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the actions and consequences leading up to and resulting from the arson attack, such as the fire breaking out, people evacuating, and emergency responders arriving. These events are concrete, visual, and likely to be captured in a video related to the incident.\n\nEVENTS:\n1. A person setting fire to the office building\n2. Flames engulfing the building\n3. People evacuating the office building in a state of panic\n4. Firefighters arriving at the scene to extinguish the fire\n5. Paramedics treating injured people outside the building",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a fire at an office building in Daegu, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage to the building, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the office building\n2. People evacuating the building in a state of panic\n3. Emergency responders providing medical aid to injured victims\n4. Flames engulfing parts of the office building\n5. Rescue teams searching for survivors in the damaged building",
"video_URL": "http://youtube.com/watch?v=rzyM4QtZNNU",
"video_description": "오늘(9일) 대구광역시 수성구 범어동 대구지방법원 인근 변호사 사무실 빌딩에서 방화로 추정되는 불이 나 7명이 숨지고 49명이 다쳤습니다. 건물 CCTV를 보면 오전 10시 53분 마스크를 쓰고 빌딩에 들어서는 남성이 확인됩니다. 한 손에는 흰 천으로 덮은 확인되지 않은 물체를 든 상태로, 경찰은 천에 덮인 물체가 인화 물질이었을 것으로 보고 있습니다. 이 남성이 해당 변호사 사무실에 들어간 지 23초 만에 불길이 일어나는 모습이 확인됩니다. ▣ KBS 기사 원문보기 : http://news.kbs.co.kr/news/view.do?ncd=5482165 ▣ 제보 하기 ◇ 카카오톡 : 'KBS제보' 검색 ◇ 전화 : 02-781-1234 ◇ 홈페이지 : https://goo.gl/4bWbkG ◇ 이메일 : [email protected] #대구화재 #방화용의자 #CCTV",
"video_id": "rzyM4QtZNNU"
}
| 8
|
[
"A surveillance camera captures a dimly lit indoor area with a staircase on the left, leading to an upper level. On the right, there is a bench. The floor appears wet, and the text in Korean indicates a situation involving a person entering a building through a water-filled entrance, highlighting a possible emergency or hazardous condition.",
"A person is seen standing in the area, carrying a large white item, possibly a blanket or a jacket. They appear to be in the midst of entering or exiting the building. The staircase on the left remains visible, and the bench is still present on the right. The floor is wet, consistent with the previous frame, suggesting that the hazardous condition continues. The person's actions indicate that they are either coming in from outside, where the condition might be wetter, or going out, possibly to seek help or avoid the water-filled area.",
"The scene shows a person, now possibly wearing a dark outfit, in the same location but with a different context. They appear to be sitting on a bench, which is to the right of the frame, indicating a change in their actions from the previous frame. The staircase remains visible on the left, and the wet floor persists, suggesting the hazardous condition is ongoing. The person's new position might imply they are taking a break or waiting, possibly due to the wet conditions or other reasons related to the situation in the video.",
"The scene shows a person in the same location as the previous frame, now appearing to be seated on a bench, indicating a change in their actions. The staircase remains visible on the left, and the wet floor persists, suggesting the hazardous condition is ongoing. The person's new position might imply they are taking a break or waiting, possibly due to the wet conditions or other reasons related to the situation in the video.",
"The scene shows a person sitting on a bench in the same location as the previous frames, possibly indicating a continuation of their break or waiting. The staircase remains visible on the left, and the wet floor persists, suggesting the hazardous condition is ongoing. The person's position might imply they are taking a break or waiting, possibly due to the wet conditions or other reasons related to the situation in the video. The text \"KBS\" in the top right corner suggests the video is from a KBS broadcast.",
"The current frame features a person sitting on a bench, continuing from the previous scene, with the staircase still visible on the left side, indicating they are likely taking a break or waiting due to the ongoing hazardous wet conditions. The text \"KBS\" in the top right corner and the additional text in the bottom left corner suggest that the scene is from a KBS broadcast, possibly providing context or commentary on the situation.",
"The current frame shows a static image with a blue background and the KBS News logo prominently displayed, indicating a transition to a news broadcast segment. The text \"구독하기\" (Subscribe) is present, suggesting a call to action for viewers to subscribe to the channel or news service. This frame serves as an interlude, likely separating different segments of the video, such as transitioning from the previous scene of someone sitting on a bench to the next part of the broadcast.",
"The current frame continues with the static image featuring a blue background and the KBS News logo, reinforcing the transition to a news broadcast segment. The text \"구독하기\" (Subscribe) remains present, maintaining the call to action for viewers to subscribe to the channel. This frame appears to be part of the interlude, bridging the different segments of the video, possibly leading into the next part of the broadcast."
] |
rzyM4QtZNNU
|
A person enters a dimly lit indoor area with a wet floor, possibly due to an emergency or hazardous condition, carrying a large white item. They then sit on a bench, taking a break or waiting, as the wet conditions persist. The scene continues with the person sitting on the bench, with minimal changes, before transitioning to a KBS news broadcast segment with a static image featuring the KBS News logo and a call to action to subscribe. The video appears to capture a moment of someone seeking refuge or waiting for assistance in a building with a water-filled entrance, followed by a transition to a news segment, possibly providing context or commentary on the situation.
|
On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.
|
[
"A person setting fire to the office building in Daegu, South Korea on 9 June 2022",
"A person setting fire to the office building during the arson attack in Daegu, South Korea on 9 June 2022",
"Flames engulfing a building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing the building during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating the office building in a state of panic due to a fire in Daegu, South Korea on 9 June 2022",
"People evacuating the office building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Firefighters arriving at the scene of a fire in Daegu, South Korea on 9 June 2022 to extinguish the blaze",
"Firefighters arriving at the scene to extinguish the fire during the arson attack in Daegu, South Korea on June 9, 2022",
"Paramedics treating injured people outside the building after fire in Daegu, South Korea on 9 June 2022",
"Paramedics treating injured people outside the building after arson attack in Daegu, South Korea on June 9, 2022"
] |
[
"Firefighters battling the blaze at the office building in Daegu, South Korea on June 9, 2022",
"Firefighters battling the blaze at the office building in Daegu, South Korea after alleged arson attack on 9 June 2022",
"People evacuating a building in a state of panic due to a fire in Daegu, South Korea on June 9, 2022",
"People evacuating the building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Emergency responders providing medical aid to injured victims of the June 9, 2022 fire in Daegu, South Korea",
"Emergency responders providing medical aid to injured victims of the June 9 2022 arson attack in Daegu, South Korea",
"Flames engulfing parts of the office building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing parts of the office building in Daegu, South Korea during the arson attack on 9 June 2022",
"Rescue teams searching for survivors in the building damaged by the fire in Daegu, South Korea on 9 June 2022",
"Rescue teams searching for survivors in the damaged building after the arson attack in Daegu, South Korea on 9 June 2022"
] |
[
"Flames engulfing the office building in Daegu, South Korea on 9 June 2022 fire incident",
"Flames engulfing the office building in Daegu, South Korea due to arson attack on 9 June 2022",
"Firefighters arriving at the scene and battling the blaze in Daegu, South Korea on 9 June 2022 during a large fire incident",
"Firefighters arriving at the scene and battling the blaze during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating building after fire in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"People evacuating building after arson attack in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"Emergency medical personnel treating injured individuals outside the building after fire in Daegu, South Korea on 9 June 2022",
"Emergency medical personnel treating injured individuals outside the building after the arson attack in Daegu, South Korea on June 9, 2022",
"Damage to the office building in Daegu, South Korea after the fire on 9 June 2022 has been extinguished",
"Damage to the office building in Daegu, South Korea after the arson attack fire was extinguished on 9 June 2022"
] |
{
"article_url": "https://namu.wiki/w/%EB%8C%80%EA%B5%AC%20%EB%B3%80%ED%98%B8%EC%82%AC%20%EC%82%AC%EB%AC%B4%EC%8B%A4%20%EB%B0%A9%ED%99%94%20%EC%82%AC%EA%B1%B4",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: To extract events from the given query, it makes sense to focus on the concrete and visual aspects of the fire and its aftermath, considering what could be reasonably captured in a video. This includes the fire itself, the response of emergency services, and the impact on the building and its occupants.\n\nEVENTS:\n1. Flames engulfing the office building in Daegu\n2. Firefighters arriving at the scene and battling the blaze\n3. People evacuating the building, some injured and covered in soot\n4. Emergency medical personnel treating injured individuals outside the building\n5. Damage to the office building after the fire has been extinguished",
"en_article_excerpt": "On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.",
"en_article_url": "https://en.wikipedia.org/wiki/Daegu_office_fire",
"event_category": "disasters",
"event_name": "daegu_office_fire",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the actions and consequences leading up to and resulting from the arson attack, such as the fire breaking out, people evacuating, and emergency responders arriving. These events are concrete, visual, and likely to be captured in a video related to the incident.\n\nEVENTS:\n1. A person setting fire to the office building\n2. Flames engulfing the building\n3. People evacuating the office building in a state of panic\n4. Firefighters arriving at the scene to extinguish the fire\n5. Paramedics treating injured people outside the building",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a fire at an office building in Daegu, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage to the building, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the office building\n2. People evacuating the building in a state of panic\n3. Emergency responders providing medical aid to injured victims\n4. Flames engulfing parts of the office building\n5. Rescue teams searching for survivors in the damaged building",
"video_URL": "http://youtube.com/watch?v=5xiV1Z2MDX4",
"video_description": "대구 변호사 사무실 빌딩 화재…7명 사망·46명 부상 오늘(9일) 오전 11시쯤 대구시 수성구 범어동 대구지방법원 인근 7층짜리 변호사 사무실 빌딩 2층에서 불이 나 7명이 숨지고 46명이 연기를 마시는 등 부상을 입었습니다. 또 안에 있던 수십 명이 긴급 대피했습니다. 사망자는 남성 5명, 여성 2명인 것으로 알려졌습니다. 당시 119에는 \"2층에서 검은 연기가 보이고 폭발음이 들렸다\"는 신고가 접수됐습니다. 불이 나자 소방차 50대와 소방인력 160명이 동원돼 불을 끄고 입주자들을 구조했습니다. 불은 20여 분만에 진화됐습니다. 경찰은 화재 발생 당시 의뢰인이 불만을 제기한 정황이 있었다는 점 등으로 미뤄 방화 여부를 조사하고 있습니다. #사무실_빌딩_화재 #사망 #연기 #대구_범어동 연합뉴스TV 기사문의 및 제보 : 카톡/라인 jebo23 ▣ 연합뉴스TV 유튜브 채널 구독 https://goo.gl/VuCJMi ▣ 대한민국 뉴스의 시작 연합뉴스TV / Yonhap News TV http://www.yonhapnewstv.co.kr/",
"video_id": "5xiV1Z2MDX4"
}
| 8
|
[
"The video shows a high-rise building with a ladder leading up to a broken window. Text in Korean indicates a building accident with 7 deaths and 46 injuries. The time displayed is 13:06, and the context suggests a news broadcast.",
"The video continues to show the high-rise building, with the ladder still present and pointing to the broken window. The Korean text remains, reaffirming the building accident with 7 deaths and 46 injuries. The time still reads 13:06, maintaining the news broadcast context.",
"The current frame shows a large white and blue banner with Korean text being held by several individuals, likely indicating a public demonstration or protest related to the high-rise building accident. The focus is on the banner, which emphasizes the ongoing response to the incident. Emergency personnel in reflective vests are present, suggesting an organized effort to address the situation. The text on the banner, combined with the ongoing news broadcast, underscores the gravity of the event and the public's engagement in the aftermath.",
"The current frame shows a damaged building with a large section of its glass facade missing, exposing the interior. A ladder is propped against the exterior wall, suggesting repair or investigation efforts. The reflection of the surrounding area can be seen in the intact glass panes, indicating the building's urban setting. The ongoing news broadcast at the bottom of the screen continues to provide updates, with the text highlighting the scale of the incident, mentioning seven fatalities and 46 injured. The presence of the ladder and the focus on the damaged structure emphasize the ongoing efforts to understand and address the aftermath of the building accident.",
"The video depicts an ongoing emergency situation outside a multi-story building. Numerous firefighters and police officers are gathered around a white ambulance, suggesting active rescue operations. The presence of emergency personnel in full gear, including helmets and reflective jackets, indicates a coordinated response to an incident. The reflective text at the bottom of the image provides details on the incident, mentioning seven fatalities and 46 injured, underscoring the severity of the situation. The surrounding environment includes the facade of the building and various vehicles, highlighting the urban setting of the emergency.",
"The current frame shows a wide shot of a modern multi-story building with large glass windows, reflecting surrounding structures. A ladder is positioned against the building, reaching up to the third floor, indicating ongoing rescue or inspection efforts. The reflective text at the bottom of the image continues to detail the incident, reiterating seven fatalities and 46 injured. The timestamp in the image indicates the time as 13:06. The presence of the ladder suggests that rescue operations are still in progress, focusing on accessing higher floors of the building.",
"The current frame depicts a scene of emergency response outside a building with multiple firefighters and rescue workers in uniforms gathered around. An ambulance is visible with its doors open, indicating active medical attention. The reflective text continues to state that the incident resulted in seven fatalities and 46 injured. The timestamp in the image indicates it is 13:06. The presence of emergency personnel and an open ambulance suggests ongoing efforts to manage and treat casualties.",
"The scene continues outside the building where emergency responders are present, with firefighters and rescue workers gathered, maintaining the emergency response. The ambulance remains visible with its doors open, indicating continuous medical care. The text reiterates the incident's impact with seven fatalities and 46 injured. The timestamp is 13:06, and the scene suggests ongoing efforts to manage and treat casualties."
] |
5xiV1Z2MDX4
|
A high-rise building accident occurred, resulting in 7 deaths and 46 injuries. The incident prompted a significant emergency response, with firefighters, police officers, and rescue workers gathered at the scene. A ladder was positioned against the building to access upper floors, and an ambulance was present to provide medical attention to the injured. The accident was severe enough to prompt a public demonstration or protest, with individuals holding a banner to express their response to the incident. The video, set against the backdrop of an urban environment, captures the immediate aftermath and response to the building accident, with emergency services working to rescue and treat those affected. The ongoing news broadcast provides updates on the situation, underscoring the gravity and public impact of the event.
|
Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.
|
[
"Strong winds from typhoon knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Heavy rainfall from typhoons causing flooding in Taiwan, the Philippines, and other affected East Asian countries such as Japan, South Korea, and possibly Russia",
"Typhoon storm surges hitting coastal communities in Russia's eastern regions and other affected areas such as Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to shelters and safe zones in Japan, South Korea, Taiwan, Philippines, and Russia during typhoon events",
"Debris and damage to buildings and infrastructure in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
[
"Strong winds from typhoons knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Flooding in coastal cities and low-lying areas due to typhoons in Japan, South Korea, Taiwan, Philippines, and Russia",
"People evacuating to emergency shelters during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Debris-filled streets and damaged buildings after typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Emergency responders rescuing people from flooded areas during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia"
] |
[
"Typhoon causing strong winds and knocking down trees and power lines in Japan and South Korea",
"Typhoon causing heavy rainfall and flooding in the Philippines and Taiwan",
"Typhoon storm surges hitting coastal communities in Russia and other affected areas like Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to emergency shelters in Japan, South Korea, Taiwan, Philippines, and Russia due to typhoon",
"Debris and damaged buildings in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%ED%9E%8C%EB%82%A8%EB%85%B8",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Hinnamnor, it makes sense to extract events that are commonly associated with a powerful tropical cyclone, such as strong winds, heavy rainfall, and storm surges, as these events are likely to be visualized in a video. The events extracted should be specific to the regions affected, including Japan, South Korea, Taiwan, the Philippines, and Russia, taking into account the typical consequences of a typhoon in these areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in the Philippines and Taiwan\n3. Storm surges hitting coastal communities in Russia\n4. Residents evacuating to emergency shelters in affected areas\n5. Debris and damaged buildings in the aftermath of the typhoon",
"en_article_excerpt": "Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Hinnamnor",
"event_category": "disasters",
"event_name": "typhoon_hinnamno",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, as these are likely to be visualized in a video associated with the query. The events should be specific to the affected regions, considering the geographical characteristics and common typhoon impacts in those areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in Taiwan and the Philippines\n3. Storm surges hitting coastal communities in Russia's eastern regions\n4. Residents evacuating to shelters and safe zones in affected areas\n5. Debris and damage to buildings and infrastructure in the aftermath of the typhoon",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the impact of a powerful typhoon, such as damage to infrastructure, evacuations, and extreme weather conditions, as these are likely to be visualized in a video associated with the query. The events should be specific to the regions affected by the typhoon, including Japan, South Korea, Taiwan, the Philippines, and Russia.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. People evacuating to emergency shelters\n4. Debris-filled streets and damaged buildings\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1566887846916792320",
"video_description": "이게맞나.. #태풍 #힌남노 #포항 #역대급태풍",
"video_id": "1566887846916792320"
}
| 8
|
[
"The image depicts a nighttime scene of a street with a heavy rainstorm. The road is wet, and visibility is low due to the rain. There are trees and a fence visible on the side of the road, along with some buildings in the background. The scene appears to be quiet, with no visible vehicles or people.",
"The current frame continues to depict a nighttime street scene under a heavy rainstorm. The road remains wet, and visibility is still low due to the rain. Trees and a fence are visible on the side of the road, with buildings in the background. The scene remains quiet, with no visible vehicles or people, maintaining the atmosphere of the previous frame.",
"The current frame continues to depict a nighttime street scene under a heavy rainstorm. The road remains wet, and visibility is still low due to the rain. Trees and a fence are visible on the side of the road, with buildings in the background. The scene remains quiet, with no visible vehicles or people, maintaining the atmosphere of the previous frame.",
"The current frame continues to show the nighttime street scene under the heavy rainstorm. The road is wet, and visibility remains low due to the rain. Trees and a fence are still visible on the side of the road, with buildings in the background. The scene remains quiet with no visible vehicles or people, maintaining the atmosphere of the previous frame.",
"The current frame continues to depict the nighttime street scene under the heavy rainstorm. The road remains wet, and visibility is still low due to the rain. Trees and a fence are still visible on the side of the road, with buildings in the background. The scene remains quiet with no visible vehicles or people, maintaining the atmosphere of the previous frame. A vehicle with its headlights on is visible on the road, moving slowly through the rain.",
"The current frame continues to depict the nighttime street scene under the heavy rainstorm. The road remains wet, and visibility is still low due to the rain. Trees and a fence are still visible on the side of the road, with buildings in the background. The scene remains quiet with no visible vehicles or people, maintaining the atmosphere of the previous frame. The vehicle with its headlights on is no longer visible on the road, suggesting it has either moved out of the frame or stopped.",
"The current frame depicts the nighttime street scene under the ongoing heavy rainstorm. The road remains wet, and visibility is still low due to the rain. Trees and a fence are still visible on the side of the road, with buildings in the background. The scene remains quiet with no visible vehicles or people, maintaining the atmosphere from the previous frame. A vehicle with its headlights on is no longer visible on the road, suggesting it has either moved out of the frame or stopped.",
"The current frame continues to show the nighttime street scene under the heavy rainstorm. The road remains wet, and visibility is still low. The trees and fence are still visible on the side of the road, with buildings in the background. The scene remains quiet with no visible vehicles or people, consistent with the previous frame. The vehicle with its headlights on is still not visible, suggesting it has remained out of the frame or stationary."
] |
1566887846916792320
|
A nighttime street scene is depicted under a heavy rainstorm, with a wet road and low visibility. The scene remains quiet throughout, with trees and a fence visible on the side of the road and buildings in the background. For most of the video, there are no visible vehicles or people. However, in one instance, a vehicle with its headlights on appears on the road, moving slowly through the rain, before disappearing from view, either by moving out of the frame or stopping, and not reappearing. The overall atmosphere of the video is one of stillness and solitude, punctuated briefly by the appearance of the vehicle.
|
Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.
|
[
"Strong winds from typhoon knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Heavy rainfall from typhoons causing flooding in Taiwan, the Philippines, and other affected East Asian countries such as Japan, South Korea, and possibly Russia",
"Typhoon storm surges hitting coastal communities in Russia's eastern regions and other affected areas such as Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to shelters and safe zones in Japan, South Korea, Taiwan, Philippines, and Russia during typhoon events",
"Debris and damage to buildings and infrastructure in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
[
"Strong winds from typhoons knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Flooding in coastal cities and low-lying areas due to typhoons in Japan, South Korea, Taiwan, Philippines, and Russia",
"People evacuating to emergency shelters during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Debris-filled streets and damaged buildings after typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Emergency responders rescuing people from flooded areas during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia"
] |
[
"Typhoon causing strong winds and knocking down trees and power lines in Japan and South Korea",
"Typhoon causing heavy rainfall and flooding in the Philippines and Taiwan",
"Typhoon storm surges hitting coastal communities in Russia and other affected areas like Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to emergency shelters in Japan, South Korea, Taiwan, Philippines, and Russia due to typhoon",
"Debris and damaged buildings in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%ED%9E%8C%EB%82%A8%EB%85%B8",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Hinnamnor, it makes sense to extract events that are commonly associated with a powerful tropical cyclone, such as strong winds, heavy rainfall, and storm surges, as these events are likely to be visualized in a video. The events extracted should be specific to the regions affected, including Japan, South Korea, Taiwan, the Philippines, and Russia, taking into account the typical consequences of a typhoon in these areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in the Philippines and Taiwan\n3. Storm surges hitting coastal communities in Russia\n4. Residents evacuating to emergency shelters in affected areas\n5. Debris and damaged buildings in the aftermath of the typhoon",
"en_article_excerpt": "Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Hinnamnor",
"event_category": "disasters",
"event_name": "typhoon_hinnamno",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, as these are likely to be visualized in a video associated with the query. The events should be specific to the affected regions, considering the geographical characteristics and common typhoon impacts in those areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in Taiwan and the Philippines\n3. Storm surges hitting coastal communities in Russia's eastern regions\n4. Residents evacuating to shelters and safe zones in affected areas\n5. Debris and damage to buildings and infrastructure in the aftermath of the typhoon",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the impact of a powerful typhoon, such as damage to infrastructure, evacuations, and extreme weather conditions, as these are likely to be visualized in a video associated with the query. The events should be specific to the regions affected by the typhoon, including Japan, South Korea, Taiwan, the Philippines, and Russia.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. People evacuating to emergency shelters\n4. Debris-filled streets and damaged buildings\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1566774984525025281",
"video_description": "다들... 이번 태풍 힌남노 조심하세요... 현재 제주... 저희 집 나무가 90도로 순간적으로 휘어진 거 처음 봐요 바람 장난아니고 비도 장난아니니까 집에... 콕... 박혀있기",
"video_id": "1566774984525025281"
}
| 8
|
[
"The image is dark and lacks discernible details, making it difficult to identify any specific actions, participants, or context of an event.",
"The image is dark and lacks discernible details, making it difficult to identify any specific actions, participants, or context of an event.",
"The scene remains dark with no discernible actions, participants, or context of an event visible.",
"The scene continues to be dark with no discernible actions, participants, or context of an event visible. The darkness persists without any significant change.",
"The scene remains dark with no discernible actions, participants, or context of an event visible. The darkness persists without any significant change.",
"The scene continues to be enveloped in darkness, with no discernible actions, participants, or context of an event visible. The persistent darkness suggests the continuation of a night setting, maintaining the overall atmosphere established in previous frames.",
"The scene remains dark, and no new actions, participants, or events are visible. The darkness persists, reinforcing the night setting from the previous frames.",
"The scene continues to be dark, with no discernible changes or new actions. The darkness suggests a consistent night setting, and there are still no visible participants or events occurring in this frame."
] |
1566774984525025281
|
The video appears to depict a continuous night setting, with all frames showing a dark scene lacking discernible details, actions, participants, or context of any event, suggesting a static and unchanging atmosphere throughout.
|
Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.
|
[
"Strong winds from typhoon knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Heavy rainfall from typhoons causing flooding in Taiwan, the Philippines, and other affected East Asian countries such as Japan, South Korea, and possibly Russia",
"Typhoon storm surges hitting coastal communities in Russia's eastern regions and other affected areas such as Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to shelters and safe zones in Japan, South Korea, Taiwan, Philippines, and Russia during typhoon events",
"Debris and damage to buildings and infrastructure in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
[
"Strong winds from typhoons knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Flooding in coastal cities and low-lying areas due to typhoons in Japan, South Korea, Taiwan, Philippines, and Russia",
"People evacuating to emergency shelters during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Debris-filled streets and damaged buildings after typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Emergency responders rescuing people from flooded areas during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia"
] |
[
"Typhoon causing strong winds and knocking down trees and power lines in Japan and South Korea",
"Typhoon causing heavy rainfall and flooding in the Philippines and Taiwan",
"Typhoon storm surges hitting coastal communities in Russia and other affected areas like Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to emergency shelters in Japan, South Korea, Taiwan, Philippines, and Russia due to typhoon",
"Debris and damaged buildings in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%ED%9E%8C%EB%82%A8%EB%85%B8",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Hinnamnor, it makes sense to extract events that are commonly associated with a powerful tropical cyclone, such as strong winds, heavy rainfall, and storm surges, as these events are likely to be visualized in a video. The events extracted should be specific to the regions affected, including Japan, South Korea, Taiwan, the Philippines, and Russia, taking into account the typical consequences of a typhoon in these areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in the Philippines and Taiwan\n3. Storm surges hitting coastal communities in Russia\n4. Residents evacuating to emergency shelters in affected areas\n5. Debris and damaged buildings in the aftermath of the typhoon",
"en_article_excerpt": "Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Hinnamnor",
"event_category": "disasters",
"event_name": "typhoon_hinnamno",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, as these are likely to be visualized in a video associated with the query. The events should be specific to the affected regions, considering the geographical characteristics and common typhoon impacts in those areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in Taiwan and the Philippines\n3. Storm surges hitting coastal communities in Russia's eastern regions\n4. Residents evacuating to shelters and safe zones in affected areas\n5. Debris and damage to buildings and infrastructure in the aftermath of the typhoon",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the impact of a powerful typhoon, such as damage to infrastructure, evacuations, and extreme weather conditions, as these are likely to be visualized in a video associated with the query. The events should be specific to the regions affected by the typhoon, including Japan, South Korea, Taiwan, the Philippines, and Russia.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. People evacuating to emergency shelters\n4. Debris-filled streets and damaged buildings\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1567139282846089217",
"video_description": "제11호 태풍 힌남노로 인한 자연재해 피해가 속출했는데요. 포항 아파트 지하주차장 침수로 인한 대규모 실종자가 발생을 했습니다. 포항 우방신세계아파트라는 곳에서 침수로 인해 실종자가 발생했고 9월 6일 20시 40분경 실종자1명(39세 남성)을 구조했고, 21시 50분 실종자1명(여성) 구조.",
"video_id": "1567139282846089217"
}
| 8
|
[
"The current frame shows several individuals in water, likely rescuers or divers, as they work in what appears to be a flooded parking area. There is a prominent sign above indicating \"OUT PARKING\" with an arrow pointing right. The scene takes place at night, and the water is illuminated by artificial lighting. The focus seems to be on the group of people in the water, suggesting an emergency or rescue operation.",
"The current frame continues to show several individuals in water, likely rescuers or divers, working in what appears to be a flooded parking area. The sign above still reads \"OUT PARKING\" with an arrow pointing right. The scene remains at night, with artificial lighting illuminating the water. A person on the right side of the frame is holding a smartphone, possibly recording or taking pictures of the event. The focus remains on the group of people in the water, suggesting the ongoing nature of the emergency or rescue operation.",
"The video continues to depict several individuals in water, likely rescuers or divers, engaged in an ongoing rescue operation in a flooded parking area. The sign above, reading \"OUT PARKING\" with an arrow pointing right, remains visible. The scene is still set at night, with artificial lighting highlighting the water. On the right side of the frame, a person continues to hold a smartphone, capturing the event by recording or taking pictures. The focus on the group of people in the water persists, emphasizing the continuous nature of the emergency or rescue operation.",
"The video continues to depict the ongoing rescue operation in a flooded area. A person is seen kneeling in the water, possibly attending to a submerged individual. The surrounding environment remains dark, with artificial lighting highlighting the water. The focus remains on the group of people in the water, emphasizing the continuous nature of the emergency or rescue operation.",
"In the current frame, the rescue operation is ongoing in the same flooded area. Several individuals, likely rescue workers, are gathered in the water, with some kneeling and others standing. They appear to be coordinating their efforts, possibly discussing the next steps in the rescue. The environment remains dimly lit with artificial lighting, which continues to highlight the water and the actions of the rescuers. The focus remains on the group, emphasizing the collaborative and coordinated nature of the emergency response.",
"In the current frame, the rescue operation continues in the flooded area. Several individuals, likely rescue workers, are present. Some are kneeling or crouching, while others stand, actively engaged in the rescue effort. They seem to be either assessing the situation or preparing to assist those in need. The environment remains dimly lit with artificial lighting, which continues to illuminate the water and the actions of the rescuers. The focus remains on the group, emphasizing the ongoing coordinated efforts of the emergency response team.",
"The rescue operation persists in the flood-affected zone. Rescue workers are actively involved, with some standing and others kneeling or crouching. They are engaged in assessing the situation and preparing to assist those in need. The area remains dimly lit by artificial lighting, highlighting the water and the rescuers' actions. The scene continues to emphasize the coordinated efforts of the emergency response team.",
"The rescue operation continues in the flood-affected zone. Rescue workers are actively involved, with some standing and others kneeling or crouching. They are engaged in assessing the situation and preparing to assist those in need. The area remains dimly lit by artificial lighting, highlighting the water and the rescuers' actions. The scene continues to emphasize the coordinated efforts of the emergency response team."
] |
1567139282846089217
|
A group of rescuers or divers are conducting an emergency rescue operation in a flooded parking area at night. The scene is illuminated by artificial lighting, and the rescuers are working together to assist those in need. Throughout the operation, the rescuers are seen coordinating their efforts, assessing the situation, and preparing to assist those affected by the flood. The rescue operation is ongoing, with the rescuers actively engaged in the water, kneeling, crouching, or standing, as they work to respond to the emergency. The environment remains dimly lit, with the artificial lighting highlighting the water and the actions of the rescuers, emphasizing the coordinated and collaborative nature of the emergency response.
|
Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.
|
[
"Strong winds from typhoon knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Heavy rainfall from typhoons causing flooding in Taiwan, the Philippines, and other affected East Asian countries such as Japan, South Korea, and possibly Russia",
"Typhoon storm surges hitting coastal communities in Russia's eastern regions and other affected areas such as Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to shelters and safe zones in Japan, South Korea, Taiwan, Philippines, and Russia during typhoon events",
"Debris and damage to buildings and infrastructure in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
[
"Strong winds from typhoons knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Flooding in coastal cities and low-lying areas due to typhoons in Japan, South Korea, Taiwan, Philippines, and Russia",
"People evacuating to emergency shelters during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Debris-filled streets and damaged buildings after typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Emergency responders rescuing people from flooded areas during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia"
] |
[
"Typhoon causing strong winds and knocking down trees and power lines in Japan and South Korea",
"Typhoon causing heavy rainfall and flooding in the Philippines and Taiwan",
"Typhoon storm surges hitting coastal communities in Russia and other affected areas like Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to emergency shelters in Japan, South Korea, Taiwan, Philippines, and Russia due to typhoon",
"Debris and damaged buildings in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%ED%9E%8C%EB%82%A8%EB%85%B8",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Hinnamnor, it makes sense to extract events that are commonly associated with a powerful tropical cyclone, such as strong winds, heavy rainfall, and storm surges, as these events are likely to be visualized in a video. The events extracted should be specific to the regions affected, including Japan, South Korea, Taiwan, the Philippines, and Russia, taking into account the typical consequences of a typhoon in these areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in the Philippines and Taiwan\n3. Storm surges hitting coastal communities in Russia\n4. Residents evacuating to emergency shelters in affected areas\n5. Debris and damaged buildings in the aftermath of the typhoon",
"en_article_excerpt": "Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Hinnamnor",
"event_category": "disasters",
"event_name": "typhoon_hinnamno",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, as these are likely to be visualized in a video associated with the query. The events should be specific to the affected regions, considering the geographical characteristics and common typhoon impacts in those areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in Taiwan and the Philippines\n3. Storm surges hitting coastal communities in Russia's eastern regions\n4. Residents evacuating to shelters and safe zones in affected areas\n5. Debris and damage to buildings and infrastructure in the aftermath of the typhoon",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the impact of a powerful typhoon, such as damage to infrastructure, evacuations, and extreme weather conditions, as these are likely to be visualized in a video associated with the query. The events should be specific to the regions affected by the typhoon, including Japan, South Korea, Taiwan, the Philippines, and Russia.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. People evacuating to emergency shelters\n4. Debris-filled streets and damaged buildings\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1566015450982494209",
"video_description": "얘들아… 초속 54미터 이상이면 건물도 붕괴될 정도의 바람이라는데 이번 힌남노는 매미보다 중심 기압이 낮은 더 강력한 태풍이라 제주/남부해안지역엔 초속 60미터까지도 예상된대.. 영동 쪽은 초속 3~40미터 수도권은 초속 15미터 예상… 다들 진짜 조심하자 대비할 수 있는 부분은 꼭 하고ㅜ",
"video_id": "1566015450982494209"
}
| 8
|
[
"In the current frame, a news broadcast is taking place in a studio. Two men are seated at a desk, one on the left and the other on the right, both dressed in suits. The man on the left is holding a pen and appears to be listening or preparing to speak, while the man on the right is gesturing with his hands, seemingly explaining or discussing a topic. Behind them, large screens display images of waves crashing against a rocky shoreline, suggesting that the topic may be related to weather conditions or a natural event. A third person, a woman in a black outfit, is seated to the right, possibly a producer or a part of the studio crew. Text at the bottom of the screen provides context, mentioning \"기존 역대 1위 바람 태풍 '매미'...제주도에서 초속 60m 기록,\" indicating that the discussion is about a record-breaking typhoon named \"Maemi\" that occurred in Jeju Island, with wind speeds reaching 60 meters per second.",
"The news broadcast continues with the same two men seated at the desk, both still dressed in suits. The man on the left remains holding a pen, looking attentive, while the man on the right continues to gesture with his hands, engaging in the discussion. The large screens behind them still show waves crashing against a rocky shoreline, reinforcing the weather-related theme. The woman in the black outfit remains seated to the right, likely still part of the studio crew. The text at the bottom of the screen has changed to \"서울 등 수도권에도 초속 15m 돌풍 불듯...시설물 피해 우려,\" indicating a shift in the discussion to potential wind speeds of 15 meters per second and concerns about damage to facilities in the Seoul metropolitan area.",
"The scene remains within the news broadcast studio, with the two men in suits still seated at the desk. The man on the left appears to be speaking, gesturing with his right hand, while the man on the right listens attentively. The large screens behind them continue to display the crashing waves against the rocky shoreline, maintaining the visual theme of the weather segment. The woman in the black outfit is still present, likely part of the studio crew. The text at the bottom of the screen reads \"기상청 '태풍 접근과 만조가 겹치면 '폭풍 해일' 가능성,\" suggesting that the discussion has now shifted to the potential for a storm surge if the typhoon approaches during high tide.",
"The focus remains on the news broadcast studio with the two men in suits seated at the desk. The man on the left is still speaking, and the man on the right is attentive. The screen behind them has now changed to display a map with regions marked in different colors, indicating varying wind speeds. The text on the screen reads \"지역별 예상 바람,\" suggesting the discussion has moved to wind speed expectations by region. The woman in the black outfit is still present. The text at the bottom of the screen reads \"2003년 태풍 '매미'로 폭풍해일 발상...인명 피해 발생,\" indicating a historical reference to the impact of Typhoon Maemi in 2003, which caused storm surges and resulted in human casualties.",
"The current frame shows a split-screen with a nighttime outdoor scene on the left and a news anchor on the right. The outdoor scene depicts a wet, illuminated road with barriers and yellow tape, suggesting an area that has been cordoned off due to flooding or some other incident. The news anchor, dressed in a suit and tie, is seated in a studio, with a backdrop that includes an image of ocean waves and a coastal area, indicating a focus on weather or natural disaster reporting. The text at the bottom of the screen reads \"기상청 '태풍 접근과 만조가 겹치면 폭풍 해일' 가능성,\" which translates to \"KMA 'If a typhoon approaches and high tide coincides, there is a possibility of a storm surge.'\" This suggests that the broadcast is discussing the potential for storm surges due to the combination of a typhoon and high tide.",
"The current frame continues the split-screen format with the nighttime outdoor scene on the left showing a close-up of a speed limit sign and a light fixture, likely part of the cordoned-off area from the previous scene, indicating the aftermath or preparation for a storm surge. The news anchor on the right remains in the studio with the same backdrop, and the text at the bottom has changed to \"2003년 태풍 '매미'로 폭풍해일 발생...인명 피해 발생,\" which translates to \"In 2003, due to Typhoon Maemi, a storm surge occurred...causing loss of life.\" This update informs viewers about a past incident involving a storm surge caused by Typhoon Maemi, emphasizing the potential dangers and historical context of the current weather situation being reported.",
"The video maintains the split-screen format, with the nighttime outdoor scene on the left showing a broader view of a wet road illuminated by streetlights, likely part of the coastal area from the previous frames, reinforcing the ongoing coverage of the storm surge situation. The news anchor on the right continues in the studio with the same backdrop, and the text at the bottom reads \"기상청 '제주도와 남해안·경상 동해안 폭풍해일 주의해야',\" which translates to \"The Korea Meteorological Administration warns of storm surges on Jeju Island, the southern coast, and the eastern coast of Gyeongsang.\" This update provides viewers with specific regions that are at risk of storm surges, stressing the importance of caution and preparedness.",
"The video continues with the split-screen format, showing a nighttime outdoor scene on the left with a broader view of a wet road illuminated by streetlights, likely part of the coastal area from previous frames, maintaining the ongoing coverage of the storm surge situation. The news anchor on the right remains in the studio with the same backdrop, and the text at the bottom reads \"2003년 태풍 '매미'로 폭풍해일 발생...이명 피해 발생,\" which translates to \"In 2003, Typhoon Maemi caused storm surges...A sound-related disaster occurred.\" This update provides a historical context, referring to a past storm surge event caused by Typhoon Maemi, emphasizing the potential for similar disasters and the need for preparedness."
] |
1566015450982494209
|
A news broadcast discusses Typhoon Maemi, a record-breaking storm that affected Jeju Island with wind speeds of 60 meters per second. The anchors, two men in suits, analyze the storm's potential impact, including wind speeds of 15 meters per second in the Seoul metropolitan area and the risk of a storm surge if the typhoon coincides with high tide. Historical context is provided, referencing the 2003 Typhoon Maemi, which caused a storm surge and resulted in human casualties. The broadcast shifts to a split-screen format, showing a news anchor in the studio and nighttime outdoor scenes of a cordoned-off, flooded area, likely in preparation for or aftermath of a storm surge. The Korea Meteorological Administration's warnings are highlighted, specifically for Jeju Island, the southern coast, and the eastern coast of Gyeongsang, emphasizing the need for caution and preparedness against potential storm surges.
|
Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.
|
[
"Strong winds from typhoon knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Heavy rainfall from typhoons causing flooding in Taiwan, the Philippines, and other affected East Asian countries such as Japan, South Korea, and possibly Russia",
"Typhoon storm surges hitting coastal communities in Russia's eastern regions and other affected areas such as Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to shelters and safe zones in Japan, South Korea, Taiwan, Philippines, and Russia during typhoon events",
"Debris and damage to buildings and infrastructure in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
[
"Strong winds from typhoons knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Flooding in coastal cities and low-lying areas due to typhoons in Japan, South Korea, Taiwan, Philippines, and Russia",
"People evacuating to emergency shelters during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Debris-filled streets and damaged buildings after typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Emergency responders rescuing people from flooded areas during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia"
] |
[
"Typhoon causing strong winds and knocking down trees and power lines in Japan and South Korea",
"Typhoon causing heavy rainfall and flooding in the Philippines and Taiwan",
"Typhoon storm surges hitting coastal communities in Russia and other affected areas like Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to emergency shelters in Japan, South Korea, Taiwan, Philippines, and Russia due to typhoon",
"Debris and damaged buildings in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%ED%9E%8C%EB%82%A8%EB%85%B8",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Hinnamnor, it makes sense to extract events that are commonly associated with a powerful tropical cyclone, such as strong winds, heavy rainfall, and storm surges, as these events are likely to be visualized in a video. The events extracted should be specific to the regions affected, including Japan, South Korea, Taiwan, the Philippines, and Russia, taking into account the typical consequences of a typhoon in these areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in the Philippines and Taiwan\n3. Storm surges hitting coastal communities in Russia\n4. Residents evacuating to emergency shelters in affected areas\n5. Debris and damaged buildings in the aftermath of the typhoon",
"en_article_excerpt": "Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Hinnamnor",
"event_category": "disasters",
"event_name": "typhoon_hinnamno",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, as these are likely to be visualized in a video associated with the query. The events should be specific to the affected regions, considering the geographical characteristics and common typhoon impacts in those areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in Taiwan and the Philippines\n3. Storm surges hitting coastal communities in Russia's eastern regions\n4. Residents evacuating to shelters and safe zones in affected areas\n5. Debris and damage to buildings and infrastructure in the aftermath of the typhoon",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the impact of a powerful typhoon, such as damage to infrastructure, evacuations, and extreme weather conditions, as these are likely to be visualized in a video associated with the query. The events should be specific to the regions affected by the typhoon, including Japan, South Korea, Taiwan, the Philippines, and Russia.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. People evacuating to emergency shelters\n4. Debris-filled streets and damaged buildings\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1566948535899041792",
"video_description": "칭구가 보내준 집앞 영상 괜찮아??? 응 근데 나도 안괜찮아 다들 괜찮으시길 #태풍_힌남노_저리가",
"video_id": "1566948535899041792"
}
| 8
|
[
"The image shows a large landslide with soil and debris flowing down a hillside. Several high-rise buildings are visible in the background, and a modern building is situated at the bottom of the landslide. A car is parked near the building, and the surrounding area appears to be muddy and affected by the landslide.",
"The landslide continues to be prominent, with more soil and debris cascading down the hillside. The car near the modern building is still present, and the area around it remains muddy. The high-rise buildings in the background are still visible, indicating ongoing and possibly worsening conditions due to the landslide.",
"The landslide shows signs of slowing down as the flow of soil and debris has reduced, with less material cascading down the hillside compared to previous frames. The car near the modern building remains in its position, and the surrounding area is still muddy, suggesting that the impact of the landslide is stabilizing but the aftermath is still evident. The high-rise buildings in the background continue to stand, indicating that the immediate threat to structures has subsided, but the situation remains cautiously monitored.",
"The landslide appears to have further slowed down, with even less material moving down the hillside compared to the previous frames. The car near the modern building remains in the same position, and the muddy surrounding area suggests that the aftermath of the landslide is still present but the immediate impact has subsided. The high-rise buildings in the background are still standing, indicating that the threat to structures has likely passed, though the area may still be under observation for safety.",
"The landslide has continued to slow down, with minimal material moving down the hillside. The car near the modern building remains stationary, and the muddy surroundings persist, indicating the aftermath of the landslide. The high-rise buildings in the background remain intact, suggesting the threat to structures has passed, and the area may still be under observation for safety.",
"The landslide appears to have ceased, with no visible movement of debris down the hillside. The car near the modern building remains stationary, and the muddy surroundings persist, reinforcing the aftermath of the landslide. The high-rise buildings in the background are still intact, indicating that the threat to structures has passed and the area is likely still under observation for safety.",
"The landslide has stopped, as indicated by the lack of movement of debris down the hillside. The car next to the modern building remains unmoved, and the muddy area surrounding it continues to be a testament to the aftermath of the landslide. The tall buildings in the background are still undamaged, suggesting that the danger to structures has ended and the region is probably under continuous surveillance for safety.",
"The scene remains static with no movement of debris down the hillside, indicating that the landslide has completely ceased. The car beside the modern building is still stationary, and the muddy area around it persists, underscoring the aftermath of the landslide. The tall buildings in the background remain unscathed, reinforcing that the immediate danger to structures has passed and the area is likely under continuous surveillance for safety."
] |
1566948535899041792
|
A landslide occurred on a hillside near a modern building and several high-rise structures, causing soil and debris to flow down and creating a muddy area around a parked car. The landslide progressively slowed down over time, eventually coming to a complete stop, with the surrounding area remaining affected by the mud and debris. Throughout the event, the nearby high-rise buildings remained intact, indicating that the threat to structures had passed once the landslide ceased. The area is likely under observation for safety following the incident.
|
Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges causing coastal erosion and damage during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to safer areas or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Debris and destroyed buildings scattered in the aftermath of the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Buildings and houses destroyed by strong winds from Typhoon in Philippines, China, and Korea in 2019",
"Flooding in coastal areas and low-lying regions during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to higher ground or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Trees and power lines uprooted or knocked down during Typhoon in Philippines, China, and Korea in 2019",
"Rescue teams providing aid to affected communities during the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Strong winds from Typhoon knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges caused by typhoons in the Philippines, China, and Korea in 2019 resulting in coastal erosion and damage",
"People evacuating to safer areas during Typhoon in the Philippines, China, and Korea in 2019",
"Debris and wreckage scattered on roads and buildings after Typhoon in Philippines, China, and Korea in 2019"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%A7%81%EB%A7%81_(2019%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are commonly associated with a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to have occurred in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas\n5. Debris and wreckage scattered on roads and buildings",
"en_article_excerpt": "Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Lingling_(2019)",
"event_category": "disasters",
"event_name": "typhoon_lingling",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to occur in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas or shelters\n5. Debris and destroyed buildings scattered in the typhoon's aftermath",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typically associated with the aftermath or impact of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Lingling. The events extracted should be specific to the regions affected by the typhoon, including the Philippines, China, and Korea.\n\nEVENTS:\n1. Buildings and houses destroyed by strong winds\n2. Flooding in coastal areas and low-lying regions\n3. People evacuating to higher ground or shelters\n4. Trees and power lines uprooted or knocked down\n5. Rescue teams providing aid to affected communities",
"video_URL": "http://youtube.com/watch?v=QJY4XlSNVf8",
"video_description": "#태풍 #링링 #제13호 #13호 #중국 (서울=연합뉴스) 제13호 태풍 '링링'이 세력을 키우며 한반도를 향해 북상하고 있습니다. 5일 기상청에 따르면 '링링'은 이날 오전 9시 현재 일본 오키나와 남서쪽 약 370㎞ 해상에서 시속 19㎞로 북상 중입니다. 발생 초기 강도가 '약'이던 '링링'은 수온이 높은 해역을 지나며 이날 현재 '강'으로 세력이 강해진 상태입니다. 한국과 미국, 일본 기상청 모두 '링링'이 토요일인 7일 수도권을 강타할 것으로 예보해 철저한 대비가 필요합니다. 중국 저장성과 하이난성에서는 지난 2일 이후 '링링'과 제14호 태풍 '가지키'의 영향으로 폭우 피해가 잇따랐는데요. 영상으로 보시죠. ◆ 연합뉴스 홈페이지→ http://www.yna.co.kr/ ◆ 이 시각 많이 본 기사 → https://goo.gl/VQTsSZ ◆ 오늘의 핫뉴스 → https://goo.gl/WyGXpG ◆ 현장영상 → https://goo.gl/5aZcx8 ◆ 카드뉴스 →https://goo.gl/QKfDTH ◆연합뉴스 공식 SNS◆ ◇페이스북→ https://www.facebook.com/yonhap/ ▣ 연합뉴스 유튜브 채널 구독 : https://goo.gl/pL7TmT ▣ 연합뉴스 인스타 : https://goo.gl/UbqiQb",
"video_id": "QJY4XlSNVf8"
}
| 8
|
[
"The frame shows a rainy urban street scene with heavy rain pouring down. Vehicles are visible on the road, and a building with closed shutters is seen on the left. The Korean text in the image reads: \"세력이 점점 강해지고 있는 가운데\" (In the midst of a steadily growing force), suggesting a context of increasing intensity or conflict. The setting appears to be a dramatic moment, possibly from a movie or television show.",
"The current frame depicts a dense forest scene with heavy rainfall. The text in Korean reads: \"연합뉴스\" (Yonhap News) and \"지난 2일 이후\" (Since the 2nd). This suggests that the scene is part of a news report or documentary, likely highlighting the impact of the recent weather conditions on the forest or the surrounding area. The focus is on the natural environment, emphasizing the aftermath or the ongoing effects of the rain.",
"The current frame shows a man walking towards a red truck parked in a wet parking lot with several buildings in the background. The text in Korean reads: \"13호 태풍 '링링'과 14호 태풍 '가즈키' 영향으로 폭우 피해 있따라\" (Due to the influence of Typhoon No. 13 'Lingling' and Typhoon No. 14 'Gazuki', there are torrential rain damages). This indicates that the scene is part of a news report or documentary, focusing on the aftermath of the impact of the two typhoons. The emphasis is on the damage caused by the heavy rain, and the man's movement suggests a response or investigation related to the situation.",
"The current frame shows a swollen river with turbulent water flowing rapidly, creating a misty spray. The text in Korean reads: \"림링'의 이동 속도가 점점 빨라지면서\" ('Lingling' is moving faster). This indicates that the scene continues to focus on the impact of Typhoon No. 13 'Lingling', specifically highlighting the increasing speed of the typhoon. The rapid flow of the river suggests that the typhoon is causing significant flooding, and the context remains that of a news report or documentary detailing the effects of the typhoon.",
"The current frame shows a dark, foggy or misty scene, likely due to the weather conditions caused by the typhoon. The text in Korean reads: \"6일 밤 제주도 서귀포 남서쪽 해상을 거쳐 7일 수도권에 강타할 것으로 예상\" ('It is expected to pass through the southwestern sea of Seogwipo, Jeju Island on the night of the 6th and strike the Seoul metropolitan area on the 7th'). This indicates that the scene continues to focus on the impact of Typhoon No. 13 'Lingling', specifically highlighting its expected path and the potential for significant impact on the Seoul metropolitan area. The dark and misty conditions suggest that the typhoon is causing severe weather conditions, and the context remains that of a news report or documentary detailing the effects of the typhoon.",
"The current frame shows a similar dark, foggy or misty scene, likely due to the ongoing impact of Typhoon No. 13 'Lingling'. The text in Korean reads: \"'링링'이 6~7일 우리나라 전역에 영향을 미칠 것으로 예상됨에 따라\" ('As it is expected to affect the entire country on the 6th and 7th'). This indicates that the focus remains on the typhoon's wide-reaching impact across the country, emphasizing the extent of the weather disturbance and the continuity of the news report or documentary on the typhoon's effects. The scene continues to depict severe weather conditions.",
"The current frame shows a map with various weather icons, indicating a severe weather advisory. The text in Korean reads: '경기도 남양주시의 예상 강우량이 100mm 이상으로 예보됨' ('The expected rainfall in Namyangju, Gyeonggi Province is forecasted to be over 100mm'). This indicates that the focus has shifted to specific weather predictions for Namyangju, emphasizing the forecasted heavy rainfall and the continuity of the news report or documentary on the typhoon's effects. The scene continues to depict severe weather conditions and the associated warnings.",
"The current frame shows an illustration of a person with glasses and a red scarf, pointing upwards. The text in Korean reads: '구독하기' ('Subscribe') and '구독 꼭 필요!' ('Subscription is definitely necessary!'), indicating a call to action for viewers to subscribe to the channel. This suggests a shift from the weather advisory to a promotional message for the channel, encouraging audience engagement."
] |
QJY4XlSNVf8
|
The video appears to be a news report or documentary about the impact of Typhoons 'Lingling' and 'Gazuki' on South Korea. The footage shows the effects of heavy rain and strong winds, including flooded rivers, damaged buildings, and severe weather conditions. The report provides updates on the typhoons' paths, expected rainfall, and potential damage, with a focus on the Seoul metropolitan area and other affected regions. The video also includes maps and weather forecasts, highlighting the severity of the situation. The report is interspersed with text overlays providing additional information and context, including the expected trajectory of the typhoons and the anticipated consequences of the heavy rainfall. The video concludes with a promotional message encouraging viewers to subscribe to the channel for further updates and information. Overall, the video aims to inform and update viewers on the developing weather situation and its impact on the region.
|
Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges causing coastal erosion and damage during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to safer areas or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Debris and destroyed buildings scattered in the aftermath of the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Buildings and houses destroyed by strong winds from Typhoon in Philippines, China, and Korea in 2019",
"Flooding in coastal areas and low-lying regions during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to higher ground or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Trees and power lines uprooted or knocked down during Typhoon in Philippines, China, and Korea in 2019",
"Rescue teams providing aid to affected communities during the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Strong winds from Typhoon knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges caused by typhoons in the Philippines, China, and Korea in 2019 resulting in coastal erosion and damage",
"People evacuating to safer areas during Typhoon in the Philippines, China, and Korea in 2019",
"Debris and wreckage scattered on roads and buildings after Typhoon in Philippines, China, and Korea in 2019"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%A7%81%EB%A7%81_(2019%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are commonly associated with a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to have occurred in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas\n5. Debris and wreckage scattered on roads and buildings",
"en_article_excerpt": "Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Lingling_(2019)",
"event_category": "disasters",
"event_name": "typhoon_lingling",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to occur in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas or shelters\n5. Debris and destroyed buildings scattered in the typhoon's aftermath",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typically associated with the aftermath or impact of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Lingling. The events extracted should be specific to the regions affected by the typhoon, including the Philippines, China, and Korea.\n\nEVENTS:\n1. Buildings and houses destroyed by strong winds\n2. Flooding in coastal areas and low-lying regions\n3. People evacuating to higher ground or shelters\n4. Trees and power lines uprooted or knocked down\n5. Rescue teams providing aid to affected communities",
"video_URL": "http://youtube.com/watch?v=ZFR-SBQwtTw",
"video_description": "태풍 '링링' 발생…주후반 한반도 영향 가능성 오늘 오전 9시쯤 필리핀 동쪽 해상에서 13호 태풍 '링링'이 발생했습니다. 강풍반경 200km의 소형 태풍인 '링링'은 계속 북상해서 수요일쯤 타이완 동쪽 해상에 접근하겠습니다. 태풍 '링링'은 금요일 오전쯤 제주도 서귀포 남서쪽 390km 해상까지 진출하겠고 이후 서해상을 향할 것으로 보입니다. 기상청은 태풍 발생 초기라 경로가 유동적이지만 주 후반부터 한반도 부근으로 북상할 가능성이 크다고 내다봤습니다. 연합뉴스TV 기사문의 및 제보 : 카톡/라인 jebo23 ▣ 연합뉴스TV 유튜브 채널 구독 https://goo.gl/VuCJMi ▣ 대한민국 뉴스의 시작 연합뉴스TV / Yonhap News TV http://www.yonhapnewstv.co.kr/",
"video_id": "ZFR-SBQwtTw"
}
| 8
|
[
"The image shows a scene of a coastal area with strong winds, indicated by the swaying palm trees and people moving hurriedly. In the background, there are several high-rise buildings, suggesting an urban coastal environment. The weather appears stormy or windy. At the bottom, Korean text provides information about a typhoon and forecasts that a storm will continue. A bus is visible on the road, and people are walking along the beach. The scene suggests preparations or responses to the weather conditions.",
"The current frame shows a turbulent ocean with large waves crashing against a rocky shoreline. The water appears very rough and foamy, indicating strong wave activity, likely due to the storm mentioned in the previous frame. The scene remains set in a coastal area, reinforcing the ongoing impact of the weather event. The text at the bottom of the image mentions a typhoon and its potential for further storms, aligning with the previous description of stormy conditions.",
"The current frame shows a scene of severe wind conditions with palm trees bending dramatically and street lamps swaying due to strong winds. The background consists of a series of tall buildings, indicating an urban environment. The weather appears overcast, and the visibility is reduced, likely due to the storm's influence. The text at the bottom of the image continues to mention the typhoon and its potential impact, suggesting that the conditions are part of the ongoing weather event.",
"The current frame depicts a chaotic street scene during a severe storm. Two men are seated in the back of a white truck labeled \"CITY ENGINEERS OFFICE,\" holding onto their belongings to prevent them from being blown away. The truck is moving along a road lined with palm trees, which are bending dramatically due to the strong winds, and various street vendors' stalls, some of which are covered with tarpaulins for protection. The background is overcast, and the visibility is low, likely due to the storm's influence. The text at the bottom of the image mentions a typhoon and its potential impact, suggesting that the conditions are part of an ongoing weather event. The time displayed is 13:20, and the text \"연합뉴스 TV\" indicates that this is a news broadcast from a South Korean news channel.",
"The current frame continues to depict the severe storm conditions as seen in the previous frame. The focus remains on the palm trees, which are being violently swayed by the strong winds, indicating the ongoing intensity of the typhoon. The text \"태풍 '링링' 발생...주후반 한반도 영향 가능성\" translates to \"Typhoon 'Linfa' has formed... Possibility of affecting the Korean Peninsula in the second half of the week,\" reinforcing the impact of the typhoon on the region. The time remains 13:20, and the presence of \"연합뉴스 TV\" suggests the footage is part of a news broadcast.",
"The current frame continues to depict the severe storm conditions as seen in the previous frame. The focus remains on the palm trees, which are being violently swayed by the strong winds, indicating the ongoing intensity of the typhoon. The text \"태풍 '링링' 발생...주후반 한반도 영향 가능성\" translates to \"Typhoon 'Linfa' has formed... Possibility of affecting the Korean Peninsula in the second half of the week,\" reinforcing the impact of the typhoon on the region. The time remains 13:20, and the presence of \"연합뉴스 TV\" suggests the footage is part of a news broadcast.",
"The video captures a stormy sea scene. The focus is on the ocean, which is experiencing strong waves and rough conditions, likely due to the typhoon mentioned in the previous frame. The intensity of the storm is evident from the powerful waves crashing. The text \"연합뉴스 TV\" indicates that the footage is part of a news broadcast, and the time is still 13:20. The turbulent sea conditions underscore the ongoing impact of the typhoon on the region.",
"The video now shows a harbor area with several boats moored, presumably to escape the storm's impact. The boats are secured with ropes and surrounded by calm waters, suggesting they are anchored to ride out the storm. The text \"연합뉴스 TV\" confirms the footage is from the news broadcast, and the time has advanced to 13:21. The serene harbor scene contrasts with the previous stormy sea conditions, indicating the boats are now safe from the typhoon's immediate effects."
] |
ZFR-SBQwtTw
|
A typhoon, identified as Typhoon 'Linfa', is impacting a coastal area in the Korean Peninsula, causing strong winds and rough sea conditions. The video shows the storm's effects on the urban environment, with palm trees swaying violently, street lamps bending, and people preparing for or responding to the weather. The footage, part of a news broadcast from 연합뉴스 TV, captures the intensity of the storm, including turbulent ocean scenes with large waves crashing against the shoreline. As the storm progresses, the video shows a truck from the City Engineers Office navigating through the windy streets, and later, a harbor area where boats are moored to escape the storm's impact. The typhoon's potential to affect the Korean Peninsula in the second half of the week is highlighted, indicating the ongoing threat of the weather event.
|
Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges causing coastal erosion and damage during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to safer areas or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Debris and destroyed buildings scattered in the aftermath of the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Buildings and houses destroyed by strong winds from Typhoon in Philippines, China, and Korea in 2019",
"Flooding in coastal areas and low-lying regions during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to higher ground or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Trees and power lines uprooted or knocked down during Typhoon in Philippines, China, and Korea in 2019",
"Rescue teams providing aid to affected communities during the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Strong winds from Typhoon knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges caused by typhoons in the Philippines, China, and Korea in 2019 resulting in coastal erosion and damage",
"People evacuating to safer areas during Typhoon in the Philippines, China, and Korea in 2019",
"Debris and wreckage scattered on roads and buildings after Typhoon in Philippines, China, and Korea in 2019"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%A7%81%EB%A7%81_(2019%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are commonly associated with a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to have occurred in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas\n5. Debris and wreckage scattered on roads and buildings",
"en_article_excerpt": "Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Lingling_(2019)",
"event_category": "disasters",
"event_name": "typhoon_lingling",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to occur in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas or shelters\n5. Debris and destroyed buildings scattered in the typhoon's aftermath",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typically associated with the aftermath or impact of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Lingling. The events extracted should be specific to the regions affected by the typhoon, including the Philippines, China, and Korea.\n\nEVENTS:\n1. Buildings and houses destroyed by strong winds\n2. Flooding in coastal areas and low-lying regions\n3. People evacuating to higher ground or shelters\n4. Trees and power lines uprooted or knocked down\n5. Rescue teams providing aid to affected communities",
"video_URL": "http://youtube.com/watch?v=8-DXe4qYo2E",
"video_description": "#태풍 #링링 (서울=연합뉴스) 제13호 태풍 '링링'이 필리핀 동부에서 발생했습니다. 이 태풍의 중심기압은 1천hPa(헥토파스칼), 중심 부근 최대 풍속은 초속 18ｍ(시속 65㎞)이며, 강풍 반경은 200㎞입니다. 한반도에 접근할 무렵 지금보다 크고 강해질 것으로 전망돼 대비가 필요한데요. 자세한 내용은 영상으로 보시죠. ◆ 연합뉴스 홈페이지→ http://www.yna.co.kr/ ◆ 이 시각 많이 본 기사 → https://goo.gl/VQTsSZ ◆ 오늘의 핫뉴스 → https://goo.gl/WyGXpG ◆ 현장영상 → https://goo.gl/5aZcx8 ◆ 카드뉴스 →https://goo.gl/QKfDTH ◆연합뉴스 공식 SNS◆ ◇페이스북→ https://www.facebook.com/yonhap/ ▣ 연합뉴스 유튜브 채널 구독 : https://goo.gl/pL7TmT ▣ 연합뉴스 인스타 : https://goo.gl/UbqiQb",
"video_id": "8-DXe4qYo2E"
}
| 8
|
[
"The image shows a weather map highlighting the potential path of a typhoon. The map indicates various stages of the typhoon's movement, with dates and times marked along its trajectory. A highlighted section in red suggests that there is a possibility of the typhoon affecting Korea. The text \"이번 주말 한국 강타 가능성이 있어\" translates to \"There is a possibility that this weekend Korea will be hit.\"",
"The image depicts a dramatic scene of turbulent ocean waves crashing against a rocky shore under heavy fog. A lighthouse is visible in the distance, partially obscured by the mist. The text in the image reads \"이날 오전, 필리핀 마닐라 동쪽 약 560km 해상서 열대저압부가 태풍으로 발달\" which translates to \"This morning, a tropical low-pressure system developed into a typhoon about 560km east of Manila, Philippines.\" This suggests that a typhoon has formed in the Philippine Sea, aligning with the previous weather map's forecast of a potential typhoon affecting Korea.",
"The current frame shows a stormy scene with heavy rain and strong winds at a coastal area. Waves are crashing against a breakwater, creating a misty atmosphere. A sign with the text \"현재 시속 26km로 북서쪽으로 이동 중\" is visible, which translates to \"Currently moving northwest at a speed of 26 km/h.\" This indicates that a typhoon or severe storm is moving towards the area, consistent with the previous information about the development of a typhoon in the Philippine Sea.",
"The current frame continues to depict the stormy coastal scene with turbulent waves crashing against the breakwater. The weather remains severe with heavy rain and strong winds. Text in the image reads \"태풍은 6일 오전 9시까지 제주도 서귀포 남서쪽 약 390km 부근 바다\" which translates to \"The typhoon will be approximately 390 km southwest of Seogwipo, Jeju Island by 9 AM on the 6th.\" This update indicates the typhoon's trajectory and provides a timeline for its progression, emphasizing the ongoing threat and the need for precautions.",
"The current frame shows a continuation of the stormy coastal scene with turbulent waves crashing against the breakwater. The severe weather persists with heavy rain and strong winds. Text in the image reads \"연합뉴스\" indicating the source of the footage. The scene remains intense, showcasing the impact of the typhoon on the coastal area.",
"The current frame shows a continuation of the stormy coastal scene with turbulent waves crashing against the breakwater. The severe weather persists with heavy rain and strong winds. Text in the image reads \"연합뉴스\" indicating the source of the footage. The scene remains intense, showcasing the impact of the typhoon on the coastal area.",
"The current frame shows a close-up of a tree branch with leaves in a misty or foggy environment. The scene indicates heavy rainfall, as suggested by the wet leaves and the overall visibility. The source of the footage is indicated by the text \"연합뉴스\" (Yonhap News). The presence of rain and the context of the video suggest that the tree is enduring the effects of a typhoon or storm, emphasizing the adverse weather conditions.",
"The current frame shows a cartoon character, possibly an elderly man with glasses and a red scarf, pointing upwards with a smile. The character appears to be speaking, with the text \"구독 꼭-인!\" (Subscribe - must!) in a speech bubble. The background is plain white. The source of the footage is indicated by the text \"연합뉴스\" (Yonhap News). The image appears to be a humorous or lighthearted promotional graphic, possibly encouraging viewers to subscribe to a service or channel."
] |
8-DXe4qYo2E
|
A typhoon is forecasted to affect Korea, as shown on a weather map highlighting its potential path. The storm develops in the Philippine Sea, east of Manila, and moves northwest towards Korea. The video depicts the severe weather conditions at a coastal area, with heavy rain, strong winds, and turbulent waves crashing against a breakwater. Updates on the typhoon's trajectory and timeline are provided, indicating its proximity to Jeju Island. The storm's impact on the coastal area is showcased, with scenes of heavy rainfall and strong winds. The video concludes with a promotional graphic encouraging viewers to subscribe, unrelated to the storm coverage.
|
Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges causing coastal erosion and damage during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to safer areas or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Debris and destroyed buildings scattered in the aftermath of the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Buildings and houses destroyed by strong winds from Typhoon in Philippines, China, and Korea in 2019",
"Flooding in coastal areas and low-lying regions during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to higher ground or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Trees and power lines uprooted or knocked down during Typhoon in Philippines, China, and Korea in 2019",
"Rescue teams providing aid to affected communities during the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Strong winds from Typhoon knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges caused by typhoons in the Philippines, China, and Korea in 2019 resulting in coastal erosion and damage",
"People evacuating to safer areas during Typhoon in the Philippines, China, and Korea in 2019",
"Debris and wreckage scattered on roads and buildings after Typhoon in Philippines, China, and Korea in 2019"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%A7%81%EB%A7%81_(2019%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are commonly associated with a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to have occurred in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas\n5. Debris and wreckage scattered on roads and buildings",
"en_article_excerpt": "Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Lingling_(2019)",
"event_category": "disasters",
"event_name": "typhoon_lingling",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to occur in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas or shelters\n5. Debris and destroyed buildings scattered in the typhoon's aftermath",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typically associated with the aftermath or impact of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Lingling. The events extracted should be specific to the regions affected by the typhoon, including the Philippines, China, and Korea.\n\nEVENTS:\n1. Buildings and houses destroyed by strong winds\n2. Flooding in coastal areas and low-lying regions\n3. People evacuating to higher ground or shelters\n4. Trees and power lines uprooted or knocked down\n5. Rescue teams providing aid to affected communities",
"video_URL": "http://youtube.com/watch?v=taOktWIvk20",
"video_description": "#태풍 #링링 #서울태풍 #수도권태풍 #최근접 #초강력태풍 (서울=연합뉴스) 한반도를 강타할 초강력 제13호 태풍 '링링'이 왔습니다. 기상청에 따르면 태풍은 7일 새벽 서귀포 서쪽 약 150㎞ 해상을 통과, 오전 6시께 전남 목포 서쪽 약 140㎞ 해상을 지났습니다. 정오께 서울 서남서쪽 약 140㎞ 해상을 지날 것으로 보이는데요. 오후 2시께 태풍 중심이 서울에 제일 가까울 전망입니다. 영상으로 보시겠습니다. [영상 : 연합뉴스TV] ◆ 연합뉴스 홈페이지→ http://www.yna.co.kr/ ◆ 이 시각 많이 본 기사 → https://goo.gl/VQTsSZ ◆ 오늘의 핫뉴스 → https://goo.gl/WyGXpG ◆ 현장영상 → https://goo.gl/5aZcx8 ◆ 카드뉴스 →https://goo.gl/QKfDTH ◆연합뉴스 공식 SNS◆ ◇페이스북→ https://www.facebook.com/yonhap/ ▣ 연합뉴스 유튜브 채널 구독 : https://goo.gl/pL7TmT ▣ 연합뉴스 인스타 : https://goo.gl/UbqiQb",
"video_id": "taOktWIvk20"
}
| 8
|
[
"The image shows a street scene with power lines and trees visible. There is a road sign in the foreground. The text in Korean reads \"연합뉴스 한반도를 감싸할 초강력 제13호 태풍 '링링'\" which translates to \"Yonhap News, Super Typhoon No. 13 'Lingling' enveloping the Korean Peninsula.\" The scene suggests preparations or warnings related to the approaching typhoon.",
"The image depicts a scene of a fishing boat with several individuals on board, likely preparing or in the midst of dealing with the effects of a typhoon. The text in Korean reads \"태풍제주강타...서귀포 서쪽 약 150km 해상 통과\" which translates to \"Typhoon hits Jeju strongly...Passes through the sea about 150km west of Seogwipo.\" The context indicates the impact of the typhoon on the coastal area, with the fishing boat being a focal point, suggesting ongoing efforts to handle the situation or the aftermath of the storm's passage.",
"The image shows a street corner in disarray with a truck and fallen utility poles and wires. A large sign is toppled over. The Korean text translates to \"The truck has been knocked over by the typhoon.\" This frame illustrates the aftermath of the typhoon's impact on urban infrastructure, showing damage to vehicles and street utilities, indicating the severity of the storm's effects in this area.",
"The scene shows a harbor with boats moored in the water. In the background, there are bright lights and structures, possibly indicating a dock or industrial area. The Korean text reads \"정오께 서울 서남쪽 약 140km 해상 지날듯,\" which translates to \"Around noon, it will pass over the sea about 140km southwest of Seoul.\" This suggests a weather event, likely the same typhoon mentioned in the previous frame, is expected to move in this direction, emphasizing the ongoing nature of the storm's path and its potential impact on the harbor and surrounding areas.",
"The scene shows a person in a green jacket being pushed by strong winds. The Korean text reads \"태풍특보 발효...\" \"매우 강한 바람 유의해야\" which translates to \"Typhoon special warning in effect... Be careful of very strong winds.\" This indicates the continuation of the storm's impact, with the focus now on the strong winds affecting individuals and emphasizing the need for caution.",
"The scene shows a person with a green jacket being pushed by strong winds. The Korean text reads \"태풍특보 발효...\" \"매우 강한 바람 유의해야\" which translates to \"Typhoon special warning in effect... Be careful of very strong winds.\" This indicates the continuation of the storm's impact, with the focus now on the strong winds affecting individuals and emphasizing the need for caution.",
"The person in the green jacket is now being helped by a police officer who is wearing a bright yellow raincoat with a hood. The police officer is standing close to the individual and appears to be providing assistance or guidance, likely due to the ongoing storm conditions. The text in the frame, \"태풍특보 발효...\" and \"매우 강한 바람 유의해야,\" remains visible, reinforcing the severe weather situation and the importance of safety measures.",
"The scene shows the logo of Yonhap News Agency on a blue background."
] |
taOktWIvk20
|
The video depicts the impact of Super Typhoon No. 13 'Lingling' as it envelops the Korean Peninsula. The typhoon brings strong winds and causes damage to urban infrastructure, including overturned trucks, fallen utility poles, and wires. Coastal areas are also affected, with a fishing boat and harbor shown amidst the storm. Individuals are seen struggling with the strong winds, with one person in a green jacket being pushed by the gusts and later assisted by a police officer in a yellow raincoat. The typhoon's path is tracked, with expectations of it passing near Seoul, and warnings are issued for people to be cautious of the very strong winds. The video concludes with the logo of Yonhap News Agency, indicating the source of the report. Overall, the video showcases the severity of the typhoon's effects on both coastal and urban areas, highlighting the need for caution and the response of authorities to assist those affected.
|
Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges causing coastal erosion and damage during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to safer areas or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Debris and destroyed buildings scattered in the aftermath of the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Buildings and houses destroyed by strong winds from Typhoon in Philippines, China, and Korea in 2019",
"Flooding in coastal areas and low-lying regions during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to higher ground or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Trees and power lines uprooted or knocked down during Typhoon in Philippines, China, and Korea in 2019",
"Rescue teams providing aid to affected communities during the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Strong winds from Typhoon knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges caused by typhoons in the Philippines, China, and Korea in 2019 resulting in coastal erosion and damage",
"People evacuating to safer areas during Typhoon in the Philippines, China, and Korea in 2019",
"Debris and wreckage scattered on roads and buildings after Typhoon in Philippines, China, and Korea in 2019"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%A7%81%EB%A7%81_(2019%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are commonly associated with a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to have occurred in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas\n5. Debris and wreckage scattered on roads and buildings",
"en_article_excerpt": "Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Lingling_(2019)",
"event_category": "disasters",
"event_name": "typhoon_lingling",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to occur in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas or shelters\n5. Debris and destroyed buildings scattered in the typhoon's aftermath",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typically associated with the aftermath or impact of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Lingling. The events extracted should be specific to the regions affected by the typhoon, including the Philippines, China, and Korea.\n\nEVENTS:\n1. Buildings and houses destroyed by strong winds\n2. Flooding in coastal areas and low-lying regions\n3. People evacuating to higher ground or shelters\n4. Trees and power lines uprooted or knocked down\n5. Rescue teams providing aid to affected communities",
"video_URL": "http://youtube.com/watch?v=t1uezBvD9U8",
"video_description": "태풍 '링링'이 서해안을 따라 빠르게 북상하면서 충북 지역 피해도 속출하고 있습니다. 충북 지역 피해 현장을 카메라에 담았습니다.",
"video_id": "t1uezBvD9U8"
}
| 8
|
[
"A large tree has fallen onto a sidewalk in an urban area, blocking part of the street and possibly causing damage to nearby buildings or infrastructure. The area appears to be a commercial district with visible storefronts.",
"The fallen tree continues to block the sidewalk, with some leaves and branches littering the ground. A person in a yellow jacket is seen walking by the tree, seemingly undisturbed by the fallen tree. The urban environment remains consistent with the previous frame, suggesting minimal change in the situation.",
"The fallen tree is no longer present, and the scene has shifted to a fallen signboard that is leaning against a building on the sidewalk. Yellow lights are scattered around the signboard, and a person in a dark outfit is walking by the signboard, seemingly unaffected by it. The urban environment remains consistent, suggesting minimal change in the situation.",
"The fallen signboard continues to rest against the building, with yellow lights still scattered around it. The individual in a dark outfit has moved slightly away from the signboard, and a person in a light-colored shirt appears near the background, walking along the sidewalk. The urban setting remains unchanged, indicating a static scenario without significant progression.",
"The fallen signboard continues to rest against the building, with yellow lights still scattered around it. The individual in a dark outfit has moved slightly away from the signboard, and a person in a light-colored shirt appears near the background, walking along the sidewalk. The urban setting remains unchanged, indicating a static scenario without significant progression.",
"The current frame depicts a scene outside a building with a partially visible sign that reads \"CAFE.\" The focus is on the backdrop of a rainy day, evident from the raindrops on the camera lens. A green net is prominently displayed, likely part of a sports facility, with trees in the foreground and a slightly blurred building in the background. The setting appears static, with no significant movement or activity observable.",
"The current frame shows a large, partially collapsed structure on the side of a road, with debris scattered around. The structure, which seems to be a billboard or a large sign, is leaning at an angle, with its base buried in dirt and surrounded by broken pieces. The background includes a mix of natural and urban elements, such as mountains, buildings, and a clear sky. The scene suggests a recent incident, possibly caused by natural forces or structural failure, with no people visible in the frame.",
"The scene continues to depict the aftermath of the structural collapse. The large billboard or sign remains partially collapsed, leaning over the roadside with its base still buried in the dirt. Debris continues to be scattered around the area, reinforcing the impression of a recent incident. The background remains consistent with mountains and buildings, and the sky is clear, suggesting no immediate signs of further disturbances. No people are visible in this frame, indicating that the focus remains on the aftermath of the collapse rather than any ongoing activities."
] |
t1uezBvD9U8
|
A series of incidents occurred in an urban area, starting with a large tree falling onto a sidewalk, blocking the street and potentially causing damage to nearby buildings. The tree was later removed, revealing a fallen signboard leaning against a building, surrounded by yellow lights. The scene then shifted to a different location, showing a rainy day outside a cafe with a green net in the background, possibly part of a sports facility. The video then cut to a road where a large billboard or sign had partially collapsed, scattering debris and leaning at an angle, with no people visible in the aftermath. Throughout the video, the urban environment remained consistent, with commercial districts, buildings, and natural elements like trees and mountains visible in the background. The events depicted appear to be unrelated, showing different incidents of damage or disruption in the urban area.
|
Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.
|
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding in urban areas of the Korean Peninsula during Typhoon Soulik in 2012",
"Heavy rainfall causing flooding in urban areas of the Korean Peninsula during Typhoon Khanun in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Soulik in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Khanun in 2012"
] |
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities caused by Typhoon Soulik on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities due to Typhoon Khanun on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Soulik hit the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Khanun hit the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
[
"Strong winds from Typhoon Soulik blowing down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun blowing down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Soulik on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Khanun in the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Soulik on the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Khanun on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Soulik on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Khanun in the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EC%86%94%EB%A6%AD_(2018%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Soulik, it makes sense to extract events that are commonly associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and damage to infrastructure. These events are likely to be visualized in a video and are consistent with the characteristics of a powerful typhoon like Soulik.\n\nEVENTS:\n1. Strong winds blowing down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Debris flying through the air\n4. Roofs being torn off buildings\n5. Emergency responders evacuating people from flooded areas",
"en_article_excerpt": "Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Soulik_(2018)",
"event_category": "disasters",
"event_name": "typhoon_soulik",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to Typhoon Soulik, it makes sense to consider the typical consequences and scenes associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and resulting damage. Given the typhoon's impact on the Korean Peninsula, events related to severe weather, destruction, and potential evacuation or rescue efforts are likely to be relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Residents evacuating their homes and seeking shelter\n4. Emergency responders rescuing people from flooded areas\n5. Debris and damaged buildings scattered across the affected regions",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact and aftermath of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Soulik. Given the severity of the typhoon, events that depict its powerful effects on the Korean Peninsula are most relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal areas and cities\n3. People evacuating their homes and seeking shelter\n4. Debris and destroyed buildings scattered across streets\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1032900418777407489",
"video_description": "제주도 태풍 솔릭의 강풍의 무서움.. 오토바이도 날려버리는 태풍 솔릭.. ㄷㄷㄷ",
"video_id": "1032900418777407489"
}
| 8
|
[
"The image shows a view from inside a vehicle, looking out through the windshield. The windshield wipers are active, indicating that it is raining. The visibility outside is low due to the rain, making the scene appear hazy and blurry. The road ahead is not clearly visible, and the surroundings include buildings and some vehicles.",
"The image continues to depict a view from inside a vehicle, with the windshield wipers still active, indicating ongoing rain. The visibility remains low, and the road ahead is not clearly visible. The surroundings still include buildings and some vehicles, consistent with the previous frame.",
"The image continues to show the view from inside a vehicle, with the windshield wipers still active, indicating ongoing rain. Visibility remains low, and the road ahead is not clearly visible. The surroundings include buildings and some vehicles, consistent with the previous frame.",
"The scene continues to depict the view from inside a vehicle, with the windshield wipers still active, indicating persistent rain. The visibility remains low, and the road ahead is not clearly visible. The surroundings include buildings and some vehicles, consistent with the previous frame.",
"The windshield wipers continue their movement, maintaining a clear view of the road despite the ongoing rain. Visibility is slightly better, revealing the road markings ahead and allowing for cautious driving. The surroundings still include buildings and some vehicles, indicating a continuous journey through the rainy environment.",
"The view from inside a vehicle shows heavy rain creating a blurred effect on the windshield, reducing visibility. The windshield wipers are still in motion, trying to clear the water. The road ahead is barely visible through the rain, with some vehicles faintly discernible in the distance. The interior of the vehicle is partially visible, including a rearview mirror and some hanging decorations.",
"The current frame continues to depict a scene viewed from inside a vehicle during heavy rain, with visibility significantly reduced due to the rainwater on the windshield. The windshield wipers are actively working to clear the water, though the effect is somewhat diminished by the intensity of the rain. The road ahead remains obscured, making it challenging to see the details clearly, but faint outlines of other vehicles can still be seen in the distance, indicating that traffic is present. The interior of the vehicle, including the rearview mirror and some hanging decorations, is partially visible, maintaining consistency with the previous frame's description. The overall scene suggests that the driver is navigating through a storm, requiring caution due to the poor visibility conditions.",
"The scene continues from inside the vehicle during the ongoing heavy rain. The windshield wipers are still in motion, attempting to clear the rainwater but with limited success due to the intensity of the downpour. The road ahead remains obscured, though the outlines of other vehicles are still visible, suggesting the presence of traffic. The interior of the vehicle, including the dashboard and part of the rearview mirror, is partially visible. The overall atmosphere indicates the driver is navigating cautiously through the storm, with reduced visibility conditions."
] |
1032900418777407489
|
The video depicts a person driving a vehicle through a rainy environment, with the entire sequence shot from the perspective of the driver's seat. The windshield wipers are constantly in motion, attempting to clear the rainwater and maintain visibility. Despite their efforts, the view of the road ahead remains partially obscured throughout the video, with the surroundings, including buildings and other vehicles, being only faintly discernible. The driver navigates cautiously, as indicated by the slow and careful progression through the rain-soaked road, with traffic present but details of other vehicles and the road itself being difficult to make out due to the heavy rain. The interior of the vehicle is occasionally visible, including the rearview mirror and some decorations, but the primary focus remains on the challenging driving conditions outside. The video captures a continuous journey through a stormy, rainy setting, emphasizing the difficulties of driving under such conditions and the need for cautious navigation.
|
Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.
|
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding in urban areas of the Korean Peninsula during Typhoon Soulik in 2012",
"Heavy rainfall causing flooding in urban areas of the Korean Peninsula during Typhoon Khanun in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Soulik in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Khanun in 2012"
] |
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities caused by Typhoon Soulik on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities due to Typhoon Khanun on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Soulik hit the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Khanun hit the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
[
"Strong winds from Typhoon Soulik blowing down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun blowing down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Soulik on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Khanun in the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Soulik on the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Khanun on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Soulik on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Khanun in the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EC%86%94%EB%A6%AD_(2018%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Soulik, it makes sense to extract events that are commonly associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and damage to infrastructure. These events are likely to be visualized in a video and are consistent with the characteristics of a powerful typhoon like Soulik.\n\nEVENTS:\n1. Strong winds blowing down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Debris flying through the air\n4. Roofs being torn off buildings\n5. Emergency responders evacuating people from flooded areas",
"en_article_excerpt": "Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Soulik_(2018)",
"event_category": "disasters",
"event_name": "typhoon_soulik",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to Typhoon Soulik, it makes sense to consider the typical consequences and scenes associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and resulting damage. Given the typhoon's impact on the Korean Peninsula, events related to severe weather, destruction, and potential evacuation or rescue efforts are likely to be relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Residents evacuating their homes and seeking shelter\n4. Emergency responders rescuing people from flooded areas\n5. Debris and damaged buildings scattered across the affected regions",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact and aftermath of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Soulik. Given the severity of the typhoon, events that depict its powerful effects on the Korean Peninsula are most relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal areas and cities\n3. People evacuating their homes and seeking shelter\n4. Debris and destroyed buildings scattered across streets\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1032211760315420675",
"video_description": "실시간 제주도 서귀포 상황 태풍 솔릭...위험행..........조심하세요다들",
"video_id": "1032211760315420675"
}
| 8
|
[
"The image shows a road obstructed by fallen palm tree branches and debris. Several vehicles are stopped ahead, likely due to the obstruction. The palm trees in the background appear to be swaying heavily, suggesting strong winds or a storm.",
"The road remains obstructed by fallen palm tree branches and debris. The strong winds continue to sway the palm trees in the background. The vehicles ahead are still stopped, indicating the obstruction persists. The overcast sky and wet road suggest that it is still stormy.",
"The vehicle is now in motion, driving through the crosswalk. The road ahead appears clear, with palm trees swaying due to strong winds. The vehicles previously stopped have moved forward, indicating the obstruction has been cleared. The overcast sky and wet road continue to suggest stormy weather conditions.",
"The vehicle continues to drive forward on the road, passing by a large pile of debris, likely fallen palm fronds, on the right side of the road. The palm trees in the background continue to sway in the strong wind, indicating ongoing stormy weather conditions. The road ahead appears mostly clear, with a few vehicles visible in the distance.",
"The vehicle moves forward on the road, passing a large pile of debris, possibly fallen palm fronds, on the right side. The palm trees in the background continue to sway, suggesting that the stormy weather persists. The road ahead remains mostly clear, with distant vehicles visible.",
"The vehicle continues to move forward on the road, passing another large pile of debris, possibly fallen palm fronds, on the right side. The palm trees in the background still sway, indicating the stormy weather persists. The road ahead remains mostly clear, with distant vehicles visible.",
"The vehicle moves forward, and the windscreen shows raindrops, indicating the stormy weather continues. The road ahead remains mostly clear with trees visible in the background, still swaying from the wind.",
"The car continues to drive, and the windshield still has raindrops, maintaining the stormy weather condition. The road remains clear with trees in the background, still swaying due to the wind."
] |
1032211760315420675
|
A vehicle navigates through a road obstructed by debris from fallen palm tree branches, likely caused by a storm with strong winds. Initially, the vehicle is stopped due to the obstruction, but as the debris is cleared, it proceeds to drive through the road, passing by several piles of debris. Throughout the journey, the stormy weather persists, characterized by strong winds swaying palm trees, an overcast sky, a wet road, and raindrops on the windshield. The vehicle continues to drive forward, eventually moving through a mostly clear road with distant vehicles visible, all while the stormy conditions continue.
|
Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.
|
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding in urban areas of the Korean Peninsula during Typhoon Soulik in 2012",
"Heavy rainfall causing flooding in urban areas of the Korean Peninsula during Typhoon Khanun in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Soulik in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Khanun in 2012"
] |
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities caused by Typhoon Soulik on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities due to Typhoon Khanun on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Soulik hit the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Khanun hit the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
[
"Strong winds from Typhoon Soulik blowing down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun blowing down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Soulik on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Khanun in the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Soulik on the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Khanun on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Soulik on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Khanun in the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EC%86%94%EB%A6%AD_(2018%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Soulik, it makes sense to extract events that are commonly associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and damage to infrastructure. These events are likely to be visualized in a video and are consistent with the characteristics of a powerful typhoon like Soulik.\n\nEVENTS:\n1. Strong winds blowing down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Debris flying through the air\n4. Roofs being torn off buildings\n5. Emergency responders evacuating people from flooded areas",
"en_article_excerpt": "Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Soulik_(2018)",
"event_category": "disasters",
"event_name": "typhoon_soulik",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to Typhoon Soulik, it makes sense to consider the typical consequences and scenes associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and resulting damage. Given the typhoon's impact on the Korean Peninsula, events related to severe weather, destruction, and potential evacuation or rescue efforts are likely to be relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Residents evacuating their homes and seeking shelter\n4. Emergency responders rescuing people from flooded areas\n5. Debris and damaged buildings scattered across the affected regions",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact and aftermath of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Soulik. Given the severity of the typhoon, events that depict its powerful effects on the Korean Peninsula are most relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal areas and cities\n3. People evacuating their homes and seeking shelter\n4. Debris and destroyed buildings scattered across streets\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1032540315515682816",
"video_description": "#태풍 #솔릭 예상 경로! 동쪽으로 방향 틀어",
"video_id": "1032540315515682816"
}
| 8
|
[
"The image displays a weather map from windy.com showing temperature and weather patterns over the region of North Korea, South Korea, and parts of China and Japan. It includes city names and temperature readings, indicating various temperatures across the areas. The map highlights weather systems, with color gradients showing temperature variations.",
"The image is a weather map from windy.com showing temperature and weather patterns over the region of North Korea, South Korea, and parts of China and Japan. It includes city names and temperature readings, indicating various temperatures across the areas. The map highlights weather systems, with color gradients showing temperature variations.",
"The image is a weather map from windy.com showing temperature and weather patterns over the region of North Korea, South Korea, and parts of China and Japan. It includes city names and temperature readings, indicating various temperatures across the areas. The map highlights weather systems, with color gradients showing temperature variations.",
"The image continues to display a weather map from windy.com, focusing on temperature and weather patterns over North Korea, South Korea, and parts of China and Japan. City names and temperature readings are present, showing a range of temperatures across the regions. The map highlights weather systems with color gradients indicating temperature variations, with a particular emphasis on a warmer region over South Korea and the surrounding area.",
"The image continues to display a weather map from windy.com, focusing on temperature and weather patterns over North Korea, South Korea, and parts of China and Japan. City names and temperature readings are present, showing a range of temperatures across the regions. The map highlights weather systems with color gradients indicating temperature variations, with a particular emphasis on a warmer region over South Korea and the surrounding area.",
"The weather map from windy.com remains the focal point, showing consistent temperature readings across the regions. North and South Korea, along with parts of China and Japan, are still marked with city names and temperatures. A notable warmer region over South Korea persists, highlighted by color gradients. The weather system colors remain unchanged, indicating stable weather patterns. The video maintains its focus on the temperature variations, with no significant alterations in the weather map's display.",
"The current frame continues to display the weather map from windy.com, maintaining the focus on temperature variations across North and South Korea, parts of China, and Japan. The temperatures in these regions remain consistent with the previous frame, with no significant changes noted. The warmer region over South Korea is still highlighted, and the weather system colors show no alterations, indicating stable weather patterns. The video continues to emphasize the temperature differences without any notable changes in the weather map's presentation.",
"The weather map from windy.com continues to showcase temperature variations across North and South Korea, parts of China, and Japan, with no significant changes in temperatures or weather patterns since the previous frame. The warmer region over South Korea persists, and the weather system colors remain consistent, indicating stable weather conditions. The video maintains its focus on the temperature differences across the regions without any notable alterations in the map's presentation."
] |
1032540315515682816
|
The video depicts a stable weather pattern over North Korea, South Korea, and parts of China and Japan, as shown on a weather map from windy.com. The map consistently displays temperature variations across the regions, with city names and temperature readings indicating a range of temperatures. A warmer region over South Korea and its surrounding area is particularly highlighted throughout the video. The weather system colors remain unchanged, indicating no significant alterations in the weather patterns. The video maintains a steady focus on the temperature differences across the regions, with no notable changes in the weather map's presentation over time.
|
Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.
|
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding in urban areas of the Korean Peninsula during Typhoon Soulik in 2012",
"Heavy rainfall causing flooding in urban areas of the Korean Peninsula during Typhoon Khanun in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Soulik in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Khanun in 2012"
] |
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities caused by Typhoon Soulik on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities due to Typhoon Khanun on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Soulik hit the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Khanun hit the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
[
"Strong winds from Typhoon Soulik blowing down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun blowing down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Soulik on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Khanun in the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Soulik on the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Khanun on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Soulik on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Khanun in the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EC%86%94%EB%A6%AD_(2018%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Soulik, it makes sense to extract events that are commonly associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and damage to infrastructure. These events are likely to be visualized in a video and are consistent with the characteristics of a powerful typhoon like Soulik.\n\nEVENTS:\n1. Strong winds blowing down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Debris flying through the air\n4. Roofs being torn off buildings\n5. Emergency responders evacuating people from flooded areas",
"en_article_excerpt": "Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Soulik_(2018)",
"event_category": "disasters",
"event_name": "typhoon_soulik",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to Typhoon Soulik, it makes sense to consider the typical consequences and scenes associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and resulting damage. Given the typhoon's impact on the Korean Peninsula, events related to severe weather, destruction, and potential evacuation or rescue efforts are likely to be relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Residents evacuating their homes and seeking shelter\n4. Emergency responders rescuing people from flooded areas\n5. Debris and damaged buildings scattered across the affected regions",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact and aftermath of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Soulik. Given the severity of the typhoon, events that depict its powerful effects on the Korean Peninsula are most relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal areas and cities\n3. People evacuating their homes and seeking shelter\n4. Debris and destroyed buildings scattered across streets\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1032471495958618112",
"video_description": "어제 저녁부터 비바람이 거세지다 잠잠하다 하더니, 지금은 세차게 몰아치는 중입니다 ㅠㅠ #태풍솔릭 #제주도 #제주시",
"video_id": "1032471495958618112"
}
| 8
|
[
"The current frame shows a view of a dense tree with green leaves. The sky appears overcast, suggesting it might be a cloudy day. There is no visible human activity or animals in the frame. The focus is primarily on the tree and the surrounding foliage.",
"The frame continues to show the dense tree with green leaves under an overcast sky, maintaining the continuity of the serene, cloudy setting from the previous frame. There is still no visible human activity or animals, with the focus remaining on the tree and surrounding foliage.",
"The frame depicts the dense tree with green leaves under a cloudy sky, similar to the previous frames. There is still no visible human activity or animals, with the focus remaining on the tree and surrounding foliage.",
"The current frame shows a dense tree with green leaves under a cloudy sky, consistent with the previous frames. The tree remains the focal point, with no visible human activity or animals, emphasizing the serene natural setting.",
"The scene continues to focus on a dense tree with green leaves under a cloudy sky, maintaining the serene natural setting. The tree remains the focal point, with no visible human activity or animals, suggesting a quiet and undisturbed environment.",
"The scene continues to focus on a dense tree with green leaves under a cloudy sky, maintaining the serene natural setting. The tree remains the focal point, with no visible human activity or animals, suggesting a quiet and undisturbed environment.",
"The scene continues to focus on a dense tree with green leaves under a cloudy sky, maintaining the serene natural setting. The tree remains the focal point, with no visible human activity or animals, suggesting a quiet and undisturbed environment.",
"The video maintains its focus on a dense tree with green leaves, continuing the serene and undisturbed natural setting established in the previous frame. The tree remains the focal point, with no visible human activity or animals, reinforcing the tranquil atmosphere of the environment."
] |
1032471495958618112
|
The video depicts a serene and undisturbed natural setting, focusing on a dense tree with green leaves under a cloudy sky. The scene remains consistent throughout, with no visible human activity or animals, emphasizing the quiet and tranquil atmosphere of the environment. The tree is the central focal point, surrounded by foliage, and the overcast sky adds to the calm ambiance, creating a sense of stillness and peacefulness that persists throughout the video.
|
Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.
|
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding in urban areas of the Korean Peninsula during Typhoon Soulik in 2012",
"Heavy rainfall causing flooding in urban areas of the Korean Peninsula during Typhoon Khanun in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Soulik in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Khanun in 2012"
] |
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities caused by Typhoon Soulik on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities due to Typhoon Khanun on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Soulik hit the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Khanun hit the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
[
"Strong winds from Typhoon Soulik blowing down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun blowing down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Soulik on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Khanun in the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Soulik on the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Khanun on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Soulik on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Khanun in the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EC%86%94%EB%A6%AD_(2018%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Soulik, it makes sense to extract events that are commonly associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and damage to infrastructure. These events are likely to be visualized in a video and are consistent with the characteristics of a powerful typhoon like Soulik.\n\nEVENTS:\n1. Strong winds blowing down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Debris flying through the air\n4. Roofs being torn off buildings\n5. Emergency responders evacuating people from flooded areas",
"en_article_excerpt": "Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Soulik_(2018)",
"event_category": "disasters",
"event_name": "typhoon_soulik",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to Typhoon Soulik, it makes sense to consider the typical consequences and scenes associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and resulting damage. Given the typhoon's impact on the Korean Peninsula, events related to severe weather, destruction, and potential evacuation or rescue efforts are likely to be relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Residents evacuating their homes and seeking shelter\n4. Emergency responders rescuing people from flooded areas\n5. Debris and damaged buildings scattered across the affected regions",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact and aftermath of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Soulik. Given the severity of the typhoon, events that depict its powerful effects on the Korean Peninsula are most relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal areas and cities\n3. People evacuating their homes and seeking shelter\n4. Debris and destroyed buildings scattered across streets\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1032234901897015298",
"video_description": "일본 가고시마에 상륙한 태풍 솔릭 위력ㅠㅠㅠ 8월19일자",
"video_id": "1032234901897015298"
}
| 8
|
[
"The video captures a chaotic scene of a strong storm with heavy rain and strong winds, affecting the streets of Okinawa's main island, as indicated by the text overlay in Japanese. The visibility is low due to the intense weather conditions, with a car barely visible amidst the torrential rain. The text provides information about the storm's intensity and a specific time and location, suggesting a warning or update about the storm's impact.",
"The current frame continues to depict the chaotic scene of the strong storm in Okinawa's main island. Heavy rain and strong winds persist, further reducing visibility. A small yellow car is now more prominently seen, struggling to navigate through the wet and windy conditions. The text overlay in Japanese remains, reinforcing the storm's intensity and providing specific time and location details, which indicates the ongoing impact of the storm and the continuous updates about its severity.",
"The current frame continues to depict the chaotic scene of the strong storm in Okinawa's main island. Heavy rain and strong winds persist, further reducing visibility. A small yellow car is now more prominently seen, struggling to navigate through the wet and windy conditions. The text overlay in Japanese remains, reinforcing the storm's intensity and providing specific time and location details, which indicates the ongoing impact of the storm and the continuous updates about its severity.",
"The storm continues to impact Okinawa's main island, with strong winds and heavy rain persisting. A small yellow car remains visible, continuing to struggle through the challenging conditions. The text overlay in Japanese continues to emphasize the storm's intensity, providing further updates on its severity and impact.",
"The current frame shows a stormy scene with strong winds and heavy rain continuing to impact the area. A sign with Japanese text is partially visible, indicating the location. A graphic overlay on the lower right shows a map with a red circle marking the storm's location, indicating it's a severe storm with strong winds. The text in Japanese at the top suggests the storm has very strong power. There is no visible car in this frame, focusing on the storm's impact on the environment.",
"The scene continues to depict a stormy environment with strong winds and heavy rain, affecting the area. A vehicle is seen attempting to navigate through the stormy conditions, emphasizing the severity of the weather. The graphic overlay remains on the lower right, marking the storm's location with a red circle, reinforcing that it is a severe storm. The top text in Japanese reiterates the storm's strong power. The overall atmosphere remains tense, highlighting the ongoing impact of the storm.",
"The scene continues to depict a stormy environment with strong winds and heavy rain, affecting the area. A vehicle is seen attempting to navigate through the stormy conditions, emphasizing the severity of the weather. The graphic overlay remains on the lower right, marking the storm's location with a red circle, reinforcing that it is a severe storm. The top text in Japanese reiterates the storm's strong power. The overall atmosphere remains tense, highlighting the ongoing impact of the storm.",
"The video continues to show the severe weather conditions, with strong winds and heavy rain persisting. The scene remains stormy, and the vehicle is still navigating through the challenging environment, further highlighting the intensity of the storm. The graphic overlay in the lower right corner continues to indicate the storm's location with a red circle, stressing its severity. The top text in Japanese continues to emphasize the storm's powerful impact. The overall atmosphere remains tense, underscoring the ongoing effects of the storm."
] |
1032234901897015298
|
The video depicts a severe storm impacting Okinawa's main island, with heavy rain and strong winds causing low visibility and challenging conditions. A small yellow car is initially seen struggling to navigate through the storm, but it eventually disappears from view. The storm's intensity and location are emphasized through text overlays in Japanese, which provide updates on its severity and impact. A map graphic overlay marks the storm's location with a red circle, reinforcing its severity. Throughout the video, vehicles are seen attempting to navigate the stormy environment, highlighting the tense atmosphere and the ongoing effects of the storm. The overall context suggests a news update or warning about the storm's impact on the area.
|
Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.
|
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding in urban areas of the Korean Peninsula during Typhoon Soulik in 2012",
"Heavy rainfall causing flooding in urban areas of the Korean Peninsula during Typhoon Khanun in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Soulik in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Khanun in 2012"
] |
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities caused by Typhoon Soulik on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities due to Typhoon Khanun on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Soulik hit the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Khanun hit the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
[
"Strong winds from Typhoon Soulik blowing down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun blowing down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Soulik on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Khanun in the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Soulik on the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Khanun on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Soulik on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Khanun in the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EC%86%94%EB%A6%AD_(2018%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Soulik, it makes sense to extract events that are commonly associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and damage to infrastructure. These events are likely to be visualized in a video and are consistent with the characteristics of a powerful typhoon like Soulik.\n\nEVENTS:\n1. Strong winds blowing down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Debris flying through the air\n4. Roofs being torn off buildings\n5. Emergency responders evacuating people from flooded areas",
"en_article_excerpt": "Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Soulik_(2018)",
"event_category": "disasters",
"event_name": "typhoon_soulik",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to Typhoon Soulik, it makes sense to consider the typical consequences and scenes associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and resulting damage. Given the typhoon's impact on the Korean Peninsula, events related to severe weather, destruction, and potential evacuation or rescue efforts are likely to be relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Residents evacuating their homes and seeking shelter\n4. Emergency responders rescuing people from flooded areas\n5. Debris and damaged buildings scattered across the affected regions",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact and aftermath of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Soulik. Given the severity of the typhoon, events that depict its powerful effects on the Korean Peninsula are most relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal areas and cities\n3. People evacuating their homes and seeking shelter\n4. Debris and destroyed buildings scattered across streets\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://youtube.com/watch?v=_V6HiUPBShQ",
"video_description": "태풍 피해 전해드렸는데요, 이렇게 제주와 일부 내륙에 피해가 집중된 건 예보와 달리 솔릭의 위력이 급격히 떨어졌기 때문입니다. 시속 100km를 넘나드는 강풍과 비를 동반해 모두를 긴장시켰던 태풍이 왜 이렇게 빠르게 약해졌는지, 엄민재 기자가 전해드립니다. 뉴스 원문 기사 보기 https://news.sbs.co.kr/news/endPage.do?news_id=N1004904932 [태풍 '솔릭' 북상] 기사 더보기 https://news.sbs.co.kr/news/newsHotIssueList.do?tagId=10000046975 #SBS뉴스 #SBSNEWS #SBS_NEWS #에스비에스뉴스 #태풍_'솔릭'_북상 #8뉴스 ▶SBS 뉴스 채널 구독하기 : https://n.sbs.co.kr/youtube ▶SBS 뉴스 라이브 : https://n.sbs.co.kr/youtubeLive , https://n.sbs.co.kr/live ▶대한민국 뉴스리더 SBS◀ 홈페이지: https://n.sbs.co.kr 페이스북: https://www.facebook.com/sbs8news 트위터: https://www.twitter.com/sbs8news",
"video_id": "_V6HiUPBShQ"
}
| 8
|
[
"A news anchor stands in front of a weather map, presenting a segment about a rapidly intensifying typhoon. The map shows wind patterns, indicating the typhoon's trajectory and intensity. The text on the screen asks, \"Why is a typhoon intensifying rapidly?\"",
"The video shows a satellite image of two large typhoons, one located off the coast of China and the other near Japan. The typhoons are depicted with swirling cloud patterns and a clearly defined eye, indicating their significant strength and organization. The presence of multiple yellow outlines surrounding the typhoons likely indicates their paths or areas of impact. This frame appears to be from a weather forecast segment, with the SBS NEWS logo displayed, suggesting the footage is from a Korean television network. The image is used to visually explain the rapid intensification of the typhoons mentioned in the previous frame.",
"The video continues to show the satellite image of the two large typhoons, with one near China and the other near Japan. The typhoons are depicted with swirling cloud patterns and clearly defined eyes. The yellow outlines around the typhoons likely indicate their projected paths or areas of impact. The SBS NEWS logo is displayed, confirming the footage is from a Korean television network. The image is part of a weather forecast segment, visually explaining the rapid intensification of the typhoons mentioned previously.",
"The frame shows palm trees swaying vigorously, indicating strong winds, possibly due to the typhoons' approach. The sky is overcast, contributing to the dramatic atmosphere. The presence of the SBS NEWS logo suggests this footage is part of a news report detailing the impact of the rapidly intensifying typhoons on the region.",
"The current frame shows a wet, possibly flooded area with rain continuing to fall. In the background, there is a hillside or a body of water, suggesting the impact of the typhoons. There is a wooden fence and several lampposts visible, also affected by the weather conditions. The sky remains overcast, indicating that the storm is ongoing. The SBS NEWS logo is still present, reinforcing that this footage is part of a news report on the typhoon's effects. A photo of a man in a suit is superimposed in the upper right corner, possibly indicating an interviewee or subject related to the report.",
"The current frame presents a map of East Asia, with a focus on the region impacted by Typhoon 19. The typhoon is depicted as a swirling mass in the ocean near the Korean Peninsula and Japan. The map shows the movement path of the typhoon, suggesting its progression towards the Japanese archipelago. The SBS NEWS logo is visible, indicating that this is part of the news report. Text on the map provides information about the typhoon's rapid movement, likely addressing its speed and potential impact on the region. The visual elements aim to convey the typhoon's trajectory and its significance for the affected areas.",
"The scene shifts to a coastal area, presumably affected by Typhoon 19, showing several boats anchored in the water and a hazy sky, indicating overcast weather conditions. The SBS NEWS logo is visible, maintaining the news report's continuity. The text in the image, '급격히 힘 빠진 솔릭, 왜?' (Why is the typhoon rapidly losing strength?), suggests that the report is discussing the typhoon's weakening. The visual elements, including the boats and the overcast sky, provide context for the typhoon's impact on coastal regions.",
"The current frame continues to show the coastal area from the previous frame, with a focus on the water and anchored boats. The sky remains overcast, indicating the persistence of Typhoon 19's impact. There is no visible change in the weather or the position of the boats, suggesting the continuation of the news report on the typhoon's status. The text, '급격히 힘 빠진 솔릭, 왜?' (Why is the typhoon rapidly losing strength?), is still present, emphasizing the ongoing discussion about the typhoon's weakening. The presence of the SBS NEWS logo confirms that the report is still in progress."
] |
_V6HiUPBShQ
|
A news report from SBS NEWS discusses a rapidly intensifying typhoon, showing its trajectory and impact on regions near China and Japan through satellite images and weather maps. The typhoon's strength and organization are visually explained, with yellow outlines indicating its projected path or area of impact. As the report progresses, footage of palm trees swaying in strong winds and flooded areas with ongoing rain suggests the typhoon's effects on the region. The report includes interviews or discussions with subjects, such as a man in a suit, and provides updates on the typhoon's movement and potential impact on the Korean Peninsula and Japan. The typhoon, referred to as Typhoon 19, is later reported to be rapidly losing strength, with the report exploring the reasons behind this weakening. The footage shifts to a coastal area, showing anchored boats and overcast weather conditions, providing context for the typhoon's impact on coastal regions. Throughout the report, the SBS NEWS logo is consistently displayed, confirming the footage is part of a Korean television network's news segment on the typhoon's rapid intensification and subsequent weakening.
|
Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.
|
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding in urban areas of the Korean Peninsula during Typhoon Soulik in 2012",
"Heavy rainfall causing flooding in urban areas of the Korean Peninsula during Typhoon Khanun in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Soulik in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Khanun in 2012"
] |
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities caused by Typhoon Soulik on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities due to Typhoon Khanun on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Soulik hit the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Khanun hit the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
[
"Strong winds from Typhoon Soulik blowing down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun blowing down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Soulik on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Khanun in the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Soulik on the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Khanun on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Soulik on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Khanun in the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EC%86%94%EB%A6%AD_(2018%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Soulik, it makes sense to extract events that are commonly associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and damage to infrastructure. These events are likely to be visualized in a video and are consistent with the characteristics of a powerful typhoon like Soulik.\n\nEVENTS:\n1. Strong winds blowing down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Debris flying through the air\n4. Roofs being torn off buildings\n5. Emergency responders evacuating people from flooded areas",
"en_article_excerpt": "Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Soulik_(2018)",
"event_category": "disasters",
"event_name": "typhoon_soulik",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to Typhoon Soulik, it makes sense to consider the typical consequences and scenes associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and resulting damage. Given the typhoon's impact on the Korean Peninsula, events related to severe weather, destruction, and potential evacuation or rescue efforts are likely to be relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Residents evacuating their homes and seeking shelter\n4. Emergency responders rescuing people from flooded areas\n5. Debris and damaged buildings scattered across the affected regions",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact and aftermath of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Soulik. Given the severity of the typhoon, events that depict its powerful effects on the Korean Peninsula are most relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal areas and cities\n3. People evacuating their homes and seeking shelter\n4. Debris and destroyed buildings scattered across streets\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://youtube.com/watch?v=Aiq8I97bscw",
"video_description": "제19호 태풍 '솔릭'이 일본 남부 해상에서 한반도를 향해 북진하고 있습니다. '솔릭'은 강한 중형급 태풍으로 중심기압은 960hPa, 강풍 반경은 340㎞이라고 하는데요. 만일 태풍이 우리나라를 관통하면 2012년 9월 '산바' 이후 약 6년 만으로 큰 피해가 우려됩니다. 자세한 내용 영상으로 보시죠. ◆ 연합뉴스 홈페이지→ http://www.yna.co.kr/ ◆ 이 시각 많이 본 기사 → https://goo.gl/VQTsSZ ◆ 오늘의 핫뉴스 → https://goo.gl/WyGXpG ◆ 현장영상 → https://goo.gl/5aZcx8 ◆ 카드뉴스 →https://goo.gl/QKfDTH ◆연합뉴스 공식 SNS◆ ◇페이스북→ https://www.facebook.com/yonhap/ ▣ 연합뉴스 유튜브 채널 구독 : https://goo.gl/pL7TmT",
"video_id": "Aiq8I97bscw"
}
| 8
|
[
"The image is a weather map showing a low-pressure system's path and location over a period from August 16 to August 25. It highlights a low-pressure system (\"X LOW\") that originated near Japan and is projected to move towards the Korean Peninsula. The map includes timestamps and distances indicating the storm's progression and is accompanied by Korean text that discusses the movement of the storm system in relation to Japan and Korea. The text mentions that the system is currently moving towards the southeast and is expected to be near the southern part of Japan on the 20th at 9 AM.",
"The current frame depicts a severe weather scene, likely associated with a typhoon, as indicated by the Korean text on the image. The text reads, \"Sholik is a severe tropical typhoon, with a central pressure of 960hPa and a radius of 340km.\" The scene shows a heavily fogged and wind-blown street with several vehicles, some of which are overturned or displaced, suggesting strong winds and heavy rain. A large building in the background is also partially obscured by the dense fog, indicating the intensity of the storm. The overall context suggests that this frame is showing the immediate impact of Typhoon Sholik on the region, with the text providing details about its classification and strength.",
"The current frame shows a map with a trajectory path indicating the movement of a severe weather system, specifically a typhoon. The path is marked with several points labeled with dates, including \"24일,\" \"23일,\" \"22일,\" \"21일,\" and \"20일,\" suggesting the progression of the typhoon over time. The map indicates that the typhoon is currently traveling at a speed of 19km/h and is moving towards the southeast, with an expected shift to the south-southeast by the 22nd. The text further describes the typhoon's impact, noting that it will bring strong winds of 270km/h to the south-southeast region and potentially cause heavy rainfall on the 23rd. The map highlights the urgency and direction of the typhoon's path, emphasizing the need for preparedness and caution.",
"The current frame shows a scene of powerful waves crashing against rocky shores, indicating a severe storm or typhoon. The text \"연합뉴스\" and \"기상청 예보\" suggests this is a news segment from the Korea Meteorological Administration's forecast. The rough sea and turbulent waves emphasize the destructive impact of the weather system described in the previous frame, reinforcing the need for caution and preparedness.",
"The current frame continues to depict the powerful waves crashing against rocky shores, further illustrating the severity of the storm or typhoon. The text highlights that the strong waves and winds have the potential to cause damage up to 40 meters inland. This emphasizes the ongoing threat of the weather system, urging viewers to remain vigilant and take necessary precautions.",
"The current frame shows a series of vehicles navigating through a heavily flooded urban street during a downpour. The headlights of the cars are on, illuminating the wet road and emphasizing the challenging driving conditions. The text in the frame reads, \"Extreme rainfall is likely to occur,\" and advises viewers to \"take the utmost precautions.\" This underscores the ongoing threat of severe weather, highlighting the need for vigilance and caution among the public.",
"The current frame shows a weather phenomenon that appears to be a tornado funnel cloud twisting in the sky, with its base touching the ground, suggesting severe weather conditions. The text in the frame reads, \"If a tornado passes over us, it has been about six years since the 'Typhoon Sanba' in September 2012.\" This indicates a comparison to past extreme weather events, specifically a significant tornado incident related to Typhoon Sanba, and highlights the infrequency of such events, suggesting a recent recurrence after a six-year gap.",
"The current frame displays a logo for Yonhap News Agency, indicating the source of the news coverage. The logo is superimposed on a blurred background, suggesting a transition or a focus shift in the video, possibly from the tornado phenomenon to news reporting."
] |
Aiq8I97bscw
|
A severe weather event, identified as Typhoon Sholik, is depicted in the video, affecting areas near Japan and the Korean Peninsula from August 16 to August 25. The typhoon brings strong winds, heavy rainfall, and powerful waves, causing damage and disruption. The video shows the storm's progression, with a low-pressure system moving southeast, and later shifting to the south-southeast, bringing extreme weather conditions, including winds of up to 270km/h and heavy rainfall. The impact of the typhoon is illustrated through scenes of flooded streets, overturned vehicles, and powerful waves crashing against rocky shores, with warnings of potential damage up to 40 meters inland. The video also mentions the possibility of a tornado, comparing it to a past event, Typhoon Sanba in 2012, highlighting the severity and rarity of such weather phenomena. Throughout the video, news segments from the Korea Meteorological Administration and Yonhap News Agency provide updates and warnings, emphasizing the need for caution and preparedness among the public.
|
Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.
|
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding in urban areas of the Korean Peninsula during Typhoon Soulik in 2012",
"Heavy rainfall causing flooding in urban areas of the Korean Peninsula during Typhoon Khanun in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Soulik in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Khanun in 2012"
] |
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities caused by Typhoon Soulik on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities due to Typhoon Khanun on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Soulik hit the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Khanun hit the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
[
"Strong winds from Typhoon Soulik blowing down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun blowing down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Soulik on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Khanun in the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Soulik on the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Khanun on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Soulik on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Khanun in the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EC%86%94%EB%A6%AD_(2018%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Soulik, it makes sense to extract events that are commonly associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and damage to infrastructure. These events are likely to be visualized in a video and are consistent with the characteristics of a powerful typhoon like Soulik.\n\nEVENTS:\n1. Strong winds blowing down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Debris flying through the air\n4. Roofs being torn off buildings\n5. Emergency responders evacuating people from flooded areas",
"en_article_excerpt": "Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Soulik_(2018)",
"event_category": "disasters",
"event_name": "typhoon_soulik",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to Typhoon Soulik, it makes sense to consider the typical consequences and scenes associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and resulting damage. Given the typhoon's impact on the Korean Peninsula, events related to severe weather, destruction, and potential evacuation or rescue efforts are likely to be relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Residents evacuating their homes and seeking shelter\n4. Emergency responders rescuing people from flooded areas\n5. Debris and damaged buildings scattered across the affected regions",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact and aftermath of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Soulik. Given the severity of the typhoon, events that depict its powerful effects on the Korean Peninsula are most relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal areas and cities\n3. People evacuating their homes and seeking shelter\n4. Debris and destroyed buildings scattered across streets\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://youtube.com/watch?v=25LVZnXdx0A",
"video_description": "중부지방을 중심으로 연일 매섭게 비가 쏟아지고 있다. 긴급상황에 대비해야 할 소방서까지 침수된 모습이 SNS를 통해 전파되면서 불안이 가중되고 있다. 비도 이 정도면 재해 수준. 아무 일도 없다는 듯 태풍 솔릭은 지나갔지만, 오히려 비의 공포는 더해져만 가는데... 제작 : 박태호PD([email protected]) ▶ 기사 원문 : http://www.ytn.co.kr/_ln/0103_201808292100061801 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, [email protected], #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ [ 한국 뉴스 채널 와이티엔 / Korea News Channel YTN ]",
"video_id": "25LVZnXdx0A"
}
| 8
|
[
"The image shows a close-up of a person speaking. The individual appears to be wearing earrings and is slightly blurred. The setting and context are unclear. The logo \"YTN\" is visible in the top right corner, indicating that this is likely a clip from a news broadcast.",
"The current frame shows a flooded indoor space, likely a store, with water covering the floor. Clothing racks and items are visible, suggesting the area is used for retail. Large Korean text overlaid on the image reads \"워터파크를 연상시키는 이 곳은...?\" which translates to \"This place that reminds of a water park...?\". The logo \"YTN\" is present, indicating a continuation of the news broadcast.",
"The scene depicts a flooded outdoor area with several structures, including a makeshift shelter with a red tarp, partially submerged in water. The ground is covered with water, and debris is floating around, indicating a significant flood. The text \"받이 매몰되고...\" suggests the area is severely affected by the flood. The YTN logo indicates it is part of a news broadcast.",
"The scene shows a flooded indoor area with water up to a few inches high. A person stands at the doorway, seemingly observing the situation. The text \"침수 피해로 건물 물놀이행\" suggests the building is experiencing water damage and the occupants are engaging in activities like playing in the water. The YTN logo indicates it is part of a news broadcast.",
"In the current frame, a news reporter is standing outside on a road, holding a microphone and a smartphone. The text on the screen, \"신이시여, 설마 솔릭 무시해서 이리시나요?\" (\"Oh my God, did you really defy the rules and let this happen?\"), suggests that the reporter is discussing an incident or situation related to a bridge in the background. The overcast sky and the bridge in the distance provide context to the outdoor setting, which could be related to the earlier scene of the flooded building, indicating a possible connection to flooding or environmental issues.",
"The current frame shows a turbulent, muddy river with strong currents, indicating severe flooding. A stone wall and a metal fence are visible in the background, suggesting a riverbank or an area designed to prevent overflow. The text \"YTN\" in the top right corner indicates the source of the news footage. This frame likely continues the reporter's discussion on the environmental issues from the previous scene, now focusing on the flood's impact on the river and surrounding infrastructure.",
"The frame depicts a person holding an umbrella standing on a staircase as water rushes over the steps. The text \"오늘의 교훈\" and \"자나 코나 물 조심\" translates to \"Today's lesson\" and \"Be careful of water, anytime, anywhere,\" respectively. This suggests the footage is from a news segment highlighting the dangers of flooding. The large waves and muddy water in the background reinforce the severe flood conditions, emphasizing the need for caution.",
"The current frame shows a black screen with white Korean text. The text reads \"알림\" which translates to \"Notification\" or \"Alert.\" This indicates that the news segment is providing an important update or warning related to the previous flooding event. The stark contrast between the black background and white text emphasizes the urgency of the message."
] |
25LVZnXdx0A
|
The video appears to be a news broadcast from YTN, covering a severe flooding event. The footage shows various locations, including flooded stores, outdoor areas, and rivers, with people navigating through the water and debris. A news reporter is seen discussing the situation, and text overlays provide context, highlighting the extent of the damage and the need for caution. The broadcast includes warnings and lessons learned from the flooding, emphasizing the importance of being prepared and aware of the dangers of water. The overall context suggests a significant environmental incident, possibly related to heavy rainfall or a natural disaster, affecting various areas and infrastructure.
|
Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.
|
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding in urban areas of the Korean Peninsula during Typhoon Soulik in 2012",
"Heavy rainfall causing flooding in urban areas of the Korean Peninsula during Typhoon Khanun in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Soulik in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Khanun in 2012"
] |
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities caused by Typhoon Soulik on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities due to Typhoon Khanun on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Soulik hit the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Khanun hit the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
[
"Strong winds from Typhoon Soulik blowing down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun blowing down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Soulik on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Khanun in the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Soulik on the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Khanun on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Soulik on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Khanun in the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EC%86%94%EB%A6%AD_(2018%EB%85%84)",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Soulik, it makes sense to extract events that are commonly associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and damage to infrastructure. These events are likely to be visualized in a video and are consistent with the characteristics of a powerful typhoon like Soulik.\n\nEVENTS:\n1. Strong winds blowing down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Debris flying through the air\n4. Roofs being torn off buildings\n5. Emergency responders evacuating people from flooded areas",
"en_article_excerpt": "Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Soulik_(2018)",
"event_category": "disasters",
"event_name": "typhoon_soulik",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to Typhoon Soulik, it makes sense to consider the typical consequences and scenes associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and resulting damage. Given the typhoon's impact on the Korean Peninsula, events related to severe weather, destruction, and potential evacuation or rescue efforts are likely to be relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Residents evacuating their homes and seeking shelter\n4. Emergency responders rescuing people from flooded areas\n5. Debris and damaged buildings scattered across the affected regions",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact and aftermath of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Soulik. Given the severity of the typhoon, events that depict its powerful effects on the Korean Peninsula are most relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal areas and cities\n3. People evacuating their homes and seeking shelter\n4. Debris and destroyed buildings scattered across streets\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://youtube.com/watch?v=BRxOTPDR0g4",
"video_description": "건물 공사 구조물이 무너지고 교회 첨탑과 호텔 지붕도 강풍에 날려 추락했습니다. 아름드리 가로수는 뿌리째 뽑혔습니다. 지난 2010년 태풍 곤파스가 몰고 온 강풍의 위력입니다. 전남 홍도에 초속 42.9m의 폭풍이 불었고 태안 38.1m, 군산 33.6m, 서울도 21.6m의 강풍이 기록됐습니다. 바람 태풍 곤파스로 6명이 숨지고 11명이 부상했으며, 1,673억 원의 재산 피해가 발생했습니다. 북상하는 19호 태풍 '솔릭'은 8년 전 '곤파스'와 비슷한 경로로 움직이고 있습니다. 내일 새벽, 제주도 서쪽을 거쳐 서해안을 따라 북상한 뒤 태안반도에 상륙해 수도권을 통과할 것으로 예상됩니다. 한반도 주변 수온이 28도 정도로 무척 높아, 곤파스보다 강한 세력을 유지한 채 북상할 가능성이 큽니다. 기상청은 태풍 '솔릭'으로 인해 목요일과 금요일 사이 전국에 최고 400mm의 폭우가 쏟아지고 초속 40m가 넘는 강풍이 불 것으로 전망했습니다. 취재기자 : 정혜윤 영상편집 : 연진영 자막뉴스 제작 : 육지혜 에디터 ▶ 기사 원문 : http://www.ytn.co.kr/_ln/0108_201808220940500446 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, [email protected], #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ [ 한국 뉴스 채널 와이티엔 / Korea News Channel YTN ]",
"video_id": "BRxOTPDR0g4"
}
| 8
|
[
"A large tree has fallen on a road, blocking vehicles. People in orange safety vests are standing near a fire truck, possibly assessing the situation. The scene appears to be in an urban area with parked cars on the side of the road. The text indicates an event in Arumidori, Japan.",
"The video shows a map of South Korea with wind speed indicators for various cities. The wind speed for Seoul is 21.6 m/s, for Daegu it's 38.1 m/s, and for Jeonnam Hongdo, it's 42.9 m/s. The text indicates strong winds impacting these locations. The scene suggests a weather-related event being reported.",
"The video displays a screen with Korean text summarizing a 2010 bar wind disaster 'gunpass,' listing six deaths, eleven injuries, and property damage amounting to 1.673 billion won. The scene illustrates the aftermath of the event.",
"The video shows a rough seascape through a rain-streaked window, indicating ongoing adverse weather conditions. The text in Korean provides context about a typhoon named 'Solrick' that is affecting the area, stating that it has moved 8 years after the previous event called 'Gonpass,' likely referencing the 2010 bar wind disaster.",
"The map illustrates the projected path of Typhoon 'Solrick' with marked dates and times showing its progression. The timeline begins with '22일 오후' (afternoon of the 22nd), followed by '23일 새벽' (early morning of the 23rd), and '23일 오후' (afternoon of the 23rd), indicating the typhoon's movement towards the Korean Peninsula. The text emphasizes that it will impact '태안반도에 상륙해 수도권을 통과할 것으로 예상됩니다' (it is expected to land on Taean Peninsula and pass through the metropolitan area).",
"The current frame shows a large fishing boat in rough seas with thick fog, emphasizing the severe weather conditions caused by the typhoon. The boat's position and the text on the screen highlight the dangers posed by the storm, noting that the waves are exceptionally high, surpassing those of a typhoon, and possess a powerful force, making it impossible for boats to navigate safely.",
"The current frame depicts a rainy scene on a street, with palm trees visible against an overcast sky. Water droplets are seen on the camera lens, indicating ongoing heavy rainfall. The text on the screen, written in Korean, reads \"전국에 최고 400mm의 폭우가 쏟아지고 초속 40m가 넘는 강풍이 불 것으로 전망했습니다.\" which translates to \"Heavy rains of up to 400mm are expected to pour across the country, with winds exceeding 40m/s.\" This suggests a severe weather warning for extreme rain and wind conditions.",
"In the current frame, the scene continues to depict a stormy atmosphere on a street, with palm trees still visible against the now darker, more ominous sky. The camera lens is still covered with water droplets, indicating the persistent heavy rainfall. The text on the screen remains in Korean and reads \"전국에 최고 400mm의 폭우가 쏟아지고 초속 40m가 넘는 강풍이 불 것으로 전망했습니다.\" translating to \"Heavy rains of up to 400mm are expected to pour across the country, with winds exceeding 40m/s.\" This reinforces the severe weather warning for extreme rain and wind conditions. The environment appears more turbulent, with the palm trees swaying more vigorously and the rain appearing denser, emphasizing the escalating severity of the storm."
] |
BRxOTPDR0g4
|
A severe typhoon, named 'Solrick', is impacting the Korean Peninsula, particularly the Taean Peninsula and the metropolitan area, bringing with it strong winds and heavy rainfall. The storm's approach and effects are being reported, with comparisons made to a previous 2010 bar wind disaster, 'Gonpass', which caused significant damage and loss of life. The video shows the typhoon's projected path, rough seas, and turbulent weather conditions, including exceptionally high waves and powerful winds that make navigation impossible for boats. On land, the storm brings heavy rains of up to 400mm and winds exceeding 40m/s, causing trees to sway violently and posing a significant threat to the area. The video also references an unrelated incident in Arumidori, Japan, where a large tree has fallen on a road, but the primary focus is on the typhoon's impact in South Korea.
|
The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.
|
[
"Strong winds blowing sand and dust across the Eastern Gobi desert steppe during the sandstorm on March 14, 2021",
"Reduced visibility on roads and highways due to heavy sand and dust in the air during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"People wearing masks and protective gear to shield themselves from the massive sandstorm that hit the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and other parts of East Asia on 14 March 2021",
"Sand and dust accumulating on buildings, streets, and vehicles during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"Flights and daily activities being disrupted due to a sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, and Korean Peninsula on March 14, 2021"
] |
[
"People wearing masks walking in low visibility conditions during a sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on 14 March 2021",
"Cars driving with headlights on during the day due to reduced visibility caused by the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on March 14, 2021",
"Sandstorm reducing visibility in urban areas of the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"Flights grounded or delayed due to sandstorm in East Asia on March 14, 2021",
"Residents sealing windows and doors to prevent sand entry during the 14 March 2021 sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia"
] |
[
"Sandstorm reducing visibility on roads and highways in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"People wearing masks to protect themselves from the sandstorm in East Asia on March 14, 2021",
"Trees and buildings covered in dust and sand during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on 14 March 2021",
"Cars and buses driving slowly due to low visibility during a sandstorm in the Eastern Gobi desert or East Asia on March 14 2021",
"Residents cleaning up sand and dust from streets and homes after the 14 March 2021 sandstorm in East Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%99%A9%EC%82%AC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects and progression of the sandstorm, such as reduced visibility, dust in the air, and people protecting themselves from the storm. These events are likely to be visualized in a video associated with the query, given the geographical scope and impact of the sandstorm.\n\nEVENTS:\n1. Dust and sand reducing visibility on roads and highways\n2. People wearing masks to protect themselves from the sandstorm\n3. Trees and buildings covered in dust and sand\n4. Cars and buses driving slowly due to low visibility\n5. Residents cleaning up sand and dust from streets and homes",
"en_article_excerpt": "The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2021_East_Asia_sandstorm",
"event_category": "disasters",
"event_name": "2021_sandstorm",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the 2021 East Asia sandstorm, it makes sense to consider the typical visual consequences of a large-scale sandstorm, such as reduced visibility, strong winds, and massive amounts of dust and sand particles in the air. Events that could be visualized in a video would likely involve the storm's impact on the environment and daily life, rather than abstract or behind-the-scenes occurrences.\n\nEVENTS:\n1. Strong winds blowing sand and dust across the Eastern Gobi desert steppe\n2. Reduced visibility on roads and highways due to heavy sand and dust in the air\n3. People wearing masks and protective gear to shield themselves from the storm\n4. Sand and dust accumulating on buildings, streets, and vehicles\n5. Flights and daily activities being disrupted due to poor weather conditions",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2021 East Asia sandstorm, it makes sense to extract events that are directly related to the effects and progression of the sandstorm, such as reduced visibility, transportation disruptions, and daily life impacts. These events should be concrete and visual, allowing them to be reasonably captioned in a video frame associated with the query.\n\nEVENTS:\n1. People wearing masks walking in low visibility conditions\n2. Cars driving with headlights on during the day due to reduced visibility\n3. Sandstorm reducing visibility in urban areas\n4. Flights being grounded or delayed at airports\n5. Residents sealing windows and doors to prevent sand entry",
"video_URL": "http://youtube.com/watch?v=Yddr-IKR_KA",
"video_description": "중국 둔황에 초대형 모래폭풍이 불어닥치면서눈 깜짝할 사이에 도시 전체가 암흑으로 뒤덮었습니다. [Ch.19] 사실을 보고 진실을 말합니다. 👍🏻 공식 홈페이지 http://news.tvchosun.com/ 👍🏻 공식 페이스북 https://www.facebook.com/tvchosunnews/ 👍🏻 공식 트위터 https://twitter.com/TVChosunNews * 뉴스제보 : 이메일([email protected]), 카카오톡(tv조선제보), 전화(1661-0190)",
"video_id": "Yddr-IKR_KA"
}
| 8
|
[
"A man in a suit and tie is sitting in a news studio, likely hosting or presenting a news program. The background features a large screen with the numbers \"24\" and text in Korean, suggesting the program is titled '시선 24' (Sisan 24), which typically means 'Focus 24' in Korean. The man appears to be speaking or about to speak, with a laptop in front of him.",
"The current frame depicts a large dust cloud or sandstorm approaching a city with multiple high-rise buildings. The environment appears urban with roads, vehicles, and commercial establishments visible. The sky is filled with a thick, brownish cloud, indicating the severity of the dust storm. There is no clear sign of the news studio or presenter from the previous frame, suggesting a shift in focus from the news studio to this weather event. The text in the top left corner reads '도심 깊은 모래폭풍 피해 규모는?' which translates to 'What is the extent of the damage from the deep sandstorm in the city center?' This suggests the news segment is covering the impact of the sandstorm on the city.",
"The current frame continues to focus on the severe dust storm, showing a dense, orange-hued cloud that obscures the view of the city. The text '도심 깊은 모래폭풍 피해 규모는?' (What is the extent of the damage from the deep sandstorm in the city center?) remains visible, maintaining the context of reporting on the storm's impact. The scene now features more natural elements, with trees and possibly a lake or river in the foreground, suggesting the storm's reach extends beyond urban areas. There is a slight visibility of structures in the distance, indicating the storm's significant visual impact.",
"The frame shows a misty, low-visibility environment likely caused by the dust storm, with an unclear view of buildings in the background. The text '도심 깊은 모래폭풍 피해 규모는?' (What is the extent of the damage from the deep sandstorm in the city center?) continues to inform on the storm's impact, now with '中 도심 흩쓴 초대형 모래폭풍' (A massive sandstorm spread in the central city) providing further context. The scene underscores the storm's severity and its extensive reach, including urban areas, with the text indicating the initial report of the storm's significant presence in the city center.",
"The current frame shows a news anchor reporting from a studio. Behind her, a split screen displays a misty, low-visibility scene, likely due to the dust storm, with the text '도심 깊은 모래폭풍 피해 규모는?' (What is the extent of the damage from the deep sandstorm in the city center?) and '中 도심 흩쓴 초대형 모래폭풍' (A massive sandstorm spread in the central city) indicating the ongoing coverage of the storm's impact. The text at the bottom of the screen '높이 100m 모래폭풍' (A sandstorm reaching 100 meters high) highlights the severity of the dust storm.",
"The current frame continues to show the news anchor reporting from a studio. Behind her, the split screen now shows a road scene with extremely low visibility due to the dust storm, with the text '도심 깊은 모래폭풍 피해 규모는?' (What is the extent of the damage from the deep sandstorm in the city center?) still present. The text at the bottom of the screen '고속도로 뒤친 모래폭풍과 먼지구름' (Sandstorm and dust clouds on the highway) indicates that the news coverage is still focused on the ongoing effects of the storm, particularly its impact on highway visibility.",
"The news anchor continues to report from the studio. The split screen now displays a scene of a dusty environment, likely due to the sandstorm. The text at the top of the screen, '도심 깊은 모래폭풍 피해 규모는?' (What is the extent of the damage from the deep sandstorm in the city center?), remains unchanged, indicating that the news coverage is still focused on assessing the damage caused by the sandstorm. The bottom text '고속도로 뒤친 모래폭풍과 먼지구름' (Sandstorm and dust clouds on the highway) continues to highlight the impact on highway visibility.",
"The news anchor continues to report from the studio, maintaining the focus on the sandstorm's impact. The split screen now displays an image of a dusty environment, with a visible dust cloud affecting visibility. The text at the top of the screen, '도심 깊은 모래폭풍 피해 규모는?' (What is the extent of the damage from the deep sandstorm in the city center?), remains the same, indicating the ongoing coverage of the sandstorm's effects. The bottom text '고속도로 뒤친 모래폭풍과 먼지구름' (Sandstorm and dust clouds on the highway) is still present, emphasizing the highway conditions affected by the storm."
] |
Yddr-IKR_KA
|
A news program titled '시선 24' (Focus 24) covers a severe dust storm hitting a city, causing low visibility and significant damage. The program, hosted by a news anchor in a studio, features footage of the storm's impact on the city, including high-rise buildings, roads, and natural areas. The storm is described as a massive sandstorm that has spread throughout the central city, reaching 100 meters high and affecting highway visibility. The news coverage focuses on assessing the extent of the damage caused by the deep sandstorm in the city center, with the anchor providing updates and footage of the storm's effects on the city and its infrastructure.
|
The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.
|
[
"Strong winds blowing sand and dust across the Eastern Gobi desert steppe during the sandstorm on March 14, 2021",
"Reduced visibility on roads and highways due to heavy sand and dust in the air during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"People wearing masks and protective gear to shield themselves from the massive sandstorm that hit the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and other parts of East Asia on 14 March 2021",
"Sand and dust accumulating on buildings, streets, and vehicles during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"Flights and daily activities being disrupted due to a sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, and Korean Peninsula on March 14, 2021"
] |
[
"People wearing masks walking in low visibility conditions during a sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on 14 March 2021",
"Cars driving with headlights on during the day due to reduced visibility caused by the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on March 14, 2021",
"Sandstorm reducing visibility in urban areas of the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"Flights grounded or delayed due to sandstorm in East Asia on March 14, 2021",
"Residents sealing windows and doors to prevent sand entry during the 14 March 2021 sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia"
] |
[
"Sandstorm reducing visibility on roads and highways in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"People wearing masks to protect themselves from the sandstorm in East Asia on March 14, 2021",
"Trees and buildings covered in dust and sand during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on 14 March 2021",
"Cars and buses driving slowly due to low visibility during a sandstorm in the Eastern Gobi desert or East Asia on March 14 2021",
"Residents cleaning up sand and dust from streets and homes after the 14 March 2021 sandstorm in East Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%99%A9%EC%82%AC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects and progression of the sandstorm, such as reduced visibility, dust in the air, and people protecting themselves from the storm. These events are likely to be visualized in a video associated with the query, given the geographical scope and impact of the sandstorm.\n\nEVENTS:\n1. Dust and sand reducing visibility on roads and highways\n2. People wearing masks to protect themselves from the sandstorm\n3. Trees and buildings covered in dust and sand\n4. Cars and buses driving slowly due to low visibility\n5. Residents cleaning up sand and dust from streets and homes",
"en_article_excerpt": "The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2021_East_Asia_sandstorm",
"event_category": "disasters",
"event_name": "2021_sandstorm",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the 2021 East Asia sandstorm, it makes sense to consider the typical visual consequences of a large-scale sandstorm, such as reduced visibility, strong winds, and massive amounts of dust and sand particles in the air. Events that could be visualized in a video would likely involve the storm's impact on the environment and daily life, rather than abstract or behind-the-scenes occurrences.\n\nEVENTS:\n1. Strong winds blowing sand and dust across the Eastern Gobi desert steppe\n2. Reduced visibility on roads and highways due to heavy sand and dust in the air\n3. People wearing masks and protective gear to shield themselves from the storm\n4. Sand and dust accumulating on buildings, streets, and vehicles\n5. Flights and daily activities being disrupted due to poor weather conditions",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2021 East Asia sandstorm, it makes sense to extract events that are directly related to the effects and progression of the sandstorm, such as reduced visibility, transportation disruptions, and daily life impacts. These events should be concrete and visual, allowing them to be reasonably captioned in a video frame associated with the query.\n\nEVENTS:\n1. People wearing masks walking in low visibility conditions\n2. Cars driving with headlights on during the day due to reduced visibility\n3. Sandstorm reducing visibility in urban areas\n4. Flights being grounded or delayed at airports\n5. Residents sealing windows and doors to prevent sand entry",
"video_URL": "http://youtube.com/watch?v=3BbP2OHdePY",
"video_description": "뿌연 하루였습니다. 몽골에서 시작된 모래폭풍이 중국을 거쳐 한반도에 상륙한 건데, 내일은 전국에서 황사가루가 섞인 '흙비'까지 내릴 전망입니다. [Ch.19] 사실을 보고 진실을 말합니다. 👍🏻 공식 홈페이지 http://news.tvchosun.com/ 👍🏻 공식 페이스북 https://www.facebook.com/tvchosunnews/ 👍🏻 공식 트위터 https://twitter.com/TVChosunNews * 뉴스제보 : 이메일([email protected]), 카카오톡(tv조선제보), 전화(1661-0190)",
"video_id": "3BbP2OHdePY"
}
| 8
|
[
"A news anchor stands in front of a large screen displaying a scene with smoke or dust, suggesting a recent event or incident. The text on the screen reads \"중 상킨 황사...내일 흑비로 내린다,\" which translates to \"Severe yellow dust...tomorrow, it will rain black.\" The broadcast appears to be from TV Chosun, and the time shown is 21:27. Additional text at the bottom provides information about various topics being covered in the news segment.",
"The scene shifts to a street view engulfed in a thick, yellow haze, indicating severe dust or sandstorm conditions. Buildings line the street, and the visibility is significantly reduced due to the dust. A car is seen on the road, and the sky appears overcast with the yellow dust dominating the atmosphere. The text \"내일 흑비 내린다\" is displayed, which means \"Tomorrow, it will rain black,\" emphasizing the severity of the upcoming weather conditions. The broadcast remains from TV Chosun at 21:27, continuing the coverage of the dust storm.",
"The current frame depicts a wide view of a cityscape, where a river flows through the center. A red bridge spans across the river, connecting the two sides of the city. The background shows a skyline with various buildings, and the scene is enveloped in a grayish haze, indicating ongoing dust or sandstorm conditions. The text \"내일 흑비 내린다\" is displayed again, reinforcing the message about the upcoming severe weather. Additionally, the broadcast time remains at 21:27 from TV Chosun, and the news ticker at the bottom includes information about BTS's record-breaking achievement and a selection of 100 companies with significant influence in the U.S. market.",
"The current frame depicts a wide view of a cityscape with a green-domed building in the foreground, surrounded by modern high-rise buildings. The sky appears overcast, suggesting ongoing weather conditions. Text at the top indicates \"내일 흑비 내린다\" (Tomorrow, there will be a heavy rain). At the bottom, the news ticker reads \"중국발 황사, 백령도 상륙한 뒤 서쪽 지역으로 확대\" (Dust from China, after landing on Baekryeong Island, spreads to western regions) and mentions the time as 21:28 on TV Chosun. The scene appears to be part of a news broadcast providing updates on weather and related events.",
"In the current frame, a man wearing a face mask and a dark jacket stands in front of a taxi on a busy urban street, engaging in an interview. The background shows multiple vehicles, including a white SUV, traveling on the road. The setting suggests a city environment, with a GS25 convenience store visible in the background, indicating a commercial area. Text at the bottom of the screen reads \"김동길 | 택시기사\" (Kim Donggil | Taxi driver) and \"미세먼지에다가 황사까지 있으니까 계속 먼지가 쌓여서 뒤야야 돼요.\" which translates to \"Due to fine dust and yellow dust, the dust continues to accumulate, so I have to clean it.\" This frame appears to be a segment within the news broadcast, focusing on the impact of pollution and weather conditions on daily life, specifically for a taxi driver.",
"The video frames depict a news broadcast covering a weather-related issue in a city. The current frame shows a busy urban street with multiple vehicles, including a taxi, moving on a wet road, likely due to recent or ongoing rainfall. A person on a scooter is also visible in the street. The environment suggests a commercial area, with buildings and signage in the background. A news anchor appears in an inset, providing information or commentary related to the weather conditions. Text at the bottom of the screen reads \"김수진 | 기상청 예보분석관\" (Kim Soo-jin | Weather Forecast Analyst) and \"북쪽으로부터 남하한 한 공기가 인해 대기가 매우 불안정해지면서 전국 곳곳에 비가 내리겠다고, 신생활 '페페저축행' 외국인 선수 1순위로 바로가 짐명.\" This translates to \"A cold air mass from the north will cause instability in the atmosphere, leading to rain in many areas across the country.\" The news segment appears to be focused on weather updates and their impact on daily life.",
"The video frames depict a news broadcast covering a weather-related issue in a city. The current frame shows a lush, green tree canopy in an urban setting, likely indicating a park or green area within the city. The environment suggests a contrast to the previous frame, which showed a busy urban street with vehicles. The news anchor appears in an inset, likely continuing to provide information or commentary related to the weather conditions. Text at the bottom of the screen reads \"스포츠 레알 마드리드, UCL 4강 홈경기에서 첼시와 1-1 무승부\" (Sports: Real Madrid, UCL Quarterfinal Home Game, Draw with Chelsea 1-1). This text suggests a shift in the news segment to sports updates, specifically mentioning a soccer match result. The overall focus of the news segment appears to be on both weather updates and sports news.",
"The video frames depict a news broadcast covering a weather-related issue in a city. The current frame shows a lush, green tree canopy in an urban setting, likely indicating a park or green area within the city. The environment suggests a contrast to the previous frame, which showed a busy urban street with vehicles. The news anchor appears in an inset, likely continuing to provide information or commentary related to the weather conditions. Text at the bottom of the screen reads \"스포츠 레알 마드리드, UCL 4강 홈경기에서 첼시와 1-1 무승부\" (Sports: Real Madrid, UCL Quarterfinal Home Game, Draw with Chelsea 1-1). This text suggests a shift in the news segment to sports updates, specifically mentioning a soccer match result. The overall focus of the news segment appears to be on both weather updates and sports news."
] |
3BbP2OHdePY
|
A news broadcast on TV Chosun covers a severe weather event, specifically a yellow dust storm affecting a city, with predictions of heavy rain to follow. The broadcast shows scenes of the city engulfed in a thick, yellow haze, reducing visibility, and later, a shift to rainy conditions. The news anchor provides updates and commentary, with interviews from individuals such as a taxi driver, who discusses the impact of the dust and fine dust on his daily work. A weather forecast analyst also appears, explaining the cause of the unstable weather conditions. The broadcast includes a news ticker with various topics, including the spread of dust from China and its effects on the region. The segment also briefly shifts to sports news, covering a soccer match result. Overall, the video depicts a news broadcast focusing on weather updates, their impact on daily life, and other current events.
|
The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.
|
[
"Strong winds blowing sand and dust across the Eastern Gobi desert steppe during the sandstorm on March 14, 2021",
"Reduced visibility on roads and highways due to heavy sand and dust in the air during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"People wearing masks and protective gear to shield themselves from the massive sandstorm that hit the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and other parts of East Asia on 14 March 2021",
"Sand and dust accumulating on buildings, streets, and vehicles during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"Flights and daily activities being disrupted due to a sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, and Korean Peninsula on March 14, 2021"
] |
[
"People wearing masks walking in low visibility conditions during a sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on 14 March 2021",
"Cars driving with headlights on during the day due to reduced visibility caused by the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on March 14, 2021",
"Sandstorm reducing visibility in urban areas of the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"Flights grounded or delayed due to sandstorm in East Asia on March 14, 2021",
"Residents sealing windows and doors to prevent sand entry during the 14 March 2021 sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia"
] |
[
"Sandstorm reducing visibility on roads and highways in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"People wearing masks to protect themselves from the sandstorm in East Asia on March 14, 2021",
"Trees and buildings covered in dust and sand during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on 14 March 2021",
"Cars and buses driving slowly due to low visibility during a sandstorm in the Eastern Gobi desert or East Asia on March 14 2021",
"Residents cleaning up sand and dust from streets and homes after the 14 March 2021 sandstorm in East Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%99%A9%EC%82%AC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects and progression of the sandstorm, such as reduced visibility, dust in the air, and people protecting themselves from the storm. These events are likely to be visualized in a video associated with the query, given the geographical scope and impact of the sandstorm.\n\nEVENTS:\n1. Dust and sand reducing visibility on roads and highways\n2. People wearing masks to protect themselves from the sandstorm\n3. Trees and buildings covered in dust and sand\n4. Cars and buses driving slowly due to low visibility\n5. Residents cleaning up sand and dust from streets and homes",
"en_article_excerpt": "The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2021_East_Asia_sandstorm",
"event_category": "disasters",
"event_name": "2021_sandstorm",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the 2021 East Asia sandstorm, it makes sense to consider the typical visual consequences of a large-scale sandstorm, such as reduced visibility, strong winds, and massive amounts of dust and sand particles in the air. Events that could be visualized in a video would likely involve the storm's impact on the environment and daily life, rather than abstract or behind-the-scenes occurrences.\n\nEVENTS:\n1. Strong winds blowing sand and dust across the Eastern Gobi desert steppe\n2. Reduced visibility on roads and highways due to heavy sand and dust in the air\n3. People wearing masks and protective gear to shield themselves from the storm\n4. Sand and dust accumulating on buildings, streets, and vehicles\n5. Flights and daily activities being disrupted due to poor weather conditions",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2021 East Asia sandstorm, it makes sense to extract events that are directly related to the effects and progression of the sandstorm, such as reduced visibility, transportation disruptions, and daily life impacts. These events should be concrete and visual, allowing them to be reasonably captioned in a video frame associated with the query.\n\nEVENTS:\n1. People wearing masks walking in low visibility conditions\n2. Cars driving with headlights on during the day due to reduced visibility\n3. Sandstorm reducing visibility in urban areas\n4. Flights being grounded or delayed at airports\n5. Residents sealing windows and doors to prevent sand entry",
"video_URL": "http://youtube.com/watch?v=6sLn3wHQvCQ",
"video_description": "초대형 모래폭풍에 산사태까지…재난영화 방불케한 순간 포착 (서울=연합뉴스) 중국 북서부 간쑤성에서 초대형 모래폭풍이 도시를 집어삼키고 산사태로 엄청난 흙더미가 쓰나미처럼 쏟아져 내리는 등 흡사 재난 영화의 한 장면 같은 순간들이 카메라에 포착됐습니다. 지난 25일 간쑤성 과저우현에서는 높이 수십 미터에 달하는 거대한 모래폭풍이 도시를 덮쳤습니다. 모래폭풍은 마치 거대한 모래 장벽 같은 모습이었습니다. 모래폭풍이 시야를 가리고 해를 가리면서 일대는 오렌지색으로 물들었습니다. 가시거리가 50m 미만, 공기 질이 최악 수준으로 내려앉으면서 대기오염 최고단계인 황색경보가 발령됐습니다. 한편 같은 날 간쑤성 룽난시에서는 산사태가 발생했습니다. 산 중턱의 한 부분에서부터 흙더미와 나무가 쓰나미처럼 산 아래로 쏟아져 내리면서 도로에 있던 관광객 수십 명이 비명을 지르며 도망쳤습니다. 이날 산사태로 차량 한 대가 파손됐지만 인명 피해는 없었다고 합니다. 영상으로 보시죠. 제작 : 김건태·안창주 영상 : 로이터 #연합뉴스 #중국 #황사 ◆ 연합뉴스 유튜브 : https://www.youtube.com/yonhap ◆ 연합뉴스 홈페이지→ http://www.yna.co.kr/ ◆ 연합뉴스 페이스북→ https://www.facebook.com/yonhap/ ◆ 연합뉴스 인스타 : https://goo.gl/UbqiQb ◆ 연합뉴스 비디오메타 채널https://www.youtube.com/channel/UCTMCrbtHU0M0SR6TuBrL4Pw",
"video_id": "6sLn3wHQvCQ"
}
| 8
|
[
"A large dust cloud is seen billowing over a row of multi-story residential buildings. The text in the image reads \"순식간에 밀려와\" and \"연합뉴스\", indicating a news report about the sudden arrival of a dust storm.",
"The large dust cloud continues to spread over a densely populated area, obscuring the buildings and sky. The text in the image reads \"시커멓고 거대한\", suggesting that the dust storm is now more intense and darker.",
"The dust cloud continues to spread over the densely populated area, now more intense and darker. The text in the image reads \"쓰나미처럼 도시를 한순간에 집어삼키다,\" suggesting that the dust storm is now rapidly engulfing the city.",
"The dust storm continues to intensify, creating a heavily obscured environment. Buildings in the background are barely visible through the dense, swirling dust. The Korean text \"공기질은 최악\" indicates that the air quality has reached its worst point, emphasizing the severity of the situation.",
"The current frame shows a scene of a severe dust storm, with thick, swirling clouds of dust dominating the sky and ground. Trees are partially obscured by the dust, emphasizing the density and intensity of the storm. The text \"연합뉴스\" is visible, indicating the source of the footage. The context suggests the continued impact of the dust storm, with the environment heavily affected and visibility significantly reduced. The ongoing severe weather conditions are highlighted, continuing from the previous frame's description of deteriorating air quality.",
"The current frame depicts a severe dust storm with thick, swirling clouds of dust dominating the scene. The text \"연합뉴스\" is visible, indicating the source of the footage. The dense dust reduces visibility, and trees are partially obscured, emphasizing the intensity of the storm. Several individuals wearing protective masks are seen in the lower part of the frame, suggesting efforts to shield themselves from the dust. The text \"(초미세먼지 비상저감조치)\" translates to \"Urgent reduction measures for ultrafine dust,\" indicating the severity of the air quality situation. The scene underscores the environmental impact and public health concerns arising from the ongoing dust storm.",
"The current frame depicts a severe dust storm with thick, swirling clouds of dust dominating the scene. The text \"연합뉴스\" is visible, indicating the source of the footage. The dense dust reduces visibility, and trees are partially obscured, emphasizing the intensity of the storm. Several individuals wearing protective masks are seen in the lower part of the frame, suggesting efforts to shield themselves from the dust. The text \"(초미세먼지 비상저감조치)\" translates to \"Urgent reduction measures for ultrafine dust,\" indicating the severity of the air quality situation. The scene underscores the environmental impact and public health concerns arising from the ongoing dust storm.",
"The current frame continues the theme of the dust storm with the text \"구독하기\" visible, which means \"Subscribe\" in English. It features an animated character pointing upwards, indicating a call to action for viewers to subscribe. The Yonhap News Agency logo is also present, reinforcing the source of the video. The character is shown with a speech bubble that reads \"구독 꼭-옥!\", translating to \"Please definitely subscribe!\" This suggests an encouragement for viewers to follow the news outlet's channel for updates on environmental and health issues related to the dust storm."
] |
6sLn3wHQvCQ
|
A severe dust storm suddenly hits a densely populated area, engulfing the city and causing extremely poor air quality. The storm intensifies, reducing visibility and prompting individuals to wear protective masks to shield themselves from the dust. As the storm continues, the air quality reaches its worst point, with ultrafine dust levels prompting urgent reduction measures. The situation underscores significant environmental and public health concerns. The footage is presented by Yonhap News Agency, concluding with a call to action to subscribe for further updates on the situation.
|
The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.
|
[
"Strong winds blowing sand and dust across the Eastern Gobi desert steppe during the sandstorm on March 14, 2021",
"Reduced visibility on roads and highways due to heavy sand and dust in the air during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"People wearing masks and protective gear to shield themselves from the massive sandstorm that hit the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and other parts of East Asia on 14 March 2021",
"Sand and dust accumulating on buildings, streets, and vehicles during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"Flights and daily activities being disrupted due to a sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, and Korean Peninsula on March 14, 2021"
] |
[
"People wearing masks walking in low visibility conditions during a sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on 14 March 2021",
"Cars driving with headlights on during the day due to reduced visibility caused by the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on March 14, 2021",
"Sandstorm reducing visibility in urban areas of the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"Flights grounded or delayed due to sandstorm in East Asia on March 14, 2021",
"Residents sealing windows and doors to prevent sand entry during the 14 March 2021 sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia"
] |
[
"Sandstorm reducing visibility on roads and highways in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"People wearing masks to protect themselves from the sandstorm in East Asia on March 14, 2021",
"Trees and buildings covered in dust and sand during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on 14 March 2021",
"Cars and buses driving slowly due to low visibility during a sandstorm in the Eastern Gobi desert or East Asia on March 14 2021",
"Residents cleaning up sand and dust from streets and homes after the 14 March 2021 sandstorm in East Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%99%A9%EC%82%AC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects and progression of the sandstorm, such as reduced visibility, dust in the air, and people protecting themselves from the storm. These events are likely to be visualized in a video associated with the query, given the geographical scope and impact of the sandstorm.\n\nEVENTS:\n1. Dust and sand reducing visibility on roads and highways\n2. People wearing masks to protect themselves from the sandstorm\n3. Trees and buildings covered in dust and sand\n4. Cars and buses driving slowly due to low visibility\n5. Residents cleaning up sand and dust from streets and homes",
"en_article_excerpt": "The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2021_East_Asia_sandstorm",
"event_category": "disasters",
"event_name": "2021_sandstorm",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the 2021 East Asia sandstorm, it makes sense to consider the typical visual consequences of a large-scale sandstorm, such as reduced visibility, strong winds, and massive amounts of dust and sand particles in the air. Events that could be visualized in a video would likely involve the storm's impact on the environment and daily life, rather than abstract or behind-the-scenes occurrences.\n\nEVENTS:\n1. Strong winds blowing sand and dust across the Eastern Gobi desert steppe\n2. Reduced visibility on roads and highways due to heavy sand and dust in the air\n3. People wearing masks and protective gear to shield themselves from the storm\n4. Sand and dust accumulating on buildings, streets, and vehicles\n5. Flights and daily activities being disrupted due to poor weather conditions",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2021 East Asia sandstorm, it makes sense to extract events that are directly related to the effects and progression of the sandstorm, such as reduced visibility, transportation disruptions, and daily life impacts. These events should be concrete and visual, allowing them to be reasonably captioned in a video frame associated with the query.\n\nEVENTS:\n1. People wearing masks walking in low visibility conditions\n2. Cars driving with headlights on during the day due to reduced visibility\n3. Sandstorm reducing visibility in urban areas\n4. Flights being grounded or delayed at airports\n5. Residents sealing windows and doors to prevent sand entry",
"video_URL": "http://youtube.com/watch?v=qaan1wMGnN0",
"video_description": "거대한 '모래 폭풍'이 하늘을 뒤덮었습니다. 지난 주말 몽골의 건조한 초원에서 발원한 '황사 바람'입니다. 태풍급 강풍을 동반한 모래 먼지가 한적한 작은 마을을 집어삼킬 듯한 기세입니다. 초원은 물론이고 주변 도시들도 앞을 분간하기 어려운 먼지 속에 갇혔습니다. '황색 폭풍'의 습격으로 몽골 초원지대 유목민 약 600명이 한때 실종됐습니다. 다행히 대부분 살아서 돌아왔지만 5살 어린 아이 를 포함해 10여 명은 결국 숨졌습니다. 최고 풍속 초속 30m가 넘는 모래 폭풍에 10층 높이의 철탑도 맥없이 부러졌습니다. 인근 지역 주민들은 모래 바람의 공포 속에, 정전 까지 돼 암흑과 추위에 떨었습니다. 몽골 초원과 가까운 중국 북쪽 네이멍구에서는 모래가 섞인 눈보라가 몰아쳤습니다. 강풍에 밀려온 모래와 눈이 민가를 뒤덮으면서 집안에 갇히는 주민들도 속출했습니다. 경찰 대여섯 명이 삽과 수레로 눈 모래를 걷어낸 지 2시간 만에 71살 할머니가 구조되기도 했습니다. 이번 황사는 강한 바람이 모래 먼지를 멀리까지 실어나르면서 '10년 만의 황사'로 강해졌습니다. 특히 몽골 초원의 봄풀이 아직 자라기 전이어서 흙먼지가 많았다고 중국 기상 당국은 분석했습니다. 황사로 뒤덮였던 베이징에는 다시 맑은 날씨가 찾아왔습니다. 강한 바람 때문에 모래 먼지는 하루 만에 사라졌 는데, 이번 봄에 황사가 몇 차례 더 예보가 돼있는 상황입니다. 취재기자 : 강성웅 촬영편집 : 고광 자막뉴스 : 윤현경 ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0134_202103170936125411 ▶ 제보 하기 : https://mj.ytn.co.kr/mj/mj_write.php ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN & YTN plus 무단 전재 및 재배포금지",
"video_id": "qaan1wMGnN0"
}
| 8
|
[
"The image shows a news broadcast from YTN with Korean text at the top reading '자막뉴스' (Subtitled News) and 'WORLD'. The main focus is on a large cloud of dust or smoke in the background, with buildings visible below. Korean text at the bottom provides further information, but the context of the news segment is not clear from the image alone.",
"The image shows a continuation of the YTN news broadcast, with the same Korean text '자막뉴스' (Subtitled News) and 'WORLD' at the top. The main focus now appears to be on a barbed wire fence, with the background still obscured by dust or smoke. At the bottom, there is Korean text that reads: '황색 폭풍의 습격으로 몽골 초원지대 유목민 약 600명이 한때 실종됐습니다,' which translates to 'Due to the yellow storm's attack, about 600 nomads in the Mongolian grasslands were once missing.' This text suggests that the news segment is covering a specific incident related to a yellow storm and its impact on nomadic communities in Mongolia.",
"The video shows a continuation of the YTN news broadcast, with the same Korean text '자막뉴스' (Subtitled News) and 'WORLD' at the top. The main focus is on a large amount of smoke or dust, indicating a possible wildfire or dust storm. The Korean text at the bottom reads: '최고 평속 초속 30m가 넘는 모래 폭풍에 10층 높이의 철탑도 맥없이 부러졌습니다,' which translates to 'Due to the sandstorm with speeds exceeding 30 meters per second, even a 10-story high steel tower collapsed.' This text suggests that the news segment is covering the severe impact of a sandstorm in Mongolia.",
"The video continues with the YTN news broadcast, maintaining the same Korean text '자막뉴스' (Subtitled News) and 'WORLD' at the top. The scene depicts an area affected by fog or smoke, with visibility significantly reduced. The Korean text at the bottom reads: '몽골 초원과 가까운 중국 북쪽 네이밍구에서는 모래가 섞인 눈보라가 몰아쳤습니다,' which translates to 'In Neimenggu, close to the Mongolian grasslands and northern China, a sandstorm with snow has hit.' This indicates that the news segment is detailing the severe impact of a sandstorm mixed with snow in the region.",
"The video continues with the YTN news broadcast, maintaining the same Korean text '자막뉴스' (Subtitled News) and 'WORLD' at the top. The scene depicts an area affected by fog or smoke, with visibility significantly reduced. The Korean text at the bottom reads: '경찰 대여섯 명이 산과 수레로 눈 쌓인 모래를 걷어낸 지 2시간 만에 71살 할머니가 구조되었습니다,' which translates to 'Police and about five people used shovels and carts to clear snow-covered sand, and after 2 hours, a 71-year-old grandmother was rescued.' This indicates that the news segment is detailing the rescue efforts of a person affected by the sandstorm mixed with snow in the region.",
"The video shows a continuation of the YTN news broadcast with the same Korean text '자막뉴스' (Subtitled News) and 'WORLD' at the top. The scene depicts an area affected by a sandstorm, with reduced visibility. The Korean text at the bottom reads: '이번 화사는 강한 바람이 모래를 몰아올리면서 '10년 만의 화사'로 강해졌습니다,' which translates to 'This sandstorm became 'the strongest sandstorm in 10 years' due to strong winds blowing sand.' This suggests the news segment is highlighting the intensity of the current sandstorm in the region.",
"In the current frame, a news anchor is reporting from a location where the sandstorm has subsided, indicated by the Korean text at the bottom of the screen: '황사로 뒤덮였던 베이징에는 다시 많은 날씨가 찾아왔습니다,' which translates to 'Beijing, which was covered in sandstorm, has seen the return of clear skies.' The anchor, wearing a suit and holding a YTN microphone, is standing in an urban area with buildings and trees in the background, suggesting the city is returning to normalcy after the storm. The red lanterns suggest a cultural or festive setting, possibly near a traditional area or during a holiday season.",
"The news anchor continues reporting from the same location, emphasizing the clear skies in Beijing after the sandstorm, as indicated by the Korean text at the bottom of the screen: '황사로 뒤덮였던 베이징에는 다시 많은 날씨가 찾아왔습니다,' which translates to 'Beijing, which was covered in sandstorm, has seen the return of clear skies.' The anchor, still wearing a suit and holding a YTN microphone, stands in the urban area with buildings and trees in the background. The red lanterns remain visible, indicating the cultural or festive setting that persists in the scene."
] |
qaan1wMGnN0
|
A severe sandstorm, referred to as a "yellow storm," hit the Mongolian grasslands and northern China, causing widespread destruction and reducing visibility. The storm, which was the strongest in 10 years, resulted in approximately 600 nomads being reported missing. The sandstorm was intense, with winds exceeding 30 meters per second, causing a 10-story steel tower to collapse. The storm also brought snow, further complicating rescue efforts. However, rescue operations were successful in some cases, with a 71-year-old grandmother being rescued after police and volunteers cleared snow-covered sand. The storm eventually subsided, and clear skies returned to Beijing, with the city returning to normalcy. The news segment, broadcast on YTN, provided updates on the storm's impact and the subsequent rescue efforts, highlighting the severity of the natural disaster and its effects on the region.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://youtube.com/watch?v=0ZROpcl5nUE",
"video_description": "열기가 식을 새도 없이 계속 쌓여만 가고 있습니다. 폭염 특보도 확대, 강화되고 있는데요. 오늘 오전 11시를 기해 경기 남부와 강원 영서 남부에도 폭염경보가 내려졌고, 전국 대부분 지역으로 폭염주의보가 확대됐습니다. 현재 경북 경주 기온이 36.6도로 전국에서 가장 뜨겁고요. 대구 36.4도, 서울도 32.9도까지 올라 올해 최고 기온을 기록할 것으로 보입니다. 밤에도 열기는 쉽게 식지 못하고 열대야로 이어지는 곳이 많겠는데요. 내일 서울의 아침 기온 24도, 대구 25도로 오늘 밤사이에도 더위로 잠 못 이루는 곳이 많겠고요. 낮에는 다시 서울 기온이 33도, 대구 37도까지 오르는 등 오늘과 비슷하겠습니다. 현재 전국에 맑은 하늘이 드러나 있는데요. 내일도 종일 쾌청한 하늘이 함께 하겠지만, 강한 자외선에는 주의하셔야겠습니다. 당분간 뚜렷한 비 소식 없이 낮에는 폭염이, 밤에는 열대야가 기승을 부리겠습니다. 지금까지 날씨 정보였습니다. ▶ 기사 원문 : http://www.ytn.co.kr/_ln/0108_201807151449122225 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, [email protected], #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ [ 한국 뉴스 채널 와이티엔 / Korea News Channel YTN ]",
"video_id": "0ZROpcl5nUE"
}
| 8
|
[
"The image shows a news broadcast with a female presenter standing on a beach backdrop. She is dressed in a pink dress and appears to be delivering a weather report. A weather map with different regions shaded in red and orange is displayed on the left side of the screen, indicating varying levels of a weather condition. Below the map, there is a small graphic of a sun with sunglasses and the text \"폭염특보\" (Heatwave Warning). The text at the bottom of the map reads \"폭염주의보\" (Heat Advisory) and \"폭염경보\" (Heatwave Warning). In the bottom right corner, there is a small inset of a man in a suit, who appears to be a news anchor or commentator.",
"The image shows the same news broadcast with the female presenter still standing on a beach backdrop. The weather map and graphic with the sun and text \"폭염특보\" (Heatwave Warning) remain on the left side of the screen. The text \"폭염주의보\" (Heat Advisory) and \"폭염경보\" (Heatwave Warning) are still visible below the map. The man in the suit in the bottom right corner is still present, suggesting ongoing commentary or news discussion. The woman appears to continue delivering the weather report, with no significant change in her position or the elements displayed on the screen.",
"The image shows the news broadcast with the female presenter still standing on a beach backdrop. The weather map and graphic with the sun and text \"폭염특보\" (Heatwave Warning) are still on the left side of the screen, displaying current temperatures across various regions. The text \"폭염주의보\" (Heat Advisory) and \"폭염경보\" (Heatwave Warning) are still visible below the map. The man in the suit in the bottom right corner is still present, suggesting ongoing commentary or news discussion. The woman appears to continue delivering the weather report, with no significant change in her position or the elements displayed on the screen.",
"The image continues to depict the news broadcast with the female presenter still standing on a beach backdrop. The weather map and graphic on the left side of the screen are no longer visible. Instead, there is now a graphic displaying temperatures for Seoul and the capital region with text \"내일도 폭염 계속\" (Heatwave Continues Tomorrow) and \"방사이 열대야\" (Hot Night). The temperatures are shown as 24°C for Seoul and 25°C for the capital region during the day and 33°C for Seoul and 37°C for the capital region at night. The man in the suit in the bottom right corner remains present, suggesting ongoing commentary or news discussion. The woman appears to continue delivering the weather report, with no significant change in her position or the elements displayed on the screen.",
"The current frame continues to depict the news broadcast with the female presenter standing on the same beach backdrop. The weather graphic on the left side of the screen remains, displaying temperatures for Seoul and the capital region with text \"내일도 폭염 계속\" (Heatwave Continues Tomorrow) and \"방사이 열대야\" (Hot Night). The temperatures are shown as 24°C for Seoul and 25°C for the capital region during the day and 33°C for Seoul and 37°C for the capital region at night. The man in the suit in the bottom right corner remains present, suggesting ongoing commentary or news discussion. The woman appears to be delivering the weather report, with no significant change in her position or the elements displayed on the screen.",
"The female presenter is standing in front of a weather map backdrop, presenting a weather forecast. The map shows cloud formations and geographical outlines of various regions. The presenter appears to be delivering information about the weather, likely continuing the theme of the previous weather reports. The man in the suit in the bottom right corner remains present, indicating ongoing commentary or news discussion.",
"The female presenter continues to stand in front of the weather map backdrop, maintaining her role in presenting the weather forecast. The map now includes specific weather icons, such as rain and sunny symbols, along with temperatures in certain regions. The presenter appears to be discussing detailed weather conditions, likely focusing on upcoming weather patterns and regional differences. The man in the suit remains in the bottom right corner, suggesting his continued involvement in providing additional commentary or insights on the weather report.",
"The female presenter continues her weather report in front of the backdrop, which now displays a weather forecast for the upcoming week in Seoul, with temperatures in Celsius. The weather icons indicate sunny conditions with the possibility of rain on some days. She is likely detailing the forecast, discussing temperature fluctuations and expected weather conditions. The man in the suit remains in the bottom right corner, continuing to provide additional commentary or insights on the weather report."
] |
0ZROpcl5nUE
|
A female news presenter delivers a weather report on a news broadcast, standing in front of a beach backdrop initially, and later in front of a weather map. The report focuses on a heatwave warning, with graphics displaying temperatures and warnings such as "폭염특보" (Heatwave Warning) and "폭염주의보" (Heat Advisory). The presenter discusses the ongoing heatwave, mentioning that it will continue the next day, with high temperatures during the day and hot nights. The temperatures for Seoul and the capital region are specifically highlighted. As the report progresses, the presenter provides a detailed weather forecast for the upcoming week, including expected temperatures and weather conditions. Throughout the report, a man in a suit appears in the bottom right corner, providing additional commentary or insights. The overall context is a news broadcast focusing on weather updates, specifically addressing the heatwave and its expected continuation.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://youtube.com/watch?v=-HJV2kcDUAA",
"video_description": "서울 기온이 39도를 넘어 관측 사상 최고 기록을 갈아치운 1일 오후 서울 지하철역에서는 전력에 과부하가 걸려 스크린도어에 이상이 생겼다. 서울교통공사에 따르면 이날 오후 2시 39분께 지하철 4호선 동작역에서 당고개 방향 승강장 안전문(스크린도어)이 작동하지 않는 현상이 발생했다. 공사 측은 \"가정에서 전력에 이상이 생기면 화재 등 사고를 예방하기 위해 두꺼비집(누전차단기)이 내려가듯이, 승강장 쪽 전력에서 같은 작용이 일어난 것\"이라고 설명했다. 동작역 스크린도어는 오후 5시 30분 현재도 열려있는 상태로, 승강장에는 안전요원이 배치돼 만일의 사고에 대비하고 있다. 스크린도어가 개방된 상태일 뿐, 열차 운행에는 지장이 없는 상황이다. 공사 관계자는 \"밤에 운행을 마친 뒤에 정확한 원인을 조사할 방침\"이라면서 \"고온으로 인해 일부 부품에 문제가 생겼을 가능성도 염두에 두고 있다\"고 말했다. 영상취재 - [연합뉴스TV 차영우] ◆ 연합뉴스 홈페이지→ http://www.yna.co.kr/ ◆ 이 시각 많이 본 기사 → https://goo.gl/VQTsSZ ◆ 오늘의 핫뉴스 → https://goo.gl/WyGXpG ◆ 현장영상 → https://goo.gl/5aZcx8 ◆ 카드뉴스 →https://goo.gl/QKfDTH ◆연합뉴스 공식 SNS◆ ◇페이스북→ https://www.facebook.com/yonhap/ ▣ 연합뉴스 유튜브 채널 구독 : https://goo.gl/pL7TmT",
"video_id": "-HJV2kcDUAA"
}
| 8
|
[
"The image shows a train station where people are walking on the platform. A train is visible in the background with a man and woman walking past the train door. A sign above the platform reads \"Transfer\" in English and Korean, indicating it's a transfer station. The image also contains text at the bottom that reads \"동작역 스크린도어 고장... '고온 때문에일 가능성이 있음'\" which translates to \"Screen door malfunction at Dongjak Station... 'It is possible due to high temperature'.\"",
"The image shows a train station platform where a train is stopped with its doors open. Passengers are visible through the open train doors. A sign above the platform reads \"Transfer\" in English and Korean.",
"The current frame shows a train station platform with the train's doors still open. The \"Transfer\" sign remains visible above the platform. A sign warns passengers to \"Watch your step\" as they board or disembark from the train.",
"The video shows a close-up view of an elevator control panel, focusing on the buttons and wires.",
"The scene shifts to a bustling subway station platform, where a modern train has just stopped. The train doors are open, and several passengers are boarding or disembarking. The platform is well-lit and clean, with a digital sign above displaying train schedules and other relevant information in Korean. The overhead sign reads '연합뉴스,' indicating the location or service provider. The atmosphere is orderly, with passengers moving smoothly, some walking briskly, others standing and waiting. The train's sleek metallic exterior and the station's organized layout reflect the efficiency and modernity of public transportation in this area.",
"The current frame shows a close-up of the control panel inside a subway train. The panel features two prominent lights: a red indicator labeled '제역림' (Emergency) and a yellow indicator labeled '장애' (Obstruction). The lights are encased in metallic frames with ridged edges for grip. The panel also includes a metallic switch to the right. The digital sign above the lights displays '연합뉴스' (Yonhap News), indicating the presence of a news channel or system within the train. The overall setting suggests a focus on safety and operational controls within the train's interior.",
"The current frame depicts a subway station platform. Several individuals are standing on the platform, waiting for the train. The platform is equipped with safety features such as tactile paving along the edge. A closed glass barrier separates the waiting area from the tracks. The digital sign above the tracks displays '연합뉴스' (Yonhap News), indicating the ongoing news broadcast within the station. The overall setting suggests a typical scene of passengers at a subway station.",
"The scene continues to show the subway station platform. The individuals are still present, waiting patiently. The platform's tactile paving remains visible, ensuring safety for visually impaired passengers. The closed glass barrier is prominent, providing a secure separation between the waiting area and the tracks. The digital sign above the tracks still displays '연합뉴스' (Yonhap News), maintaining the context of the news broadcast. The overall atmosphere remains calm and typical for a subway station."
] |
-HJV2kcDUAA
|
The video depicts a series of scenes at a subway station, likely in South Korea, given the presence of Korean text and signs. The event begins with a train stopped at a transfer station, indicated by signs reading "Transfer" in English and Korean, where passengers are boarding and disembarking. A malfunctioning screen door is mentioned, possibly due to high temperature. The scene then shifts to a bustling subway platform where a modern train has stopped, and passengers are moving in an orderly manner. The video also shows close-up views of a train's control panel, highlighting safety features such as emergency and obstruction indicators. The setting is one of efficiency and modernity, with digital signs displaying train schedules, news from "Yonhap News," and safety measures like tactile paving and glass barriers to protect passengers. Throughout the video, the atmosphere remains calm and typical for a subway station, with passengers waiting and moving about. The focus is on the functionality, safety, and daily operation of the subway system.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://youtube.com/watch?v=MZR5vPcBcI4",
"video_description": "극한 폭염속에도 경남 밀양 얼음골에선 주먹만한 얼음 기둥이 관측됐습니다. 신기한 건 이례적인 더위 속에서도 이 얼음이 평년보다 더 오랫동안, 꽁꽁 얼어있다는건데요. 어떻게 된 일일까요. 최진석 기자가 소개합니다. [리포트] 경남 밀양 재약산 해발 600m. 불볕더위에 바깥 온도는 36도를 넘어섰지만 바위 사이로 시원한 바람이 나옵니다. 바위 안쪽 온도를 재보니 서늘한 가을 기온인 9.2도. 바위 틈엔 주먹만한 얼음 기둥까지 있습니다. 이 지역의 명소이자 천연기념물 224호인 얼음골입니다. 불볕더위에 지친 사람들은 시원한 바람이 신기하기만 합니다. [이미경/부산광역시 북구 : \"여기까지 올라오는데 참 많이 힘들었는데, 너무 선선한 바람이 부니까 너무 너무 좋아요.\"] 바위 틈에서는 에어컨을 틀어놓은 것처럼 차가운 자연 바람이 나오고 있습니다. 열화상카메라로 온도를 재보니 1도밖에 되지 않습니다. 이곳의 얼음은 보통 장마철인 6,7월이면 다 녹아 없어지지만 올해는 계속되는 폭염의 상황에도 더 꽁꽁 얼어붙은 채 남아있습니다. [변희룡/부경대 지구환경과학과 명예교수 : \"10여 년 관측했는데, 올해 얼음이 가장 오래 관측됐거든요. 장마철에 비가 많이 오면씻겨지는데 장마철에 비가 많이 안왔어요.\"] 기록적인 폭염 속에 더위를 식히려 지난달에만 2만 여명이 찾은 밀양 얼음골. 신비로운 비밀을 간직한 채 더위에 지친 이들의 색다른 피서지가 되고 있습니다. KBS 뉴스 최진석입니다.",
"video_id": "MZR5vPcBcI4"
}
| 8
|
[
"The video depicts a female news anchor presenting a news report. In the background, there is footage of a natural scene with a metal fence and a body of water. The anchor is standing in a studio, and there is visible Korean text at the bottom of the screen.",
"The current frame shows a news broadcast with a focus on a bright, sunlit sky with some clouds. The text at the top left of the screen reads \"일음골, 폭염에 더 '꽁꽁'\", indicating a news story about the area of Il-eum-gol, experiencing extreme cold despite the heatwave. At the bottom of the screen, there is another line of Korean text that reads \"경남 밀양시 산내면\", suggesting the location of the story is Mil-yang City, Gyeongnam Province, in the San-nae area. The overall atmosphere is calm and serene, contrasting with the news about extreme cold.",
"The current frame shows a group of people gathered on a wooden platform in a wooded area. They are standing behind a metal railing and appear to be observing something below, possibly related to the news story about extreme cold in the area of Il-eum-gol. The people are dressed in casual clothing and some are wearing hats or sunglasses, suggesting it is a sunny day. The background shows a rocky landscape with a staircase leading down to a lower level. The overall atmosphere is one of curiosity and interest, as the group seems to be focusing on something of interest.",
"In the current frame, the group of people has moved to a different location within the wooded area. They are now standing in front of a rocky area with a metal railing, suggesting that they are on a lookout or viewing point. The individuals are still dressed in casual clothing, with some wearing hats or sunglasses, indicating that the sunny weather persists. The background features a rocky landscape with sparse vegetation, and the group appears to be engaged in a conversation or interview, as one person is holding a microphone with the KBS logo, suggesting that this is a news segment. The text at the top of the image reads \"일음골, 폭염에 더 '꽁꽁'\" which translates to \"Il-eum-gol, even colder in the heat,\" indicating that despite the hot weather, the area remains cold, possibly due to the altitude or the location being a valley. The overall atmosphere is one of curiosity and interest as the group discusses the unique climatic conditions of the area.",
"In the current frame, the man in white is crouching down near the rocky area with the metal railing, and he appears to be examining something closely on the ground. He is wearing a white shirt and dark pants, and the background still features the rocky landscape with sparse vegetation. The text at the top of the image reads \"일음골, 폭염에 더 '꽁꽁'\" which translates to \"Il-eum-gol, even colder in the heat,\" indicating that the area remains cold despite the hot weather. The man is holding a notepad and pen, suggesting that he might be taking notes or conducting an interview. The overall atmosphere remains one of curiosity and interest as the man investigates the unique conditions of the area.",
"The current frame shows a close-up of a small icy stream or gushing water coming from a rocky crevice. The water is flowing rapidly, and the surrounding rocks are covered in moss and other vegetation. There is a large icy formation or ice sheet in the foreground, partially blocking the stream's path. The text at the top of the image, \"일음골, 폭염에 더 '꽁꽁'\" translates to \"Il-eum-gol, even colder in the heat,\" indicating that the area remains cold despite the hot weather. The overall atmosphere is one of curiosity and interest as the man investigates the unique conditions of the area, observing the icy stream and the surrounding environment.",
"The current frame shows a group of people gathered around a rocky stream, with some individuals sitting and others standing. They appear to be exploring and interacting with the stream, which is surrounded by dense greenery and trees. The overall atmosphere seems to be one of curiosity and interest as the group investigates the unique conditions of the area, similar to the previous frame's focus on the icy stream and surrounding environment.",
"The current frame captures a close-up view of an icy formation within a rocky stream. The ice is clear and appears to be flowing or dripping from an overhang, indicating a cold environment. The surrounding rocks are wet and show signs of moss, suggesting a damp and possibly humid area. This continues the theme from the previous frames, focusing on the natural and unique conditions of the icy stream and its surroundings."
] |
MZR5vPcBcI4
|
A news report is being presented by a female anchor about the area of Il-eum-gol in Mil-yang City, Gyeongnam Province, which is experiencing extreme cold despite a heatwave. The report features footage of a group of people, including a news team with a microphone from KBS, visiting the area and observing the unique climatic conditions. They are shown standing on a wooden platform, at a lookout point, and near a rocky stream, where they investigate and interact with the environment. The stream has icy formations and is surrounded by dense greenery, indicating a cold and humid microclimate. Throughout the report, the group's curiosity and interest in the area's unusual conditions are evident as they examine the icy stream, take notes, and conduct interviews. The overall context is a news segment aiming to inform viewers about this unusual natural phenomenon in Il-eum-gol.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://youtube.com/watch?v=HCV2Hx8B0-c",
"video_description": "8월의 첫날인 오늘 최악의 폭염이 이어졌습니다. 오늘 얼마나 더웠는지 기온만 봐도 알 수가 있는데요. 강원도 홍천은 낮 기온 41도, 서울 39.6도까지 오르면서 기상 관측 이래 가장 높은 기온을 기록했습니다. 내일도 극심한 폭염은 계속됩니다. 해안가를 제외하고는 전국이 낮 기온 35도를 넘어서면서 뜨겁겠습니다. 서울과 춘천 39도, 대전과 대구는 38도까지 오르면서 오늘만큼 덥겠습니다. 토요일부터는 기온이 조금 내려가겠지만 낮 기온 35도 안팎으로 찜통더위는 이어집니다. 절기상 입추인 다음 주 화요일에도 낮 기온 35도로 무덥겠습니다. 현재 경기와 충남, 전북에는 오존주의보가 발효 중입니다. 내일도 전국이 맑겠고 자외선이 강해서 오존 농도가 높아질 수 있겠는데요. 중부와 전북 지역에서는 오존을 주의하셔야겠습니다. 아침 기온은 서울 29도로 밤 사이에도 무덥겠습니다. 한낮에는 광주 37도, 부산 35도로 오늘만큼 덥겠습니다. 바다의 물결은 제주해상에서 최고 4미터까지 거세게 일겠습니다. 더위가 밤낮을 가리지 않는 만큼 온열 질환에 걸리지 않도록 건강 관리를 잘해주시기 바랍니다. 날씨정보 전해드렸습니다.",
"video_id": "HCV2Hx8B0-c"
}
| 8
|
[
"The image depicts a weather forecast presenter standing in front of a graphical weather chart. The chart shows temperature trends over a period, with red and orange lines indicating high and low temperatures, respectively. The presenter appears to be explaining the forecast, with the text \"당분간 더위는 이어져\" (The heat will continue for a while) displayed on the chart, indicating a continuation of warm weather. The background shows a cityscape with tall buildings and a clear sky.",
"The weather forecast presenter continues to present in front of the graphical weather chart, which now also displays additional text \"서울, °C\" (Seoul, °C), indicating the specific location and temperature unit. The presenter is still explaining the forecast, likely discussing the upcoming weather conditions for Seoul. The background remains consistent with a cityscape and clear sky.",
"The weather forecast presenter is still presenting in front of the graphical weather chart, which now shows specific temperatures and labels such as \"낮\" (daytime) and \"아침\" (morning), likely detailing the temperature ranges for those periods. The presenter points to the chart, likely elaborating on the forecast, while the cityscape background and clear sky remain consistent.",
"The weather forecast presenter is continuing to present in front of the graphical weather chart, which still displays specific temperatures and labels such as \"낮\" (daytime) and \"아침\" (morning). The presenter is no longer pointing to the chart but appears to be speaking, likely elaborating on the forecast. The cityscape background and clear sky remain consistent.",
"The weather forecast presenter is now standing and appears to be speaking, likely continuing to elaborate on the forecast shown in the graphical chart. The cityscape background and clear sky remain consistent with the previous frames.",
"The weather forecast presenter is continuing her report, standing in front of a graphical chart displaying a temperature trend over time. The chart shows a gradual decline in temperature, with specific values highlighted. The presenter appears engaged in her delivery, using hand gestures to emphasize the information. The cityscape and clear sky in the background provide a consistent visual context.",
"The weather forecast presenter is continuing her report, standing in front of a graphical chart displaying a temperature trend over time. The chart shows a gradual decline in temperature, with specific values highlighted. The presenter appears engaged in her delivery, using hand gestures to emphasize the information. The cityscape and clear sky in the background provide a consistent visual context.",
"The weather forecast presenter is still engaged in her report, now standing in front of a graphical chart displaying a temperature trend over time. She continues to use hand gestures to emphasize the information. The cityscape and clear sky in the background remain consistent with the previous frame."
] |
HCV2Hx8B0-c
|
A weather forecast presenter delivers a report in front of a graphical weather chart, discussing the continuation of warm weather in Seoul. The presenter explains the forecast, pointing to the chart and using hand gestures to emphasize temperature trends over time, including daytime and morning temperatures. The presentation takes place in a studio with a cityscape and clear sky visible in the background, providing a consistent visual context throughout the report. The forecast indicates a gradual decline in temperature, with the presenter elaborating on the details and emphasizing key points.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://youtube.com/watch?v=XYrtvA02lKc",
"video_description": "경기도 분당에서 폭염으로 수도 배관이 파열되면서 교량의 균열이 발생해 교통이 통제되고 있습니다. 어젯밤(29일) 10시쯤 경기도 성남시 분당구에 있는 길이 25m, 폭 20m인 야탑 10교에 설치된 수도 배관이 터지면서 물이 치솟았습니다. 이 사고로 교각이 왼쪽으로 15도 정도 기울었고 도로 일부에도 균열이 생겼습니다. 경찰은 사고가 나자 야탑교 사거리부터 탑골 사거리까지 440m 구간 차량 통행을 전면 통제했습니다. 사고 당시 다리 위를 지나던 차량이 많지 않아 별다른 피해는 없었습니다. 경기 분당경찰서는 노후화된 교각이 폭염 영향으로 팽창하면서 짓눌린 수도관이 터져 물이 치솟은 것으로 추정된다고 설명했습니다. 최기성 [[email protected]] ▶ 기사 원문 : http://www.ytn.co.kr/_ln/0103_201807300822376551 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, [email protected], #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ [ 한국 뉴스 채널 와이티엔 / Korea News Channel YTN ]",
"video_id": "XYrtvA02lKc"
}
| 8
|
[
"The image shows two news anchors in a studio, with a cityscape background. The male anchor is on the left, dressed in a dark suit with an orange tie, and the female anchor is on the right, wearing a white outfit. The news ticker at the bottom of the screen displays Korean text, which translates to: \"10 divers were killed in an accident while setting up a power transmission line... 'Delivering power to the flooded area'.\" The news broadcast appears to be covering a significant accident involving divers.",
"The current frame shows a large crack running down the middle of a bridge, suggesting significant structural damage. The scene appears to be outdoors, with trees and a clear sky in the background. The crack is located near the center of the bridge, with the road divided by a yellow line. The road has orange traffic cones placed on both sides of the crack, indicating that it is closed for safety. The bridge appears to be made of concrete and has a metal railing on the right side. The overall scene suggests that there has been a recent accident or disaster that has caused damage to the bridge.",
"The current frame depicts a significant crack running along the side of a road near a sidewalk, suggesting structural damage. The crack is noticeable and extends along the pavement adjacent to a yellow line marking the road boundary. A metal railing is visible on the right side, and yellow caution tape is wrapped around the posts, indicating a restricted area for safety. The scene appears to be outdoors, with sunlight casting shadows on the pavement. The text in the image, which is in Korean, translates to \"10 kilometers of crack formation on road... 'In the end, panic'\". This suggests that the damage is extensive, affecting a large portion of the road, and has caused concern or disruption.",
"The image shows a section of a road with significant structural damage, indicated by a large crack extending along the pavement near the sidewalk. Yellow caution tape and traffic cones have been placed around the area, likely to restrict access and ensure safety. The scene is outdoors, with trees lining the road and sunlight casting shadows on the pavement. The text in Korean translates to \"10 kilometers of crack formation on road... 'In the end, panic'\", suggesting extensive damage and a sense of urgency or disruption.",
"The image shows a similar section of a road with significant structural damage, indicated by a large crack extending along the pavement near the sidewalk. Yellow caution tape and traffic cones have been placed around the area, likely to restrict access and ensure safety. The scene is outdoors, with trees lining the road and sunlight casting shadows on the pavement. The text in Korean translates to \"10 kilometers of crack formation on road... 'In the end, panic'\", suggesting extensive damage and a sense of urgency or disruption.",
"The current frame shows a close-up of a bridge with noticeable damage, including large cracks and a section where the concrete has collapsed or is hanging precariously. There are patches of grass and debris beneath the damaged area, indicating the severity of the structural failure. The Korean text at the bottom reads \"분당 아파트 10교 구역으로 통제... '폭염에 팽창'\", which translates to \"Gwanggyo District, Gyeonggi-do, apartment complex area... 'Expanded due to heatwave'\", suggesting that the damage was exacerbated by the heat. The scene continues to emphasize the extent of the structural issue and the impact of extreme weather conditions.",
"The current frame continues to highlight the structural damage on a bridge, with visible large cracks and a section where the concrete appears to have collapsed or is precariously hanging. The area below the damaged section shows patches of grass and debris, reinforcing the severity of the structural failure. The Korean text at the bottom reads \"화면제공 경기 분당경찰서,\" which translates to \"Provided by Gyeonggi-do Bundang Police Station,\" indicating the source of the footage. This frame further emphasizes the extent of the structural issue and the impact of extreme weather conditions on the bridge.",
"The current frame continues to highlight the structural damage on a bridge, with visible large cracks and a section where the concrete appears to have collapsed or is precariously hanging. The area below the damaged section shows patches of grass and debris, reinforcing the severity of the structural failure. The Korean text at the bottom reads \"화면제공 경기 분당경찰서,\" which translates to \"Provided by Gyeonggi-do Bundang Police Station,\" indicating the source of the footage. This frame further emphasizes the extent of the structural issue and the impact of extreme weather conditions on the bridge."
] |
XYrtvA02lKc
|
A news broadcast reports on a significant accident involving 10 divers who were killed while setting up a power transmission line to deliver power to a flooded area. The incident is linked to a larger issue of structural damage caused by extreme weather conditions, such as a heatwave, which has affected various infrastructure, including roads and bridges. The video footage shows extensive cracks on roads and bridges, with some areas closed off for safety, indicating a state of panic and disruption. The damage is highlighted through images of cracked roads, collapsed bridge sections, and debris, emphasizing the severity of the structural failures. The source of some footage is attributed to the Gyeonggi-do Bundang Police Station, suggesting an official investigation or response to the incidents. Overall, the video depicts a serious situation involving loss of life, infrastructure damage, and the challenges posed by extreme weather conditions.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://twitter.com/i/status/1038669934375493632",
"video_description": "재난수준 폭염에도 올 여름 전력부족 없었다 올여름 재난 수준의 폭염으로 냉방 전력수요가 급증했지만 전력이 부족한 날은 없었음 7월과 8월 두 달 동안 공급예비율은 7일간을 제외, 모두 두 자릿수 이상을 유지 전력부족도 없었고, 전기세도 감면해준 문재인 정부",
"video_id": "1038669934375493632"
}
| 8
|
[
"The image shows a news broadcast from 연합뉴스TV (Yonhap News TV) with the headline in Korean stating \"재난수준 폭염에도 올 여름 전력부족 없었다\" which translates to \"No power shortage this summer despite disaster-level heatwave.\" The scene appears to be inside a control room or monitoring center with multiple computer screens displaying data. The time displayed is 13:36, and the temperature shown is 25.3°C.",
"In this frame, three men are standing in front of a large screen filled with various graphs and data points. They are wearing red vests with white text on the back, likely indicating their roles or affiliations. The man on the left is pointing at the screen, presumably explaining the information displayed, while the other two men are attentively looking at the screen, possibly discussing or analyzing the data presented. The screen shows a graph with a blue and red line trend, numbers, and text, indicating a detailed analysis or monitoring of some metrics. The bottom of the frame includes a news ticker in Korean, which includes the date \"23일\" (23rd) and the time \"13:36\", as well as other news headlines. The weather information indicates a temperature of 23.5°C. The scene appears to be a continuation of the previous frame, focusing on the same topic of the summer heatwave and power management.",
"In this frame, three men are seated at a desk filled with computer monitors and various devices. They are wearing yellow vests with blue text on the front, indicating their roles or affiliations. The man on the left is focused on writing something on a piece of paper, while the other two men are also looking down at their work, possibly discussing or analyzing data. The monitors in front of them display various graphs and data points, suggesting they are involved in monitoring or managing some operation. The bottom of the frame includes a news ticker in Korean, which includes the date \"23일\" (23rd) and the time \"13:36\", as well as other news headlines. The scene appears to be a continuation of the previous frames, focusing on the same topic of the summer heatwave and power management.",
"The current frame shows a man looking at a digital display that shows various data in Korean, including power generation and consumption figures. The man is wearing glasses, indicating he is closely examining the information. The display includes numbers such as \"10,018.0만kW\" and \"9,144.0만kW\", which likely represent different power metrics. At the bottom of the screen, there is a news ticker in Korean with the time \"13:37\" and more headlines. The scene continues the focus on monitoring and managing power usage, suggesting the ongoing theme of managing energy during a heatwave.",
"The current frame shows a man looking at a digital display that shows various data in Korean, including power generation and consumption figures. The man is wearing glasses, indicating he is closely examining the information. The display includes numbers such as \"10,018.0만kW\" and \"9,144.0만kW\", which likely represent different power metrics. At the bottom of the screen, there is a news ticker in Korean with the time \"13:37\" and more headlines. The scene continues the focus on monitoring and managing power usage, suggesting the ongoing theme of managing energy during a heatwave.",
"The current frame shows a man standing in front of a large digital display with various complex diagrams and data points in Korean, indicating he is monitoring the power grid. The man is wearing a yellow safety vest and a pink shirt, suggesting he is a worker or technician in a control room. The display includes lines and symbols, likely representing different parts of the electrical system. The news ticker at the bottom of the screen continues to display information in Korean, with the time \"13:37\" and additional headlines. The scene reinforces the theme of power management during a heatwave, as the man is focused on ensuring the stability of the power supply.",
"The current frame displays a close-up of multiple electrical meters and wiring, indicating the monitoring and distribution of electricity. The meters have labels and numbers, likely for identification and tracking usage. The presence of these meters, along with the wiring, suggests a focus on the infrastructure supporting the power grid. The news ticker at the bottom continues to display information in Korean, with the time \"13:37\" remaining consistent, reinforcing the ongoing narrative of power management during the heatwave. The scene highlights the technical aspects of power distribution and the measures being taken to maintain stability in the supply.",
"The scene presents a detailed view of electrical meters and their associated wiring, likely used for monitoring and distributing power within a residential or commercial building. The meters are arranged in a systematic layout on a wooden panel, with each meter displaying distinct numbers for identification and tracking usage. The visible wiring includes red and black cables, which are essential for the proper functioning of the electrical system. The news ticker at the bottom of the screen continues to provide Korean information, with the time \"13:37\" still visible, suggesting the scene is part of a news segment about power management during a heatwave. The text on the meters is in Korean, and the overall focus remains on the technical aspects of power distribution and the infrastructure supporting it."
] |
1038669934375493632
|
The video depicts a news broadcast from Yonhap News TV discussing the management of power supply during a severe heatwave in South Korea. The scene is set in a control room or monitoring center where technicians and workers, identified by their vests, are closely monitoring the power grid and analyzing data on computer screens. They are tracking power generation and consumption figures, ensuring there is no shortage despite the high demand caused by the heatwave. The video shows various aspects of power management, including monitoring of electrical meters, wiring, and infrastructure, highlighting the efforts to maintain stability in the power supply. Throughout the video, a news ticker at the bottom of the screen displays the time, 13:36-13:37, and other news headlines, emphasizing the real-time nature of the broadcast and the ongoing focus on managing energy during the heatwave.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://twitter.com/i/status/1026325665824403456",
"video_description": "\"너무 덥지? 잘 지내고 있어?\" 관심어린 안부 한 마디가 폭염의 열기를 식힐 수 있습니다. 더위가 기승을 부리는 요즘 부모님께 또 친구에게 안부 전화 하는 건 어떨까요? (출처 : 국민안전방송 안전한TV) #성남시 #폭염 #가마솥더위 #폭염대비",
"video_id": "1026325665824403456"
}
| 8
|
[
"Three men are walking along a paved path surrounded by greenery. The man on the left is using a walking stick, and the man on the right is wearing a cap and a small black bag. The man in the middle is carrying a backpack.",
"A woman with her hair tied back is looking to the side. She is wearing a beige shirt.",
"The woman with her hair tied back is looking down, possibly at a piece of paper or device, while wearing a beige shirt.",
"The woman with her hair tied back is looking up, appearing thoughtful or engaged in a conversation, still wearing a beige shirt.",
"The woman, with her hair tied back and wearing a beige shirt, is now talking on a white phone. She continues to appear engaged in her conversation, still positioned in the same area.",
"The woman, with her hair tied back and wearing a beige shirt, is still talking on her white phone. She remains engaged in her conversation, positioned in the same area with the cityscape in the background.",
"The woman continues her conversation on her white phone while standing in the same position, with the cityscape visible in the background. The text on the screen indicates she is discussing her interest in something.",
"The woman remains engaged in her conversation on her white phone, standing with the cityscape in the background. The text on the screen suggests she is expressing her enthusiasm or interest in a topic."
] |
1026325665824403456
|
A group of three men are walking along a path surrounded by greenery, while a woman, wearing a beige shirt with her hair tied back, is engaged in a phone conversation in a cityscape setting, discussing something that sparks her interest and enthusiasm.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://youtube.com/watch?v=09W_DRDb9HQ",
"video_description": "+--------------------------------------------------------------------------------+ ◈ 중앙일보 공식 SNS 채널 ◈ - 페이스북 : https://www.facebook.com/joongang/ - 인스타그램 : https://www.instagram.com/joongangilbo - 트위터 : http://www.twitter.com/joongangilbo - 유튜브 : https://goo.gl/DyGoPC - 네이버 TV : http://tvcast.naver.com/joongangsisa - 네이버포스트 : https://goo.gl/eeYh4k 당신이 원하는 뉴스, 중앙일보 SNS 채널과 함께하세요. +--------------------------------------------------------------------------------+",
"video_id": "09W_DRDb9HQ"
}
| 8
|
[
"The image shows a piece of cheese, an egg, and several slices of bacon arranged on a surface. The egg is cracked open, with the yolk centered and the white spread around it. The bacon slices are placed neatly beside the egg. There is a timer indicating 0 hours and 31 minutes. The text on the image, in Korean, translates to \"The cheese that the whole country is obsessed with, a delicious snack\".",
"The image shows a piece of cheese, an egg, and several slices of bacon arranged on a surface. The egg is cracked open, with the yolk centered and the white spread around it. The bacon slices are placed neatly beside the egg. There is a timer indicating 1 hour and 47 minutes. The text on the image, in Korean, translates to \"The cheese that the whole country is obsessed with, a delicious snack\".",
"The image shows the egg from the previous frame, now cooked and solidified on the surface. The yolk appears fully set, and the egg white has formed a distinct shape. The timer has advanced to indicate 2 hours and 6 minutes. The text on the image, in Korean, translates to \"The cheese that the whole country is obsessed with, a delicious snack.\"",
"A close-up of a cheese wheel with a bite taken out of it, revealing the creamy inside, with a wooden stick inserted, ready for eating. The text in Korean translates to \"The whole country is obsessed with this delicious snack.\"",
"The image shows a clear plastic cup on a textured surface, with several dark brown, shiny, square-shaped objects inside it. The text in Korean at the top translates to \"The whole country is obsessed with this delicious snack.\" The objects appear to be pieces of a sweet treat, possibly chocolate or candy, submerged in a liquid.",
"The current frame shows a clear plastic cup on a textured surface, similar to the previous frame, with the same dark brown, shiny, square-shaped objects inside it. The objects are still submerged in the liquid. The background features a blue sky with some clouds. The text in Korean at the top translates to \"The whole country is obsessed with this delicious snack.\" Additionally, there is a clock icon with the text \"10 min\" in the lower right corner, indicating the passage of time.",
"In the current frame, a hand holding a white plastic spoon scoops up one of the dark brown, shiny, square-shaped objects from a clear plastic cup filled with a similar dark brown liquid, continuing the interaction from the previous frames. The background remains an outdoor setting with a blue sky and clouds. The text at the top of the image in Korean translates to \"The whole country is obsessed with this delicious snack.\" The clock icon in the lower right corner now reads \"15 min,\" indicating the passage of time from the previous frame.",
"The video is in Korean, with the text \"중앙일보\" at the center, indicating the source or channel name."
] |
09W_DRDb9HQ
|
The video appears to be a Korean-language food or cooking video, showcasing a popular snack. It begins with a setup of ingredients, including cheese, an egg, and bacon, with a timer counting up. The egg is shown to be cooked over time, with the timer advancing. The video then cuts to a cheese wheel with a bite taken out of it and a wooden stick inserted, ready for eating. The scene shifts to a clear plastic cup containing dark brown, shiny, square-shaped objects, possibly chocolate or candy, submerged in a liquid. A hand is then shown scooping up one of these objects with a spoon, with a clock icon in the corner indicating the passage of time. The video ends with a screen displaying the source or channel name, "중앙일보". Overall, the video seems to be highlighting a delicious and popular Korean snack, with the exact nature of the snack and the cooking or preparation process being the main focus.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://youtube.com/watch?v=8wcKX0LCc08",
"video_description": "폭염 때문에 힘든 건 사람만이 아닙니다. 과육이 물러진 수박이 산지에서 폐기되는 등 제철 과일과 채소 피해도 잇따르고 있습니다.",
"video_id": "8wcKX0LCc08"
}
| 8
|
[
"A news anchor is presenting on MBC News Today, with a backdrop showing a field with numerous watermelons and a close-up of sliced watermelons. The time is displayed as 07:18, and the temperature is 28°C. Text on the screen indicates a focus on a national watermelon market that has fallen.",
"The current frame shows a field with a large number of watermelons scattered on the ground. Some of the watermelons are intact while others are cut open, revealing their red flesh. The scene is set in a rural area with green vegetation around. The time displayed is 07:18, and the temperature is 28°C. The text on the screen suggests a focus on the current situation of the national watermelon market.",
"The focus remains on a close-up view of the watermelons. The frame continues to showcase the watermelons in the rural field with some still whole and others cut open, exposing the red interior. The time displayed is still 07:18, and the temperature remains at 28°C. The text on the screen maintains its focus on the national watermelon market situation, indicating a consistent narrative about the current state of the market.",
"The focus remains on the watermelons in the rural field, with some still whole and others cut open, exposing the red interior. A person is now present in the frame, kneeling in the watermelon field, possibly inspecting or speaking about the watermelons. The time displayed is 07:18, and the temperature remains at 28°C. The text on the screen continues to focus on the national watermelon market situation, indicating a consistent narrative about the current state of the market.",
"The scene shifts to a close-up of a watermelon in the field, highlighting its exterior texture and green stripes. The person from the previous frame is not visible. The time displayed is now 07:19, indicating a one-minute progression. The temperature remains at 26°C. The text on the screen discusses the need to continue observing the watermelon price situation, suggesting an ongoing narrative about the market's status. The overlay image shows a person wearing a hat, potentially a farmer, but their face is not visible.",
"The video shows a close-up of a corn ear in the field, with the husks partially open, revealing the kernels. The time is now 07:19, consistent with the previous frame, indicating the scene is still within the same timeframe. The temperature remains at 26°C. The text overlay continues to discuss the ongoing situation of observing the watermelon price situation, suggesting the video is part of a news report about agricultural markets or conditions. The image maintains a focus on agriculture, moving from watermelons to corn, indicating a broader context of agricultural produce and market conditions.",
"The video shows a view of a field with green foliage, likely crops, with a narrow path in the middle. The time remains at 07:19, indicating the scene is still within the same timeframe as the previous frames. The temperature is still at 26°C. The text overlay in Korean reads \"오늘은 폭염에 생산량 급증...가격 폭락\" which translates to \"Today, due to the heatwave, production has surged...prices have plummeted,\" suggesting the video is discussing the impact of the heatwave on agricultural production and market prices. The image shows a continuation of the agricultural theme, focusing on the broader context of crop production and market conditions in response to weather conditions.",
"In this current frame, we see a person working in the field, dressed in a long-sleeved pink shirt and camouflage pants, bending over to tend to the crops. The individual appears to be harvesting or tending to the plants, indicating active involvement in agricultural work. The time is still marked at 07:19, and the temperature has risen to 30°C, likely due to the progression of the day. The text overlay in Korean reads \"서울 용산 어혈사 사무실서 화재...850만원 피해\" which translates to \"Fire in Sejong Hall, Seoul Yongsan, Office... 85 million won damage,\" introducing a new element of a fire incident unrelated to the agricultural theme. The image continues to depict the broader context of agricultural activities, but now includes an overlay of news about an incident in Seoul, highlighting a shift in focus within the video."
] |
8wcKX0LCc08
|
A news report on MBC News Today discusses the national watermelon market, which has fallen due to a surge in production caused by a heatwave, resulting in plummeting prices. The video shows footage of a rural field with numerous watermelons, some cut open, and a person inspecting them. The scene shifts to show other agricultural produce, such as corn, and the broader context of crop production in the field. A person is later seen tending to crops, highlighting the active involvement in agricultural work. The report also briefly mentions a fire incident in Seoul, indicating a shift in focus to other news. Overall, the video primarily focuses on the impact of the heatwave on agricultural production and market prices, specifically the watermelon market.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://youtube.com/watch?v=g9CbgCp52qc",
"video_description": "연일 불볕더위가 기승을 부리는 가운데 서울시가 도로에 물을 뿌려 열을 식히는 작업을 강화합니다. 서울시는 낮 최고기온이 32℃ 이상으로 오르면 폭염에 노출될 가능성이 큰 정오부터 오후 4시까지 중앙버스전용차로를 중심으로 살수 차량 운행을 확대한다고 밝혔습니다. 서울시는 여름철 도로 물뿌리기로 미세먼지를 제거하는 동시에 온열질환 등 폭염으로 발생할 수 있는 안전사고도 방지할 수 있기를 기대하고 있습니다. ▶ 기사 원문 : http://www.ytn.co.kr/_ln/0115_201807181131189139 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, [email protected], #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ [ 한국 뉴스 채널 와이티엔 / Korea News Channel YTN ]",
"video_id": "g9CbgCp52qc"
}
| 8
|
[
"A man is wearing a dark pink suit with a white shirt and a purple tie. He appears to be in a dimly lit room with candles in the background, creating an intense atmosphere.",
"The current frame is extremely dark, making it challenging to discern specific details. The previous frame's intense atmosphere persists, but the low lighting prevents a clear view of the scene.",
"A man with long hair and a beard is seen in profile, looking into the distance. The lighting casts dramatic shadows on his face, suggesting a tense or reflective moment.",
"The man with long hair and a beard is seen in profile, looking intently into the distance. The lighting casts dramatic shadows on his face, suggesting a tense or reflective moment.",
"The man is still walking toward the Eiffel Tower, which is partially obscured by fog. He walks with purpose, his silhouette contrasting against the muted background.",
"The man is standing near a metallic door, possibly in an industrial or urban setting. He is smiling and looking towards the camera, indicating a moment of interaction or arrival. The environment appears dimly lit with some graffiti visible in the background.",
"The man is now outside, possibly in an urban or outdoor setting, looking serious. The environment appears dimly lit with some red foliage visible in the background.",
"The current frame depicts an intense scene where a figure, likely the man from previous frames, is running through an environment engulfed in flames. The setting is chaotic, with debris and fiery elements surrounding the figure, indicating a high-stakes situation. The figure appears determined, suggesting a sense of urgency or a mission to accomplish amidst the destruction."
] |
g9CbgCp52qc
|
A man, distinguishable by his changing appearances, including a dark pink suit and later long hair with a beard, navigates through various environments, conveying a sense of intensity and purpose. The video begins in a dimly lit, atmospheric setting, transitions through moments of tension and reflection, and progresses to the man walking towards the Eiffel Tower shrouded in fog. His journey continues in industrial or urban settings, where he exhibits a range of emotions from seriousness to a brief moment of smiles. The culmination of his journey is marked by an intense, high-stakes scene where he is seen running through a flaming environment, suggesting a mission or escape amidst chaos. Throughout, the man's determination and the dramatic lighting underscore the video's themes of urgency and reflection.
|
In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.
|
[
"People bundling up in heavy clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in heavy clothing to brave the cold during record cold temperatures in East Asia, Southeast Asia, and South Asia in late January 2016",
"People bundling up in heavy clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong, during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia during late January 2016 snowfall events",
"Frost or ice formation on car windshields, roads, and buildings during the cold wave in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings during snowfall in East Asia, Southeast Asia, and South Asia in late January 2016",
"Residents in East Asia, Southeast Asia, and South Asia shoveling snow or using umbrellas to navigate snowy streets during the late January 2016 cold wave",
"Residents in East and South Asia shoveling snow or using umbrellas to navigate snowy streets during record cold temperatures in late January 2016",
"Residents shoveling snow or using umbrellas to navigate snowy streets in East Asia, Southeast Asia, or South Asia in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia Southeast Asia and South Asia during late January 2016"
] |
[
"People bundling up in warm clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in warm clothing to brave the cold in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People bundling up in warm clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"Frozen lakes and rivers with people ice skating or playing in East Asia Southeast Asia or South Asia during late January 2016 cold wave",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia where people are ice skating or playing during the record cold temperatures of late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, or South Asia where people are ice skating or playing in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia during late January 2016 cold wave",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia after snowfall in late January 2016",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 cold wave",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off sidewalks and driveways in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
[
"People bundling up in winter clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in winter clothing to brave the cold in East and South Asia during late January 2016 record cold snap",
"People bundling up in winter clothing to brave the cold during late January 2016 snowfall in East, Southeast, and South Asia",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during the cold wave of late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia due to record cold temperatures in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia after snowfall in late January 2016",
"Trees and buildings covered in snow and ice during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off streets and sidewalks in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_1%EC%9B%94_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%95%9C%ED%8C%8C",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, and the consequences of the snowfall, as these events are likely to be visualized in a video. The extracted events should be specific to the regions mentioned and the time of year, taking into account the typical climate and scenery of East Asia, mainland Southeast Asia, and northern South Asia in late January.\n\nEVENTS:\n1. People bundling up in winter clothing to brave the cold\n2. Snow falling in cities and towns\n3. Frozen lakes and rivers\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off streets and sidewalks",
"en_article_excerpt": "In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.",
"en_article_url": "https://en.wikipedia.org/wiki/January_2016_East_Asia_cold_wave",
"event_category": "disasters",
"event_name": "2016_east_asia_cold_wave",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, disruptions to daily life, and unusual weather phenomena like snowfall in regions that rarely see it. These events would be visually representative of the cold wave's impact and could be reasonably captured in a video.\n\nEVENTS:\n1. People bundling up in heavy clothing to brave the cold\n2. Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong\n3. Frost or ice forming on surfaces like car windshields, roads, and buildings\n4. Residents shoveling snow or using umbrellas to navigate snowy streets\n5. Cars and buses driving slowly on icy or snow-covered roads",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a cold wave, such as people dealing with the cold and snow, and disruptions to daily life. These events should be visual and concrete, and could be reasonably captured in a video of the cold wave's impact.\n\nEVENTS:\n1. People bundling up in warm clothing to brave the cold\n2. Snowplows clearing roads and highways\n3. Frozen lakes and rivers with people ice skating or playing\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off sidewalks and driveways",
"video_URL": "http://twitter.com/i/status/1346958705632296961",
"video_description": "전국 눈 대단한 한파 다들 잘 이겨내요",
"video_id": "1346958705632296961"
}
| 8
|
[
"The image shows a cityscape with high-rise apartment buildings on both sides of a central pathway. The area appears to be a residential complex with several tall buildings, and there is a park-like setting with trees and pathways in the foreground. The sky is overcast, indicating a cloudy or foggy day.",
"The scene continues to showcase the cityscape with the same high-rise apartment buildings and the central pathway. The park-like setting remains visible, and the overcast sky persists, reinforcing the cloudy or foggy atmosphere. There are no discernible changes or movements in the environment or people.",
"The scene continues to showcase the cityscape with the same high-rise apartment buildings and the central pathway. The park-like setting remains visible, and the overcast sky persists, reinforcing the cloudy or foggy atmosphere. There are no discernible changes or movements in the environment or people.",
"The scene remains consistent with the cityscape, featuring high-rise apartment buildings and a central pathway. The park-like setting is still visible, and the overcast sky continues, maintaining the cloudy or foggy atmosphere. There are no discernible changes or movements in the environment or people.",
"The scene continues to show the cityscape with high-rise apartment buildings and a central pathway, but now there are a few people walking along the pathway, indicating movement and activity in the environment. The park-like setting and overcast sky remain consistent with the previous frame.",
"The cityscape with high-rise apartment buildings and the central pathway remains visible. A few people are still walking along the pathway, indicating ongoing movement and activity. There is no significant change in the environment or the actions of the people.",
"The cityscape with high-rise apartment buildings is still visible. A few people continue to walk along the pathway, maintaining the ongoing movement and activity. There is no significant change in the environment or the actions of the people.",
"The cityscape with high-rise apartment buildings remains prominent. The pathway is visible with a few people continuing to walk, sustaining the scene's dynamic nature. There are no significant changes in the environment or the pedestrians' actions."
] |
1346958705632296961
|
The video depicts a static cityscape of a residential complex with high-rise apartment buildings and a central pathway, set against an overcast sky. The scene remains largely unchanged throughout, with a park-like setting in the foreground. Initially, the environment appears deserted, but as the video progresses, a few people are introduced, walking along the pathway, injecting movement and activity into the otherwise static scene. The video captures a mundane, everyday moment in the life of the residential complex, showcasing the peaceful coexistence of the urban landscape and its inhabitants on a cloudy or foggy day.
|
In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.
|
[
"People bundling up in heavy clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in heavy clothing to brave the cold during record cold temperatures in East Asia, Southeast Asia, and South Asia in late January 2016",
"People bundling up in heavy clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong, during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia during late January 2016 snowfall events",
"Frost or ice formation on car windshields, roads, and buildings during the cold wave in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings during snowfall in East Asia, Southeast Asia, and South Asia in late January 2016",
"Residents in East Asia, Southeast Asia, and South Asia shoveling snow or using umbrellas to navigate snowy streets during the late January 2016 cold wave",
"Residents in East and South Asia shoveling snow or using umbrellas to navigate snowy streets during record cold temperatures in late January 2016",
"Residents shoveling snow or using umbrellas to navigate snowy streets in East Asia, Southeast Asia, or South Asia in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia Southeast Asia and South Asia during late January 2016"
] |
[
"People bundling up in warm clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in warm clothing to brave the cold in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People bundling up in warm clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"Frozen lakes and rivers with people ice skating or playing in East Asia Southeast Asia or South Asia during late January 2016 cold wave",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia where people are ice skating or playing during the record cold temperatures of late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, or South Asia where people are ice skating or playing in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia during late January 2016 cold wave",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia after snowfall in late January 2016",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 cold wave",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off sidewalks and driveways in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
[
"People bundling up in winter clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in winter clothing to brave the cold in East and South Asia during late January 2016 record cold snap",
"People bundling up in winter clothing to brave the cold during late January 2016 snowfall in East, Southeast, and South Asia",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during the cold wave of late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia due to record cold temperatures in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia after snowfall in late January 2016",
"Trees and buildings covered in snow and ice during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off streets and sidewalks in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_1%EC%9B%94_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%95%9C%ED%8C%8C",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, and the consequences of the snowfall, as these events are likely to be visualized in a video. The extracted events should be specific to the regions mentioned and the time of year, taking into account the typical climate and scenery of East Asia, mainland Southeast Asia, and northern South Asia in late January.\n\nEVENTS:\n1. People bundling up in winter clothing to brave the cold\n2. Snow falling in cities and towns\n3. Frozen lakes and rivers\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off streets and sidewalks",
"en_article_excerpt": "In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.",
"en_article_url": "https://en.wikipedia.org/wiki/January_2016_East_Asia_cold_wave",
"event_category": "disasters",
"event_name": "2016_east_asia_cold_wave",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, disruptions to daily life, and unusual weather phenomena like snowfall in regions that rarely see it. These events would be visually representative of the cold wave's impact and could be reasonably captured in a video.\n\nEVENTS:\n1. People bundling up in heavy clothing to brave the cold\n2. Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong\n3. Frost or ice forming on surfaces like car windshields, roads, and buildings\n4. Residents shoveling snow or using umbrellas to navigate snowy streets\n5. Cars and buses driving slowly on icy or snow-covered roads",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a cold wave, such as people dealing with the cold and snow, and disruptions to daily life. These events should be visual and concrete, and could be reasonably captured in a video of the cold wave's impact.\n\nEVENTS:\n1. People bundling up in warm clothing to brave the cold\n2. Snowplows clearing roads and highways\n3. Frozen lakes and rivers with people ice skating or playing\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off sidewalks and driveways",
"video_URL": "http://youtube.com/watch?v=2qCY0mBeZy4",
"video_description": "지난 연말부터 시작된 한파의 기세는 여전했습니다. 강원도 산간은 영하 20도, 철원 영하 15.9도, 서울도 영하 9.8도를 기록했습니다. 이번 한파는 풀리지 않고 다음 주까지 이어질 것으로 보입니다. 주말부터 다음 주 초반까지 기온이 조금 오르지만, 이후 다시 기온이 급강하하기 때문입니다. 특히 다음 주 후반에는 서울 기온이 영하 15도까지 떨어지는 강력한 한파가 맹위를 떨칠 전망입니다. 올겨울 들어 가장 강력한 추위입니다. [윤기한 / 기상청 통보관 : 한파가 누그러지지 않은 상황에서 2차로 한기가 추가로 내려오는 것입니다. 따라서 다음 주에는 추위 강도가 지금보다 훨씬 세질 것으로 보입니다.] 북극 한파가 새해 첫날부터 열흘 이상 이어지는 것입니다. 서해안의 눈도 잠시 약해졌다가 다음 주 중반 이후에는 눈 폭탄으로 쏟아질 것으로 우려됩니다. 기상청은 이번 한파와 폭설로 동파와 축사, 비닐하우스 붕괴 등 시설물 피해가 속출할 것이라며 사전 대비를 당부했습니다. 취재기자: 김진두 영상편집: 한경희 자막뉴스: 박해진 ▶ 기사 원문 : https://www.ytn.co.kr/replay/view.php?idx=29&key=202101020712296278 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, [email protected], #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN & YTN plus 무단 전재 및 재배포금지",
"video_id": "2qCY0mBeZy4"
}
| 8
|
[
"The image shows a weather forecast or update from a news channel, indicated by the logo \"YTN\" in the top right corner. The focus is on temperatures in various Korean cities: Seoul, Cheonan, Suwon, Gwangju, and Busan. The temperature readings are displayed in a blue table with icicle graphics, indicating cold weather. The temperatures listed are -20.4°C in Seoul, -15.9°C in Cheonan, -9.8°C in Suwon, and -5.0°C in both Gwangju and Busan. The text at the bottom provides further context, stating the daily low temperatures for the same cities. The background shows a blurred image of frost-covered branches, reinforcing the theme of cold weather.",
"The image shows a group of people walking on a bridge in a cold environment. The scene is captured by a news channel, as indicated by the \"YTN\" logo in the top right corner. The individuals are dressed warmly in heavy jackets and hats, suggesting that they are braving cold temperatures. In the background, there are buildings with signs, and the presence of a metal railing along the bridge is visible. The bottom text reads in Korean, which translates to \"The temperature has risen slightly from the morning, but will drop again later.\" This provides context to the scene, indicating that the cold conditions are not expected to last throughout the day. The overall setting and attire of the people highlight the cold weather conditions being experienced.",
"The current frame displays a weather forecast graphic from the news channel \"YTN.\" The forecast shows a temperature chart for the upcoming days, highlighting a significant cold wave expected to hit the region. The graph indicates that temperatures will drop to -15 degrees Celsius, with the lowest point on the 8th day. The text at the top reads \"Extreme cold wave expected to last until the 10th day,\" while the bottom text states \"Especially, Seoul will experience temperatures as low as -15 degrees Celsius.\" The overall context suggests that the video is providing a detailed outlook on the upcoming extreme cold weather conditions affecting the area.",
"The video presents a scene where a person is seen using a red drill to break ice in a blue container. The individual appears focused on breaking through the thick ice layer, likely to access the water underneath. The context suggests that due to the extremely cold weather conditions mentioned in the previous frame, the water has frozen, and the individual is taking action to use the water. The text overlay at the bottom of the frame reads \"올겨울 들어서 가장 강력한 추위입니다,\" which translates to \"This is the strongest cold spell since this winter.\" This reinforces the severity of the weather conditions being experienced and the necessity for the action shown.",
"The scene depicts a person in a dark hooded jacket standing outdoors, with another person partially visible in the background wearing an orange jacket. The context suggests a continuation of the cold weather theme, as indicated by the individuals' winter attire. The text overlay at the bottom of the frame reads \"따라서 다음 주에는 추위 강도가 지금보다 훨씬 세질 것으로 보입니다,\" translating to \"Therefore, next week, the intensity of the cold is expected to be much stronger than now.\" This implies that the cold weather conditions will worsen, aligning with the actions seen in the previous frame where a person was breaking ice to access water due to extreme cold.",
"The current frame shows three children walking through a snowy landscape. The children are dressed in winter clothing, suitable for cold weather. The snow appears deep, covering the ground extensively. The text overlay at the bottom of the frame reads \"서해안의 눈도 잠시 약해졌다가 다음 주 중반 이후에는 눈 폭탄으로 쏟아질 것으로 우려됩니다,\" translating to \"Concerns arise that the snowfall in the western coast, which temporarily weakened, is expected to turn into a snowstorm in the middle of next week.\" This suggests that the children might be experiencing milder snow conditions now, but a significant snowstorm is anticipated soon.",
"The current frame shows a white car driving through a snowy terrain. The car's tires are kicking up snow as it moves, indicating the challenging driving conditions. The text overlay at the bottom of the frame reads \"기상청은 이번 한파와 폭설로 동파와 축사, 비닐하우스 붕괴 등 시설물 피해가 속출할 것이라며 사전 대비를 당부했습니다.\" This translates to \"The Korea Meteorological Administration warned that due to the current cold wave and heavy snowfall, there will be numerous damages to facilities, such as frozen pipes and collapsed greenhouses, and urged preemptive measures.\" This suggests that the current frame is emphasizing the need for preparedness due to the severe weather conditions.",
"The current frame shows a white car driving through a snowy terrain, with the car's tires kicking up snow as it moves. The text overlay at the bottom of the frame reads \"기상청은 이번 한파와 폭설로 동파와 축사, 비닐하우스 붕괴 등 시설물 피해가 속출할 것이라며 사전 대비를 당부했습니다.\" This translates to \"The Korea Meteorological Administration warned that due to the current cold wave and heavy snowfall, there will be numerous damages to facilities, such as frozen pipes and collapsed greenhouses, and urged preemptive measures.\" This suggests that the current frame is emphasizing the need for preparedness due to the severe weather conditions."
] |
2qCY0mBeZy4
|
A news report from YTN covers an extreme cold wave hitting Korea, with temperatures dropping significantly in various cities such as Seoul, Cheonan, Suwon, Gwangju, and Busan. People are shown braving the cold, walking on a bridge and taking necessary actions like breaking ice to access water. The weather forecast indicates that the cold spell will worsen, with temperatures expected to drop further and a significant snowstorm anticipated in the western coast. The report shows children walking in snowy landscapes and cars driving through challenging snowy terrains, highlighting the severe weather conditions. The Korea Meteorological Administration warns of potential damages to facilities due to the cold wave and heavy snowfall, urging preemptive measures to be taken. Overall, the video depicts the harsh winter conditions in Korea, the impact on daily life, and the need for preparedness and caution due to the extreme weather.
|
In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.
|
[
"People bundling up in heavy clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in heavy clothing to brave the cold during record cold temperatures in East Asia, Southeast Asia, and South Asia in late January 2016",
"People bundling up in heavy clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong, during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia during late January 2016 snowfall events",
"Frost or ice formation on car windshields, roads, and buildings during the cold wave in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings during snowfall in East Asia, Southeast Asia, and South Asia in late January 2016",
"Residents in East Asia, Southeast Asia, and South Asia shoveling snow or using umbrellas to navigate snowy streets during the late January 2016 cold wave",
"Residents in East and South Asia shoveling snow or using umbrellas to navigate snowy streets during record cold temperatures in late January 2016",
"Residents shoveling snow or using umbrellas to navigate snowy streets in East Asia, Southeast Asia, or South Asia in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia Southeast Asia and South Asia during late January 2016"
] |
[
"People bundling up in warm clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in warm clothing to brave the cold in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People bundling up in warm clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"Frozen lakes and rivers with people ice skating or playing in East Asia Southeast Asia or South Asia during late January 2016 cold wave",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia where people are ice skating or playing during the record cold temperatures of late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, or South Asia where people are ice skating or playing in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia during late January 2016 cold wave",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia after snowfall in late January 2016",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 cold wave",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off sidewalks and driveways in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
[
"People bundling up in winter clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in winter clothing to brave the cold in East and South Asia during late January 2016 record cold snap",
"People bundling up in winter clothing to brave the cold during late January 2016 snowfall in East, Southeast, and South Asia",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during the cold wave of late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia due to record cold temperatures in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia after snowfall in late January 2016",
"Trees and buildings covered in snow and ice during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off streets and sidewalks in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_1%EC%9B%94_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%95%9C%ED%8C%8C",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, and the consequences of the snowfall, as these events are likely to be visualized in a video. The extracted events should be specific to the regions mentioned and the time of year, taking into account the typical climate and scenery of East Asia, mainland Southeast Asia, and northern South Asia in late January.\n\nEVENTS:\n1. People bundling up in winter clothing to brave the cold\n2. Snow falling in cities and towns\n3. Frozen lakes and rivers\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off streets and sidewalks",
"en_article_excerpt": "In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.",
"en_article_url": "https://en.wikipedia.org/wiki/January_2016_East_Asia_cold_wave",
"event_category": "disasters",
"event_name": "2016_east_asia_cold_wave",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, disruptions to daily life, and unusual weather phenomena like snowfall in regions that rarely see it. These events would be visually representative of the cold wave's impact and could be reasonably captured in a video.\n\nEVENTS:\n1. People bundling up in heavy clothing to brave the cold\n2. Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong\n3. Frost or ice forming on surfaces like car windshields, roads, and buildings\n4. Residents shoveling snow or using umbrellas to navigate snowy streets\n5. Cars and buses driving slowly on icy or snow-covered roads",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a cold wave, such as people dealing with the cold and snow, and disruptions to daily life. These events should be visual and concrete, and could be reasonably captured in a video of the cold wave's impact.\n\nEVENTS:\n1. People bundling up in warm clothing to brave the cold\n2. Snowplows clearing roads and highways\n3. Frozen lakes and rivers with people ice skating or playing\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off sidewalks and driveways",
"video_URL": "http://youtube.com/watch?v=QmU3W9ffZeM",
"video_description": "기온이 마치 롤러코스터처럼 떨어질 모양입니다. 얼마나 추워질지 벌써부터 겁도 나는데요. 일단 내일 아침 서울 기온은 영하 11도까지 떨어지겠고요. 목요일부터는 찬바람이 더욱 강해지면서 아침 기온이 영하 15도로 전날 낮 대비 13도가량 기온이 급감하겠습니다. 한낮 기온도 영하 11도에 머물 텐데요. 다음 날 금요일 아침 기온은 영하 17도로 이번 한파의 절정이 되겠습니다. 한파 대비 미리 해주시는 게 좋겠습니다. 이에 따라서 오늘 밤 9시를 기해서는 경기 동부와 북부, 충청도, 경북 곳곳에 한파경보가 발효되겠고요. 서울 등 그 밖의 수도권과 충청도 전북 내륙 지역까지 한파주의보가 확대 발효되겠습니다. 눈구름도 함께 몰려오겠습니다. 내일 퇴근길 무렵에 서해 등 서쪽지역에 눈이 내리기 시작해 밤사이에 전국으로 확대될 텐데요. 특히 서해안 지역으로는 최대 30cm 이상, 제주 산지에는 최고 50cm 이상의 폭설이 우려됩니다. 충남 지역에는 금요일까지 호남과 제주도는 일요일까지 눈이 길게 이어지겠습니다. 날씨였습니다. https://imnews.imbc.com/replay/2021/nw1700/article/6048848_34922.html #날씨,#추위 #한파",
"video_id": "QmU3W9ffZeM"
}
| 8
|
[
"A woman in a brown dress is presenting a weather forecast graph. The graph shows temperature changes over time, indicating a drop from -3.6°C to -17°C. The text mentions \"북극발 한파 대비\" (Preparation for Arctic Cold Wave) and \"서울 °C\" (Seoul °C), suggesting a focus on the cold wave's impact on Seoul.",
"A woman in a brown dress is continuing her presentation of the weather forecast graph. The graph shows the temperature dropping from -3.6°C to -17°C. The text \"북극발 한파 대비\" (Preparation for Arctic Cold Wave) and \"서울 °C\" (Seoul °C) emphasize the significance of the cold wave in Seoul. The woman is pointing to the graph, indicating the sharp temperature decline.",
"The woman in the brown dress continues to present the weather forecast graph, which illustrates the temperature dropping further to -17°C. The text \"북극발 한파 대비\" (Preparation for Arctic Cold Wave) and \"서울 °C\" (Seoul °C) remain visible, highlighting the impact of the cold wave in Seoul. The woman is pointing to the graph, continuing to emphasize the significant temperature decline.",
"The woman in the brown dress is presenting a map of Korea, highlighting areas affected by the cold wave. She points to the map, with the text \"기상특보\" (Special Weather Report) and \"한파경보\" (Cold Wave Warning) indicating a weather alert, specifically targeting the northern regions of Korea.",
"In the current frame, the woman continues to present the map, now pointing to the central regions of Korea. The text \"기상특보\" (Special Weather Report) and \"한파주의보\" (Cold Wave Caution) are displayed, indicating an advisory for colder areas. The background shows a frozen landscape with tall grasses, emphasizing the cold weather conditions.",
"The woman continues her presentation outdoors in a snowy setting. She is now standing in front of a graphic displaying a snowflake and Korean text that reads \"내일 방부터 폭설\" (Heavy Snow Expected Tomorrow) and \"서해안 최고 30cm\". The background remains consistent with the previous frame, featuring a frozen landscape with tall grasses and trees.",
"The woman continues her presentation outdoors in a snowy setting. She is standing in front of a graphic displaying a snowflake and Korean text that reads \"내일 방부터 폭설\" (Heavy Snow Expected Tomorrow) and \"서해안 최고 30cm\". The background remains consistent with the previous frame, featuring a frozen landscape with tall grasses and trees.",
"The woman continues her presentation outdoors in a snowy setting. She is standing in front of a graphic displaying a snowflake and Korean text that reads \"내일 방부터 폭설\" (Heavy Snow Expected Tomorrow) and \"서해안 최고 30cm\". The background remains consistent with the previous frame, featuring a frozen landscape with tall grasses and trees."
] |
QmU3W9ffZeM
|
A woman in a brown dress presents a weather forecast, warning of an Arctic cold wave's impact on Seoul, with temperatures expected to drop from -3.6°C to -17°C. She highlights areas affected by the cold wave on a map of Korea, indicating a special weather report and cold wave warning for northern regions and a cold wave caution for central regions. The presentation then shifts to an outdoor snowy setting, where she announces that heavy snow is expected the next day, with up to 30cm predicted for the west coast, emphasizing the severity of the upcoming weather conditions.
|
In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.
|
[
"People bundling up in heavy clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in heavy clothing to brave the cold during record cold temperatures in East Asia, Southeast Asia, and South Asia in late January 2016",
"People bundling up in heavy clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong, during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia during late January 2016 snowfall events",
"Frost or ice formation on car windshields, roads, and buildings during the cold wave in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings during snowfall in East Asia, Southeast Asia, and South Asia in late January 2016",
"Residents in East Asia, Southeast Asia, and South Asia shoveling snow or using umbrellas to navigate snowy streets during the late January 2016 cold wave",
"Residents in East and South Asia shoveling snow or using umbrellas to navigate snowy streets during record cold temperatures in late January 2016",
"Residents shoveling snow or using umbrellas to navigate snowy streets in East Asia, Southeast Asia, or South Asia in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia Southeast Asia and South Asia during late January 2016"
] |
[
"People bundling up in warm clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in warm clothing to brave the cold in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People bundling up in warm clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"Frozen lakes and rivers with people ice skating or playing in East Asia Southeast Asia or South Asia during late January 2016 cold wave",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia where people are ice skating or playing during the record cold temperatures of late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, or South Asia where people are ice skating or playing in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia during late January 2016 cold wave",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia after snowfall in late January 2016",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 cold wave",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off sidewalks and driveways in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
[
"People bundling up in winter clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in winter clothing to brave the cold in East and South Asia during late January 2016 record cold snap",
"People bundling up in winter clothing to brave the cold during late January 2016 snowfall in East, Southeast, and South Asia",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during the cold wave of late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia due to record cold temperatures in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia after snowfall in late January 2016",
"Trees and buildings covered in snow and ice during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off streets and sidewalks in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_1%EC%9B%94_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%95%9C%ED%8C%8C",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, and the consequences of the snowfall, as these events are likely to be visualized in a video. The extracted events should be specific to the regions mentioned and the time of year, taking into account the typical climate and scenery of East Asia, mainland Southeast Asia, and northern South Asia in late January.\n\nEVENTS:\n1. People bundling up in winter clothing to brave the cold\n2. Snow falling in cities and towns\n3. Frozen lakes and rivers\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off streets and sidewalks",
"en_article_excerpt": "In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.",
"en_article_url": "https://en.wikipedia.org/wiki/January_2016_East_Asia_cold_wave",
"event_category": "disasters",
"event_name": "2016_east_asia_cold_wave",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, disruptions to daily life, and unusual weather phenomena like snowfall in regions that rarely see it. These events would be visually representative of the cold wave's impact and could be reasonably captured in a video.\n\nEVENTS:\n1. People bundling up in heavy clothing to brave the cold\n2. Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong\n3. Frost or ice forming on surfaces like car windshields, roads, and buildings\n4. Residents shoveling snow or using umbrellas to navigate snowy streets\n5. Cars and buses driving slowly on icy or snow-covered roads",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a cold wave, such as people dealing with the cold and snow, and disruptions to daily life. These events should be visual and concrete, and could be reasonably captured in a video of the cold wave's impact.\n\nEVENTS:\n1. People bundling up in warm clothing to brave the cold\n2. Snowplows clearing roads and highways\n3. Frozen lakes and rivers with people ice skating or playing\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off sidewalks and driveways",
"video_URL": "http://youtube.com/watch?v=G7XGz4uL6mI",
"video_description": "기상정보 배혜지 기상캐스터 2021년 1월 12일 화요일 아침 시각 빙판길 골목길 언덕길 등 보행 조심하세요... 감기 걸리지 않도록 건강관리 잘하세요. 행복한 화요일 되세요.^^ #감기조심 #한파특보 #한파경보 #한파주의보 #건조경보 #화재예방 #산불조심 #코로나19 #COVID19 #기상정보 #날씨 #Weather #배혜지기상캐스터 #기상캐스터 #WeatherCaster #KBS뉴스광장 ============================================================== Uploaded by: 하안마음 (White Heart.rhythm7777777) Youtube: http://www.youtube.com/user/rhythmsgarden Twitter: https://twitter.com/rhythm700 Face Book: https://www.facebook.com/rhythm700 Instagram: https://www.instagram.com/rhythm7777777 헤일리 웨스튼라 Hayley Westenra Official Website: http://www.hayleywestenra.com Instagram: https://www.instagram.com/hayleywestenra Twitter: https://twitter.com/hayleywestenra FaceBook: https://www.facebook.com/hayleywestenra Youtube: https://www.youtube.com/channel/UCuA623UAgxrJuWcMcaI_kgg 헤일리 웨스튼라 코리아 Hayley Westenra Korea Fancafe: http://cafe.daum.net/HayleyWestenra Facebook: https://www.facebook.com/hayleywestenra Youtube: https://www.youtube.com/channel/UCBrwEte0dnl1JTWSpzGFVeA/videos Wikipedia: http://en.wikipedia.org/wiki/Hayley_Westenra",
"video_id": "G7XGz4uL6mI"
}
| 8
|
[
"A news anchor stands in front of a snowy mountain backdrop, presenting weather information. A graphic on the screen shows a comparison of temperatures from previous years and today, highlighting a slight increase. The text on the screen indicates a rise in temperature in the morning, with temperatures in Seoul ranging from -9.6°C yesterday to -9.3°C today, and the lowest temperature at -4.0°C. The current time displayed is 7:47 AM on the 12th day.",
"The news anchor, standing in front of the snowy mountain backdrop, continues presenting weather information. The graphic on the screen now emphasizes today's temperature compared to previous years, showing a slight rise. The text indicates that the morning temperature in Seoul has risen from -9.6°C yesterday to -9.3°C today, with the lowest temperature at -4.0°C. The time remains 7:47 AM on the 12th day, maintaining continuity with the previous frame's context.",
"The news anchor, standing in front of a cityscape backdrop, continues the weather report. The graphic on the screen highlights an area in yellow, labeled as \"내륙\" (inland), indicating a specific region of interest. The text on the screen reads \"일시 내륙,\" suggesting a forecast or alert related to the inland area. The time displayed is 7:47 AM on the 12th, consistent with the previous frame's timestamp, indicating continuity in the weather report presentation.",
"The news anchor, standing in front of a cityscape backdrop, continues the weather report. The graphic on the screen highlights an area in yellow, labeled as \"나쁜\" (bad), indicating a specific region of interest. The text on the screen reads \"일시 나쁜,\" suggesting a forecast or alert related to the bad area. The time displayed is 7:47 AM on the 12th, consistent with the previous frame's timestamp, indicating continuity in the weather report presentation.",
"The news anchor, still in front of the cityscape backdrop, continues the weather report. The graphic on the screen shows a map with different shades of blue and green, representing weather patterns. Two areas are circled in pink, with one labeled \"대설주의보\" (heavy snow warning), indicating regions of concern. The text \"레이더 영상\" (radar image) is displayed, suggesting the graphic is a live radar image. The time remains 7:47 AM on the 12th, maintaining continuity in the weather report.",
"The news anchor, still in front of the cityscape backdrop, continues the weather report. The graphic on the screen shows three maps of Korea, each indicating the expected snowfall for different time periods: 12~15, 15~18, and 18~21 hours. Different regions are shaded in purple and green, with green indicating areas of significant snowfall. The text \"눈 내리는 지역\" (areas with snowfall) and \"KBS1 12(화) 07:48\" (KBS1, Tuesday, 7:48 AM) is displayed, providing context for the weather forecast.",
"The news anchor is still presenting the weather forecast in front of a snowy cityscape backdrop. The graphic on the screen remains, showing three maps of Korea with expected snowfall for different time periods: 12~15, 15~18, and 18~21 hours. Different regions are shaded in purple and green, with green indicating significant snowfall areas. The text \"눈 내리는 지역\" (areas with snowfall) and \"KBS1 12(화) 07:48\" (KBS1, Tuesday, 7:48 AM) continues to be displayed, maintaining the weather report context.",
"The news anchor continues to present the weather forecast in front of a snowy cityscape backdrop. The graphic on the screen shows three maps of Korea with expected snowfall for different time periods: 12~15, 15~18, and 18~21 hours. Different regions are shaded in purple and green, with green indicating significant snowfall areas. The text \"눈 내리는 지역\" (areas with snowfall) and \"KBS1 12(화) 07:48\" (KBS1, Tuesday, 7:48 AM) is displayed, maintaining the weather report context."
] |
G7XGz4uL6mI
|
A news anchor presents a weather report in front of different backdrops, including a snowy mountain and a cityscape. The report compares today's temperatures to previous years, noting a slight rise in Seoul from -9.6°C to -9.3°C. The anchor highlights areas of interest, including inland regions and areas with bad weather, and issues forecasts and alerts, such as a heavy snow warning. The report includes live radar images and maps showing expected snowfall for different time periods, shading areas of significant snowfall in green. The presentation takes place on a Tuesday at 7:47-7:48 AM, with the anchor providing continuous updates on the weather situation.
|
In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.
|
[
"People bundling up in heavy clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in heavy clothing to brave the cold during record cold temperatures in East Asia, Southeast Asia, and South Asia in late January 2016",
"People bundling up in heavy clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong, during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia during late January 2016 snowfall events",
"Frost or ice formation on car windshields, roads, and buildings during the cold wave in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings during snowfall in East Asia, Southeast Asia, and South Asia in late January 2016",
"Residents in East Asia, Southeast Asia, and South Asia shoveling snow or using umbrellas to navigate snowy streets during the late January 2016 cold wave",
"Residents in East and South Asia shoveling snow or using umbrellas to navigate snowy streets during record cold temperatures in late January 2016",
"Residents shoveling snow or using umbrellas to navigate snowy streets in East Asia, Southeast Asia, or South Asia in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia Southeast Asia and South Asia during late January 2016"
] |
[
"People bundling up in warm clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in warm clothing to brave the cold in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People bundling up in warm clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"Frozen lakes and rivers with people ice skating or playing in East Asia Southeast Asia or South Asia during late January 2016 cold wave",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia where people are ice skating or playing during the record cold temperatures of late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, or South Asia where people are ice skating or playing in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia during late January 2016 cold wave",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia after snowfall in late January 2016",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 cold wave",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off sidewalks and driveways in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
[
"People bundling up in winter clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in winter clothing to brave the cold in East and South Asia during late January 2016 record cold snap",
"People bundling up in winter clothing to brave the cold during late January 2016 snowfall in East, Southeast, and South Asia",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during the cold wave of late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia due to record cold temperatures in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia after snowfall in late January 2016",
"Trees and buildings covered in snow and ice during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off streets and sidewalks in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_1%EC%9B%94_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%95%9C%ED%8C%8C",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, and the consequences of the snowfall, as these events are likely to be visualized in a video. The extracted events should be specific to the regions mentioned and the time of year, taking into account the typical climate and scenery of East Asia, mainland Southeast Asia, and northern South Asia in late January.\n\nEVENTS:\n1. People bundling up in winter clothing to brave the cold\n2. Snow falling in cities and towns\n3. Frozen lakes and rivers\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off streets and sidewalks",
"en_article_excerpt": "In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.",
"en_article_url": "https://en.wikipedia.org/wiki/January_2016_East_Asia_cold_wave",
"event_category": "disasters",
"event_name": "2016_east_asia_cold_wave",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, disruptions to daily life, and unusual weather phenomena like snowfall in regions that rarely see it. These events would be visually representative of the cold wave's impact and could be reasonably captured in a video.\n\nEVENTS:\n1. People bundling up in heavy clothing to brave the cold\n2. Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong\n3. Frost or ice forming on surfaces like car windshields, roads, and buildings\n4. Residents shoveling snow or using umbrellas to navigate snowy streets\n5. Cars and buses driving slowly on icy or snow-covered roads",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a cold wave, such as people dealing with the cold and snow, and disruptions to daily life. These events should be visual and concrete, and could be reasonably captured in a video of the cold wave's impact.\n\nEVENTS:\n1. People bundling up in warm clothing to brave the cold\n2. Snowplows clearing roads and highways\n3. Frozen lakes and rivers with people ice skating or playing\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off sidewalks and driveways",
"video_URL": "http://twitter.com/i/status/1346762056142188546",
"video_description": "눈보라 때문에 기절을 함",
"video_id": "1346762056142188546"
}
| 8
|
[
"The image depicts a snowy urban scene. Snow is visibly falling, covering the ground and creating a serene atmosphere. The buildings are illuminated with signs in Korean, indicating a commercial area. The street appears deserted, with no visible people or vehicles. The snowfall is heavy, indicating winter weather conditions.",
"The image continues to depict a snowy urban scene. Snowfall is still heavy, with snow visibly covering the ground, maintaining the serene atmosphere. The illuminated signs on the buildings remain visible, indicating the commercial area. The street is still deserted, with no visible people or vehicles, reinforcing the winter weather conditions and the quietness of the area.",
"The current frame maintains the depiction of a snowy urban scene, with heavy snowfall continuing to cover the ground, preserving the serene atmosphere. The illuminated signs on the buildings, including one reading 'JUNO HAIR,' are still visible, indicating the commercial area. The street remains deserted with no visible people or vehicles, reinforcing the winter weather conditions and the quietness of the area.",
"The snowfall persists in the urban setting, blanketing the streets and maintaining the calm ambiance. The 'JUNO HAIR' sign remains visible among the lit-up building signs, pointing to the commercial district. The street continues to be devoid of people or vehicles, emphasizing the ongoing winter weather and the tranquil atmosphere.",
"The snowfall continues in the urban setting, covering the streets and preserving the serene atmosphere. The 'JUNO HAIR' sign remains visible among the illuminated building signs, indicating the commercial district. The street is still devoid of people or vehicles, highlighting the ongoing winter weather and the tranquil ambiance.",
"The snowfall persists, with the 'JUNO HAIR' sign still visible amid the illuminated building signs, reinforcing the setting's commercial nature. The street remains empty, devoid of people or vehicles, which accentuates the quiet and peaceful atmosphere due to the winter weather.",
"The snowfall continues, blanketing the street and maintaining the serene, undisturbed ambiance. The 'JUNO HAIR' sign and other illuminated storefronts are still visible, suggesting a commercial area. The street remains devoid of people and vehicles, emphasizing the tranquil setting under the heavy snowfall.",
"The snowfall persists, continuing to blanket the street and maintaining the serene, undisturbed ambiance. The 'JUNO HAIR' sign and other illuminated storefronts are still visible, suggesting a commercial area. The street remains devoid of people and vehicles, emphasizing the tranquil setting under the heavy snowfall."
] |
1346762056142188546
|
The video depicts a serene and tranquil urban scene during heavy snowfall in a commercial area of a Korean city. The streets are completely deserted, with no people or vehicles visible throughout the video. The scene is dominated by the heavy snowfall, which blankets the ground and creates a peaceful atmosphere. Illuminated signs on buildings, including one for 'JUNO HAIR,' indicate the commercial nature of the area. The video showcases a consistent and undisturbed winter wonderland scene, with the snowfall being the primary focus and the commercial district providing the backdrop.
|
In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.
|
[
"People bundling up in heavy clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in heavy clothing to brave the cold during record cold temperatures in East Asia, Southeast Asia, and South Asia in late January 2016",
"People bundling up in heavy clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong, during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia during late January 2016 snowfall events",
"Frost or ice formation on car windshields, roads, and buildings during the cold wave in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings during snowfall in East Asia, Southeast Asia, and South Asia in late January 2016",
"Residents in East Asia, Southeast Asia, and South Asia shoveling snow or using umbrellas to navigate snowy streets during the late January 2016 cold wave",
"Residents in East and South Asia shoveling snow or using umbrellas to navigate snowy streets during record cold temperatures in late January 2016",
"Residents shoveling snow or using umbrellas to navigate snowy streets in East Asia, Southeast Asia, or South Asia in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia Southeast Asia and South Asia during late January 2016"
] |
[
"People bundling up in warm clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in warm clothing to brave the cold in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People bundling up in warm clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"Frozen lakes and rivers with people ice skating or playing in East Asia Southeast Asia or South Asia during late January 2016 cold wave",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia where people are ice skating or playing during the record cold temperatures of late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, or South Asia where people are ice skating or playing in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia during late January 2016 cold wave",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia after snowfall in late January 2016",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 cold wave",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off sidewalks and driveways in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
[
"People bundling up in winter clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in winter clothing to brave the cold in East and South Asia during late January 2016 record cold snap",
"People bundling up in winter clothing to brave the cold during late January 2016 snowfall in East, Southeast, and South Asia",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during the cold wave of late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia due to record cold temperatures in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia after snowfall in late January 2016",
"Trees and buildings covered in snow and ice during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off streets and sidewalks in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_1%EC%9B%94_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%95%9C%ED%8C%8C",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, and the consequences of the snowfall, as these events are likely to be visualized in a video. The extracted events should be specific to the regions mentioned and the time of year, taking into account the typical climate and scenery of East Asia, mainland Southeast Asia, and northern South Asia in late January.\n\nEVENTS:\n1. People bundling up in winter clothing to brave the cold\n2. Snow falling in cities and towns\n3. Frozen lakes and rivers\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off streets and sidewalks",
"en_article_excerpt": "In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.",
"en_article_url": "https://en.wikipedia.org/wiki/January_2016_East_Asia_cold_wave",
"event_category": "disasters",
"event_name": "2016_east_asia_cold_wave",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, disruptions to daily life, and unusual weather phenomena like snowfall in regions that rarely see it. These events would be visually representative of the cold wave's impact and could be reasonably captured in a video.\n\nEVENTS:\n1. People bundling up in heavy clothing to brave the cold\n2. Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong\n3. Frost or ice forming on surfaces like car windshields, roads, and buildings\n4. Residents shoveling snow or using umbrellas to navigate snowy streets\n5. Cars and buses driving slowly on icy or snow-covered roads",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a cold wave, such as people dealing with the cold and snow, and disruptions to daily life. These events should be visual and concrete, and could be reasonably captured in a video of the cold wave's impact.\n\nEVENTS:\n1. People bundling up in warm clothing to brave the cold\n2. Snowplows clearing roads and highways\n3. Frozen lakes and rivers with people ice skating or playing\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off sidewalks and driveways",
"video_URL": "http://twitter.com/i/status/1346961474866925570",
"video_description": "눈보라가 휘날리는 바람 찬 부산 시청 #풍산",
"video_id": "1346961474866925570"
}
| 8
|
[
"A person in a black coat stands on a sidewalk beside a road marked with pedestrian crosswalks. They appear to be looking down at something in their hands. The road is lined with traffic cones, and the environment has leafless trees and buildings in the background. The weather seems overcast, and there is a small amount of snow visible on the ground.",
"The scene continues to depict a cold, snowy urban environment. The individual in the black coat, who was previously seen looking down, is now positioned next to a silver van parked on the side of the street. The van's door is open, indicating the person might be interacting with the vehicle, perhaps retrieving or placing an item inside. The presence of the van and the person's engagement with it suggest a continuation of the activity that was hinted at in the previous frame. The snowy sidewalk and the overcast sky remain consistent with the earlier depiction, reinforcing the cold weather setting.",
"The scene continues in the cold, snowy urban environment. The individual in the black coat is now standing at the edge of the crosswalk, looking towards the street. They appear to be waiting or observing the traffic. The crosswalk is partially covered with snow, and there are orange traffic cones lining the street, indicating some roadwork or restriction. The overall atmosphere remains consistent with the earlier frames, reinforcing the cold and somewhat desolate urban setting.",
"The individual in the black coat is still standing at the edge of the crosswalk, maintaining their position to observe the traffic. The snowy crosswalk and the orange traffic cones continue to line the street, indicating ongoing roadwork or restrictions. The atmosphere remains consistent with the earlier frames, emphasizing the cold and somewhat desolate urban environment.",
"The individual in the black coat is still standing at the edge of the crosswalk, maintaining their position to observe the traffic. The snowy crosswalk and the orange traffic cones continue to line the street, indicating ongoing roadwork or restrictions. The atmosphere remains consistent with the earlier frames, emphasizing the cold and somewhat desolate urban environment.",
"The individual in the black coat is standing at the edge of the crosswalk, looking towards the street with a focused expression, possibly anticipating a change in traffic flow. The snowy crosswalk and the orange traffic cones are still present, indicating ongoing roadwork or restrictions. The atmosphere continues to reflect the cold and somewhat desolate urban environment, with no significant changes in the scene.",
"The individual in the black coat is now slightly more relaxed and no longer looking towards the street, suggesting they might be waiting for a break in the traffic or simply taking a moment to pause. The snowy crosswalk and the orange traffic cones remain visible, reinforcing the ongoing roadwork or restrictions. The atmosphere continues to reflect the cold and somewhat desolate urban environment, with no significant changes in the scene.",
"In the current frame, the individual in the black coat continues to wait on the sidewalk, maintaining a relaxed posture and not appearing to interact with the surroundings. The white van with its rear door open is still present, indicating ongoing activity or work. The crosswalk remains snowy, and the orange traffic cones continue to suggest roadwork or restrictions. The urban setting appears quiet and desolate, with no notable changes in the environment or activity."
] |
1346961474866925570
|
A person in a black coat is depicted in a cold, snowy urban environment, initially standing on a sidewalk beside a road marked with pedestrian crosswalks and lined with traffic cones. The individual interacts with a silver van, possibly retrieving or placing an item, before proceeding to wait at the edge of the crosswalk, observing the traffic. They maintain this position for some time, occasionally relaxing, as they appear to wait for a break in traffic or a change in their circumstances. The setting remains consistent throughout, with leafless trees, buildings, and ongoing roadwork or restrictions indicated by orange traffic cones. The atmosphere is cold and somewhat desolate, with the person's actions suggesting they are engaged in a task or waiting for something, but the exact nature of their activity or purpose is not clearly defined.
|
In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.
|
[
"People bundling up in heavy clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in heavy clothing to brave the cold during record cold temperatures in East Asia, Southeast Asia, and South Asia in late January 2016",
"People bundling up in heavy clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong, during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia during late January 2016 snowfall events",
"Frost or ice formation on car windshields, roads, and buildings during the cold wave in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings during snowfall in East Asia, Southeast Asia, and South Asia in late January 2016",
"Residents in East Asia, Southeast Asia, and South Asia shoveling snow or using umbrellas to navigate snowy streets during the late January 2016 cold wave",
"Residents in East and South Asia shoveling snow or using umbrellas to navigate snowy streets during record cold temperatures in late January 2016",
"Residents shoveling snow or using umbrellas to navigate snowy streets in East Asia, Southeast Asia, or South Asia in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia Southeast Asia and South Asia during late January 2016"
] |
[
"People bundling up in warm clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in warm clothing to brave the cold in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People bundling up in warm clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"Frozen lakes and rivers with people ice skating or playing in East Asia Southeast Asia or South Asia during late January 2016 cold wave",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia where people are ice skating or playing during the record cold temperatures of late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, or South Asia where people are ice skating or playing in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia during late January 2016 cold wave",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia after snowfall in late January 2016",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 cold wave",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off sidewalks and driveways in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
[
"People bundling up in winter clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in winter clothing to brave the cold in East and South Asia during late January 2016 record cold snap",
"People bundling up in winter clothing to brave the cold during late January 2016 snowfall in East, Southeast, and South Asia",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during the cold wave of late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia due to record cold temperatures in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia after snowfall in late January 2016",
"Trees and buildings covered in snow and ice during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off streets and sidewalks in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_1%EC%9B%94_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%95%9C%ED%8C%8C",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, and the consequences of the snowfall, as these events are likely to be visualized in a video. The extracted events should be specific to the regions mentioned and the time of year, taking into account the typical climate and scenery of East Asia, mainland Southeast Asia, and northern South Asia in late January.\n\nEVENTS:\n1. People bundling up in winter clothing to brave the cold\n2. Snow falling in cities and towns\n3. Frozen lakes and rivers\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off streets and sidewalks",
"en_article_excerpt": "In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.",
"en_article_url": "https://en.wikipedia.org/wiki/January_2016_East_Asia_cold_wave",
"event_category": "disasters",
"event_name": "2016_east_asia_cold_wave",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, disruptions to daily life, and unusual weather phenomena like snowfall in regions that rarely see it. These events would be visually representative of the cold wave's impact and could be reasonably captured in a video.\n\nEVENTS:\n1. People bundling up in heavy clothing to brave the cold\n2. Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong\n3. Frost or ice forming on surfaces like car windshields, roads, and buildings\n4. Residents shoveling snow or using umbrellas to navigate snowy streets\n5. Cars and buses driving slowly on icy or snow-covered roads",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a cold wave, such as people dealing with the cold and snow, and disruptions to daily life. These events should be visual and concrete, and could be reasonably captured in a video of the cold wave's impact.\n\nEVENTS:\n1. People bundling up in warm clothing to brave the cold\n2. Snowplows clearing roads and highways\n3. Frozen lakes and rivers with people ice skating or playing\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off sidewalks and driveways",
"video_URL": "http://youtube.com/watch?v=PxIbNGPQYw8",
"video_description": "지난주 부터 계속되는 한파에 SNS 등에서는 순간포착 영상인 이른바 '얼었어' 시리즈가 유행하고 있다고 합니다. https://imnews.imbc.com/replay/2021/nwtoday/article/6054105_34943.html #한파, #SNS, #얼었어시리즈",
"video_id": "PxIbNGPQYw8"
}
| 8
|
[
"The image shows a television news broadcast with two men standing on either side of a large screen displaying text in Korean. They appear to be news anchors or reporters discussing a topic related to the text on the screen. The background features a cityscape at night. The text on the screen references \"중고차 시장\" and \"买车 10年新车10倍增加,\" indicating a discussion about the used car market and a significant increase in new cars over 10 years. The image also displays the time \"11월 7:16\" (November 7:16) and the logo \"MBC,\" suggesting it is from a broadcast of that network.",
"The television news broadcast continues with the two men standing on either side of the screen, still engaged in discussion. The text on the screen now reads \"한국 이거는 '열렸어' 시리즈\" and \"강추위에도 '열죽아,'\" suggesting a focus on a series called \"열렸어\" and a commentary on enduring cold weather. The background remains the cityscape at night, and the time \"11월 7:16\" and the logo \"MBC\" are still visible, maintaining the continuity of the broadcast.",
"The television news broadcast now features a single man in the center of the screen, delivering the news. The background continues to display a cityscape at night, and the time \"11월 7:17\" is visible in the top right corner, indicating a minute has passed from the previous frame. The text on the screen reads \"뉴스 투데이\" and \"경제,\" suggesting a shift in focus to economic news. The man is dressed in a dark suit with a red tie and appears to be reading from notes. The weather information \"동해 -6°\" is displayed, indicating cold weather conditions.",
"The video shows a collage of three images related to consumer goods. The first image on the left features a hand opening a package of baby wipes. The middle image displays a hand holding a clear plastic bottle filled with a brownish substance, possibly a beverage, with a red and white label. The third image on the right shows a bottle of Coca-Cola Zero Sugar. The text across the bottom of the collage reads \"최강 한국에 '열렸어' 시리즈 등장,\" suggesting that a series related to Korea has appeared or is being discussed. The weather information \"청주 -9°\" indicates cold weather in the location mentioned. The images likely relate to a news segment discussing consumer goods or a new product series in Korea.",
"The video continues with a collage of images related to consumer goods. The first image on the left shows three yellow, gelatinous objects in a bowl with a floral pattern. The second image on the right displays a hand holding two halves of a brown object, which appear to be cracked open, revealing a yellow interior. The text at the bottom of the collage reads \"최강 한국에 '열렸어' 시리즈 등장,\" indicating that a series related to Korea has appeared or is being discussed. The weather information \"전주 -6°\" indicates cold weather in the location mentioned. The images suggest a news segment discussing a new product series in Korea, possibly highlighting a specific item or its popularity.",
"The video continues with a collage of images related to consumer goods and news. On the left, there is an image of a water tap with water flowing from it, indicating the presence of water. On the right, there is an image of a dish with noodles being lifted from a bowl with chopsticks, suggesting a food item. The text at the bottom of the collage reads \"전국 계량기 동파 사고 5,000여 건\" which translates to \"5,000 or more water meter freezing accidents nationwide,\" indicating a news segment discussing a significant number of incidents where water meters have frozen and possibly malfunctioned or been damaged due to the cold weather. The text at the top right corner shows \"MBC 11 (수) 7:17,\" suggesting that this is a news segment broadcasted on MBC channel at 7:17 PM on Wednesday. The images and text together suggest a news segment discussing the impact of cold weather on infrastructure and daily life, specifically focusing on the freezing of water meters.",
"The video continues to address the cold weather impacts, now focusing on an individual opening a panel to reveal a water meter. The text at the top left reads \"뉴스 투데이,\" indicating it's a news segment, while the text at the bottom left states \"사회,\" suggesting a societal issue is being discussed. The person, wearing a sleeve, is performing maintenance or inspection on the water meter, which appears to be at risk of freezing due to the cold conditions. The text at the bottom of the frame shows \"서울 -9°\" indicating the current temperature in Seoul is -9 degrees Celsius. This frame likely continues the theme of the previous frame, highlighting the ongoing challenges faced due to cold weather and its effects on infrastructure.",
"In this frame, a person is seen opening a panel to inspect or maintain a water meter, continuing the focus on the cold weather impacts. The text \"뉴스 투데이\" in the top left corner indicates that this is part of a news segment, and the societal issue of infrastructure maintenance in freezing conditions is being highlighted. The person, still wearing a sleeve, is performing the task carefully. The text at the bottom left corner reads \"사회,\" reinforcing the societal context of the segment. The temperature in Seoul is shown to be -9 degrees Celsius, emphasizing the ongoing challenges of maintaining infrastructure in such cold conditions."
] |
PxIbNGPQYw8
|
A television news broadcast on MBC discusses various topics, starting with the used car market and its significant increase over 10 years. The broadcast then shifts to a series called "열렸어" and comments on the cold weather. The news anchors transition to economic news, "뉴스 투데이," and report on cold weather conditions, displaying temperatures from different locations. The broadcast features collages of images related to consumer goods, possibly highlighting new products or series in Korea. However, the focus shifts to the impact of cold weather on infrastructure, specifically the freezing of water meters, with reports of over 5,000 accidents nationwide. The news segment shows individuals inspecting and maintaining water meters to prevent or address freezing issues, emphasizing the societal challenges posed by the cold weather, particularly in maintaining essential services in Seoul and other areas where temperatures have dropped significantly.
|
Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.
|
[
"Heavy rains and floods in the southern Korean Peninsula during summer 2020",
"Heavy rains pouring down in southern South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North and South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during the summer floods of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during heavy rains in summer 2020",
"Rescue teams navigating boats through flooded streets to reach stranded residents during the summer floods of 2020 in North and South Korea",
"Rescue teams navigating boats through flooded streets to reach stranded residents in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after floods in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after heavy rains in North and South Korea during the summer of 2020"
] |
[
"People evacuating flooded homes and buildings in the Korean Peninsula during the summer rainy season of 2020",
"People evacuating flooded homes and buildings in the Korean Peninsula during summer 2020 heavy rains",
"Cars and buildings submerged in floodwater in North Korea and South Korea during the summer floods of 2020",
"Cars and buildings submerged in floodwater during heavy rains in the Korean Peninsula in summer 2020",
"Emergency responders rescuing people from flooded areas in North Korea and South Korea during the summer rainy season of 2020",
"Emergency responders rescuing people from flooded areas in North and South Korea during heavy rains in the summer of 2020",
"Debris and wreckage from destroyed buildings and infrastructure due to floods in North and South Korea during the summer 2020 rainy season",
"Debris and wreckage from destroyed buildings and infrastructure in North Korea, South Korea, and the Korean Peninsula after heavy rains during the summer rainy season of June-August 2020",
"Residents clearing mud and water from their homes and streets after floods in the Korean Peninsula during the summer 2020 rainy season",
"Residents clearing mud and water from their homes and streets in North and South Korea after heavy rains during the summer rainy season of 2020"
] |
[
"Floodwaters inundating homes and buildings in southern Korea, particularly in South Korea, during the summer rainy season of 2020",
"Floodwaters inundating homes and buildings in southern Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North and South Korea during heavy rains in summer 2020",
"Rescue workers helping those stranded by the floods in North Korea and South Korea during the summer rainy season of 2020",
"Rescue workers helping those stranded by floods in the Korean Peninsula during the summer rainy season of 2020",
"Cars and buildings submerged in water during floods in North and South Korea, Korean Peninsula, Summer 2020",
"Cars and buildings submerged in water in North and South Korea during heavy rains in summer 2020",
"Emergency responders distributing aid and supplies to communities affected by floods in North Korea and South Korea during the summer rainy season of June to August 2020",
"Emergency responders distributing aid and supplies to affected communities in North and South Korea during heavy rains in the summer of 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2020%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact of floods and heavy rains in Korea, such as scenes of flooding, damage, and rescue efforts, as these are likely to be visualized in a video about the event. The extracted events should be specific to the region and the time of year, taking into account the regional rainy season and the areas most affected by the floods.\n\nEVENTS:\n1. Floodwaters inundating homes and buildings in southern Korea\n2. People evacuating flooded areas by boat\n3. Rescue workers helping those stranded by the floods\n4. Cars and buildings submerged in water\n5. Emergency responders distributing aid and supplies to affected communities",
"en_article_excerpt": "Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Korean_floods",
"event_category": "disasters",
"event_name": "2020_korean_floods",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the cause and effects of the flooding, such as scenes of heavy rainfall, flooded areas, and rescue efforts. These events are likely to be visualized in a video documenting the floods and their impact on the region.\n\nEVENTS:\n1. Heavy rains pouring down in the southern parts of the Korean Peninsula\n2. Rivers overflowing and flooding nearby cities and towns\n3. People evacuating their homes and seeking higher ground\n4. Rescue teams navigating boats through flooded streets to reach stranded residents\n5. Cars and buildings submerged in water with debris scattered around",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the consequences of flooding and heavy rainfall, such as damage to infrastructure, evacuation efforts, and scenes of flooding. These events are likely to be visualized in a video capturing the impact of the floods on the region.\n\nEVENTS:\n1. People evacuating flooded homes and buildings\n2. Cars and buildings submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Debris and wreckage from destroyed buildings and infrastructure\n5. Residents clearing mud and water from their homes and streets",
"video_URL": "http://youtube.com/watch?v=SPZkwqJerMU",
"video_description": "2020년 홍수 피해 주민들에 1천483억원 보상 2020년 여름 기나긴 장마로 큰 홍수 피해를 당한 주민들이 총 1천480여억원의 보상금을 지급받게 됐습니다. 환경부 소속 중앙환경분쟁조정위원회는 홍수 피해를 본 주민들과 정부, 지자체 및 한국수자원공사 간 분쟁조정 절차가 최근 마무리됐다고 밝혔습니다. 조정위는 관계부처 원인 조사에서 댐·하천을 미흡하게 관리한 사실이 드러난 점 등을 고려했다고 밝혔습니다. 연합뉴스TV 기사문의 및 제보 : 카톡/라인 jebo23 ▣ 연합뉴스TV 유튜브 채널 구독 https://goo.gl/VuCJMi ▣ 대한민국 뉴스의 시작 연합뉴스TV / Yonhap News TV http://www.yonhapnewstv.co.kr/",
"video_id": "SPZkwqJerMU"
}
| 8
|
[
"A news anchor is reporting from a studio with a backdrop of a night cityscape. The headline displayed on the screen reads \"2020년 홍수 피해 주민들에게 1천483억원 보상\" which translates to \"1.483 trillion won compensation to residents affected by the 2020 flood.\"",
"The image shows a large pile of debris, including various household items, furniture, and garbage, indicating the aftermath of a flood. The text on the screen states \"연합뉴스TV\" and \"2020년 홍수 피해 주민들에게 1천483억원 보상\" which reiterates the compensation amount of 1.483 trillion won to those affected by the 2020 flood. The bottom ticker displays weather information for Seoul.",
"The current frame continues to depict the aftermath of a flood, with a large mound of debris, including a variety of household items, furniture, and garbage, visible in the foreground. The background shows turbulent, muddy floodwaters, suggesting the receding flood. The text \"연합뉴스TV\" and \"2020년 홍수 피해 주민들에게 1천483억원 보상\" remains on the screen, emphasizing the compensation amount of 1.483 trillion won for the flood-affected residents. The bottom ticker still displays the weather information for Seoul.",
"The current frame shows an area with debris, including damaged household items, furniture, and garbage scattered across the scene. The background reveals a mountainous region, and the sky appears overcast, contributing to the sense of aftermath. The text \"연합뉴스TV\" and \"2020년 홍수 피해 주민들에게 1천483억원 보상\" remains on the screen, reiterating the compensation for the flood-affected residents. The bottom ticker continues to show weather information for Seoul.",
"The image shows an area filled with debris, including a large tire, broken household items, and garbage, indicating the aftermath of a flood. The text \"연합뉴스TV\" is visible, along with the headline \"2020년 홍수 피해 주민들에게 1천483억원 보상,\" which translates to \"1.483 trillion won compensation for residents affected by the 2020 flood.\" The background includes a mountainous region, and the sky is overcast, adding to the somber atmosphere. The bottom ticker displays weather information for Seoul, with temperatures around 5.2°C.",
"The scene remains focused on the aftermath of the flood, with the foreground displaying a mix of rubble and debris. A building with a dark roof is visible, likely part of a structure affected by the disaster. The same headline from the previous frame, \"2020년 홍수 피해 주민들에게 1천483억원 보상,\" reiterates the compensation announcement for the affected residents. The environment remains consistent with signs of flood damage, suggesting the video is documenting the extensive impact of the 2020 flood on the community.",
"The current frame continues to depict the aftermath of the flood, focusing on a large pile of debris and rubble. The environment shows extensive damage, with visible wooden planks, metal sheets, and other debris scattered around. A speed limit sign is partially visible, indicating that this scene is likely near a road or highway. The overall atmosphere suggests ongoing recovery efforts and the significant impact of the disaster on the community.",
"The scene appears to be the aftermath of an event, with several objects covered in tarpaulin, suggesting an ongoing cleanup or restoration effort. Red caution tape indicates restricted access, possibly for safety reasons. A building in the background has partially open windows, and there are various items such as a wheel and wooden furniture scattered around. The text \"연합뉴스TV\" and \"광주 6,985\" suggest this is a news broadcast covering the aftermath in Gwangju, where the number 6,985 could indicate a significant figure, possibly related to the event."
] |
SPZkwqJerMU
|
A news report from 연합뉴스TV covers the aftermath of the 2020 flood in South Korea, announcing 1.483 trillion won in compensation for affected residents. The video shows extensive damage and debris in various locations, including mountainous regions, with household items, furniture, and garbage scattered across the scenes. The report likely takes place in Gwangju, with the number 6,985 possibly indicating a significant figure related to the event. The footage depicts ongoing recovery efforts, with restricted access areas, cleanup efforts, and damaged buildings. The overall context suggests a significant natural disaster with a substantial impact on the community, prompting a large-scale compensation package and ongoing restoration work.
|
Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.
|
[
"Heavy rains and floods in the southern Korean Peninsula during summer 2020",
"Heavy rains pouring down in southern South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North and South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during the summer floods of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during heavy rains in summer 2020",
"Rescue teams navigating boats through flooded streets to reach stranded residents during the summer floods of 2020 in North and South Korea",
"Rescue teams navigating boats through flooded streets to reach stranded residents in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after floods in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after heavy rains in North and South Korea during the summer of 2020"
] |
[
"People evacuating flooded homes and buildings in the Korean Peninsula during the summer rainy season of 2020",
"People evacuating flooded homes and buildings in the Korean Peninsula during summer 2020 heavy rains",
"Cars and buildings submerged in floodwater in North Korea and South Korea during the summer floods of 2020",
"Cars and buildings submerged in floodwater during heavy rains in the Korean Peninsula in summer 2020",
"Emergency responders rescuing people from flooded areas in North Korea and South Korea during the summer rainy season of 2020",
"Emergency responders rescuing people from flooded areas in North and South Korea during heavy rains in the summer of 2020",
"Debris and wreckage from destroyed buildings and infrastructure due to floods in North and South Korea during the summer 2020 rainy season",
"Debris and wreckage from destroyed buildings and infrastructure in North Korea, South Korea, and the Korean Peninsula after heavy rains during the summer rainy season of June-August 2020",
"Residents clearing mud and water from their homes and streets after floods in the Korean Peninsula during the summer 2020 rainy season",
"Residents clearing mud and water from their homes and streets in North and South Korea after heavy rains during the summer rainy season of 2020"
] |
[
"Floodwaters inundating homes and buildings in southern Korea, particularly in South Korea, during the summer rainy season of 2020",
"Floodwaters inundating homes and buildings in southern Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North and South Korea during heavy rains in summer 2020",
"Rescue workers helping those stranded by the floods in North Korea and South Korea during the summer rainy season of 2020",
"Rescue workers helping those stranded by floods in the Korean Peninsula during the summer rainy season of 2020",
"Cars and buildings submerged in water during floods in North and South Korea, Korean Peninsula, Summer 2020",
"Cars and buildings submerged in water in North and South Korea during heavy rains in summer 2020",
"Emergency responders distributing aid and supplies to communities affected by floods in North Korea and South Korea during the summer rainy season of June to August 2020",
"Emergency responders distributing aid and supplies to affected communities in North and South Korea during heavy rains in the summer of 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2020%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact of floods and heavy rains in Korea, such as scenes of flooding, damage, and rescue efforts, as these are likely to be visualized in a video about the event. The extracted events should be specific to the region and the time of year, taking into account the regional rainy season and the areas most affected by the floods.\n\nEVENTS:\n1. Floodwaters inundating homes and buildings in southern Korea\n2. People evacuating flooded areas by boat\n3. Rescue workers helping those stranded by the floods\n4. Cars and buildings submerged in water\n5. Emergency responders distributing aid and supplies to affected communities",
"en_article_excerpt": "Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Korean_floods",
"event_category": "disasters",
"event_name": "2020_korean_floods",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the cause and effects of the flooding, such as scenes of heavy rainfall, flooded areas, and rescue efforts. These events are likely to be visualized in a video documenting the floods and their impact on the region.\n\nEVENTS:\n1. Heavy rains pouring down in the southern parts of the Korean Peninsula\n2. Rivers overflowing and flooding nearby cities and towns\n3. People evacuating their homes and seeking higher ground\n4. Rescue teams navigating boats through flooded streets to reach stranded residents\n5. Cars and buildings submerged in water with debris scattered around",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the consequences of flooding and heavy rainfall, such as damage to infrastructure, evacuation efforts, and scenes of flooding. These events are likely to be visualized in a video capturing the impact of the floods on the region.\n\nEVENTS:\n1. People evacuating flooded homes and buildings\n2. Cars and buildings submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Debris and wreckage from destroyed buildings and infrastructure\n5. Residents clearing mud and water from their homes and streets",
"video_URL": "http://youtube.com/watch?v=mtt7-wXFwxI",
"video_description": "(서울=뉴스1) 김연수 기자 = 지난 1일부터 전국을 강타하고 있는 집중호우로 전국에서 피해가 속출하고 있습니다. 특히 큰 비가 내린 남부 지방을 중심으로 지난 7일 이후 1만1717건의 시설피해가 집계됐다. 섬진강댐 하류 제방이 붕괴돼 주민들이 긴급대피했고 화동군 화개장터가 32년 만에 침수됐습니다. 도로와 교량, 주택 등 1만7879건의 시설피해가 접수된 가운데 제5호 태풍 '장미'가 북상하면서 피해 규모가 더욱 커질 것으로 전망되는데요. 수마가 할퀴고 간 자리 영상으로 확인해보세요. #장마 #홍수피해 #홍수 #물폭탄",
"video_id": "mtt7-wXFwxI"
}
| 8
|
[
"The image shows a flooded street with muddy water covering the pavement. In the background, there are shops with awnings and signs. Text in the foreground reads \"주민 3000여명 대피,\" which translates to \"Over 3000 residents evacuated.\" The scene indicates a response to flooding or a similar emergency.",
"In the current frame, rescue personnel in red and orange gear are navigating a flooded street, using a raft to move through the water. They are seen guiding the raft, likely aiding in the evacuation or rescue operation of the affected residents. The street is filled with muddy water, and shops line the background, with one displaying the text \"레드스토어\" (Red Store). The scene emphasizes the ongoing emergency response efforts amidst the flood situation.",
"The image shows an aerial view of a flooded area with muddy water covering much of the landscape. There is a narrow path, possibly a road or a trail, running through the flooded area. In the foreground, a small building or structure is partially submerged in the water. The text on the image reads \"장천배수장 난동강 철봉괴\" and \"마을 침수,\" which translates to \"Jangcheon Pumping Station, Nandoongang Pier, Village Flooded.\" This indicates that the flooding is severe enough to have affected a village, with emergency response efforts likely ongoing to address the situation.",
"The image shows an aerial view of a flooded area with muddy water covering much of the landscape. There is a narrow path, possibly a road or a trail, running through the flooded area. In the foreground, a small building or structure is partially submerged in the water. The text on the image reads \"장천배수장 난동강 철봉괴\" and \"마을 침수,\" which translates to \"Jangcheon Pumping Station, Nandoongang Pier, Village Flooded.\" This indicates that the flooding is severe enough to have affected a village, with emergency response efforts likely ongoing to address the situation.",
"In the current frame, the focus shifts to a person, possibly a local resident or emergency responder, navigating through the flooded area. They are wearing a red vest and holding onto a makeshift rope or line, likely to stay afloat in the high water levels. The person is carrying a bright green bag, which could contain essential items or supplies needed for the flood response. The background shows a house partially submerged in the floodwaters, indicating the extent of the flooding in the area. The text \"338명 박살\" translates to \"338 people devastated,\" suggesting a significant number of people have been affected by the flood. The presence of the text \"뉴스1TV\" indicates that this footage is from a news broadcast, highlighting the urgency and scale of the situation.",
"The current frame shows a flooded area with muddy brown water flowing rapidly, possibly during a flood event. A person is seen standing in the water, holding onto a railing or fence, seemingly observing the flood. The text \"극한\" is displayed prominently, which translates to \"extreme,\" suggesting the severity of the situation. In the background, there are trees and what appears to be a building or structure on higher ground, indicating that the floodwaters have submerged the lower areas. The presence of the text \"뉴스1TV\" again confirms that this footage is from a news broadcast, emphasizing the urgent nature of the flood conditions.",
"The current frame displays a widespread flood with a significant area inundated by muddy water. Several buildings, including a multi-story structure, are visible amidst the floodwaters. The text '제5호 태풍 '장미' 북상' (Typhoon 'Rose' Approaching) indicates the cause of the flooding. A specific mention of '10일 부산기상청 태풍주의보 발효' (Typhoon Warning Issued by Busan Meteorological Agency on the 10th) provides information on the emergency measures taken. The footage, labeled '뉴스1TV' (News 1 TV), highlights the severity and extent of the flooding caused by the approaching typhoon.",
"The current frame shows a blue gradient background with white Korean text. The text reads '뉴스1TV' at the top, indicating the broadcasting channel. Below, the text lists the key elements of the current segment: '영상 | 전남소방본부 등' on the left, indicating that the video footage is sourced from the Jeollanam-do Fire Department, and '제작 | 김연수' on the right, crediting the segment's production to Kim Yeon-su. This frame serves as a transition or credit screen, providing information about the content sources and production credits."
] |
mtt7-wXFwxI
|
A severe flood, caused by Typhoon Rose, has affected a village, prompting a large-scale evacuation and emergency response effort. Over 3000 residents were evacuated, with rescue personnel in red and orange gear navigating the flooded streets using rafts to aid in the evacuation. The flooding has submerged buildings, roads, and landscapes, with muddy water covering much of the area. The situation is described as "extreme," with 338 people reported to be devastated by the flood. News footage from News 1 TV shows the extent of the flooding, with emergency responders and residents navigating the high water levels. The Jeollanam-do Fire Department is involved in the response efforts, and the situation is being closely monitored and reported on by the news channel.
|
Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.
|
[
"Heavy rains and floods in the southern Korean Peninsula during summer 2020",
"Heavy rains pouring down in southern South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North and South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during the summer floods of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during heavy rains in summer 2020",
"Rescue teams navigating boats through flooded streets to reach stranded residents during the summer floods of 2020 in North and South Korea",
"Rescue teams navigating boats through flooded streets to reach stranded residents in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after floods in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after heavy rains in North and South Korea during the summer of 2020"
] |
[
"People evacuating flooded homes and buildings in the Korean Peninsula during the summer rainy season of 2020",
"People evacuating flooded homes and buildings in the Korean Peninsula during summer 2020 heavy rains",
"Cars and buildings submerged in floodwater in North Korea and South Korea during the summer floods of 2020",
"Cars and buildings submerged in floodwater during heavy rains in the Korean Peninsula in summer 2020",
"Emergency responders rescuing people from flooded areas in North Korea and South Korea during the summer rainy season of 2020",
"Emergency responders rescuing people from flooded areas in North and South Korea during heavy rains in the summer of 2020",
"Debris and wreckage from destroyed buildings and infrastructure due to floods in North and South Korea during the summer 2020 rainy season",
"Debris and wreckage from destroyed buildings and infrastructure in North Korea, South Korea, and the Korean Peninsula after heavy rains during the summer rainy season of June-August 2020",
"Residents clearing mud and water from their homes and streets after floods in the Korean Peninsula during the summer 2020 rainy season",
"Residents clearing mud and water from their homes and streets in North and South Korea after heavy rains during the summer rainy season of 2020"
] |
[
"Floodwaters inundating homes and buildings in southern Korea, particularly in South Korea, during the summer rainy season of 2020",
"Floodwaters inundating homes and buildings in southern Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North and South Korea during heavy rains in summer 2020",
"Rescue workers helping those stranded by the floods in North Korea and South Korea during the summer rainy season of 2020",
"Rescue workers helping those stranded by floods in the Korean Peninsula during the summer rainy season of 2020",
"Cars and buildings submerged in water during floods in North and South Korea, Korean Peninsula, Summer 2020",
"Cars and buildings submerged in water in North and South Korea during heavy rains in summer 2020",
"Emergency responders distributing aid and supplies to communities affected by floods in North Korea and South Korea during the summer rainy season of June to August 2020",
"Emergency responders distributing aid and supplies to affected communities in North and South Korea during heavy rains in the summer of 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2020%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact of floods and heavy rains in Korea, such as scenes of flooding, damage, and rescue efforts, as these are likely to be visualized in a video about the event. The extracted events should be specific to the region and the time of year, taking into account the regional rainy season and the areas most affected by the floods.\n\nEVENTS:\n1. Floodwaters inundating homes and buildings in southern Korea\n2. People evacuating flooded areas by boat\n3. Rescue workers helping those stranded by the floods\n4. Cars and buildings submerged in water\n5. Emergency responders distributing aid and supplies to affected communities",
"en_article_excerpt": "Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Korean_floods",
"event_category": "disasters",
"event_name": "2020_korean_floods",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the cause and effects of the flooding, such as scenes of heavy rainfall, flooded areas, and rescue efforts. These events are likely to be visualized in a video documenting the floods and their impact on the region.\n\nEVENTS:\n1. Heavy rains pouring down in the southern parts of the Korean Peninsula\n2. Rivers overflowing and flooding nearby cities and towns\n3. People evacuating their homes and seeking higher ground\n4. Rescue teams navigating boats through flooded streets to reach stranded residents\n5. Cars and buildings submerged in water with debris scattered around",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the consequences of flooding and heavy rainfall, such as damage to infrastructure, evacuation efforts, and scenes of flooding. These events are likely to be visualized in a video capturing the impact of the floods on the region.\n\nEVENTS:\n1. People evacuating flooded homes and buildings\n2. Cars and buildings submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Debris and wreckage from destroyed buildings and infrastructure\n5. Residents clearing mud and water from their homes and streets",
"video_URL": "http://youtube.com/watch?v=5j_NI2eL3HA",
"video_description": "북한에서 집중 호우로 일어난 홍수에 22명이 숨지고 4명이 실종됐습니다. 국제적십자사연맹은 미국의소리 방송에 보낸 이메일에서 \"북한 조선 적십자회와 국가 비상 재해 위원회에 따르면 심각한 홍수로 인해 22명이 사망하고 4명이 실종됐다\"고 밝혔습니다. https://imnews.imbc.com/replay/2020/nwtoday/article/5873504_32531.html #북한 #집중호우 #홍수",
"video_id": "5j_NI2eL3HA"
}
| 8
|
[
"The current frame shows a news anchor standing in front of a screen displaying a coastal scene. The anchor is dressed in a suit and holding a booklet with a blue cover. The screen behind him has text in Korean, with the main headline reading \"국제적심자연명 '북, 협수로 22명 사망·4명 실종'\" which translates to \"North Korea: 22 dead, 4 missing in international incident.\" Additional information on the screen includes the time (7:23) and a logo with \"MBC\" at the top right. There is also a smaller text in the lower left corner of the screen.",
"The image shows two individuals dressed in dark, hooded raincoats standing in a wooded area. They appear to be in a discussion or pointing at something off-camera. The text on the screen, in Korean, continues to provide information about the incident involving North Korea, stating \"국제적심자연명 '북, 협수로 22명 사망·4명 실종'\" which translates to \"North Korea: 22 dead, 4 missing in international incident.\" The time displayed is 7:23, and the \"MBC\" logo is visible in the top right corner. The bottom of the screen shows additional text, likely providing further details on the incident or related news.",
"The image shows a large wave or surge of water in a dark, overcast setting. The text on the screen, in Korean, continues to provide information about the incident involving North Korea, stating \"국제적심자연명 '북, 협수로 22명 사망·4명 실종'\" which translates to \"North Korea: 22 dead, 4 missing in international incident.\" The time displayed is 7:23, and the \"MBC\" logo is visible in the top right corner. The bottom of the screen shows additional text, likely providing further details on the incident or related news.",
"The current frame shows a construction vehicle, possibly a bulldozer or excavator, carrying what appears to be debris or sandbags, partially submerged in floodwaters. The vehicle is moving through the water, likely in an attempt to address the flood situation. The surrounding area is muddy and waterlogged, with trees and greenery visible in the background, indicating a rural or semi-rural setting. The text on the screen continues to provide information about the incident involving North Korea, repeating \"국제적심자연명 '북, 협수로 22명 사망·4명 실종'\" which translates to \"North Korea: 22 dead, 4 missing in international incident.\" The time displayed is 7:24, and the \"MBC\" logo is still present in the top right corner. The bottom of the screen shows additional text, likely providing further details on the incident or related news.",
"The current frame shows a construction vehicle, possibly a bulldozer or excavator, partially submerged in floodwaters and moving through the water. The vehicle is carrying debris or sandbags, likely as part of the efforts to manage the flood situation. The surrounding area is muddy and waterlogged, with trees and greenery visible in the background, indicating a rural or semi-rural setting. The text on the screen continues to provide information about the incident involving North Korea, repeating \"국제적심자연명 '북, 협수로 22명 사망·4명 실종'\" which translates to \"North Korea: 22 dead, 4 missing in international incident.\" The time displayed is 7:24, and the \"MBC\" logo is still present in the top right corner. The bottom of the screen shows additional text, likely providing further details on the incident or related news.",
"The current frame shows a large construction vehicle, likely a bulldozer, driving through a flooded area. The vehicle appears to be navigating through the water, which is at a level that partially submerges the lower parts of the vehicle. The surrounding area is muddy and waterlogged, with trees and greenery visible in the background, indicating a rural or semi-rural setting. The text on the screen provides information about a natural disaster, specifically mentioning \"국제적심자연명 '북, 협수로 22명 사망·4명 실종'\" which translates to \"International appeal for North Korea: 22 dead, 4 missing due to flooding.\" The time displayed is 7:24, and the \"MBC\" logo is present in the top right corner. The bottom of the screen shows additional text, likely providing further details on the incident or related news.",
"The current frame shows a body of water, likely a river or flood-affected area, with turbulent water indicating strong currents or recent rainfall. There are no visible vehicles or construction equipment, suggesting a different location or moment within the affected area. The text on the screen continues to provide information about the natural disaster, specifically mentioning \"국제적심자연명 '북, 협수로 22명 사망·4명 실종'\" which translates to \"International appeal for North Korea: 22 dead, 4 missing due to flooding.\" The time displayed is 7:24, and the \"MBC\" logo is present in the top right corner. The bottom of the screen shows additional text, likely providing further details on the incident or related news.",
"The current frame continues to show the body of water with turbulent water indicating strong currents or recent rainfall, consistent with the previous frame. The text on the screen remains the same, providing information about the natural disaster with the same details about the number of deaths and missing persons in North Korea due to flooding. The time displayed is still 7:24, and the \"MBC\" logo is present in the top right corner. The bottom of the screen still shows additional text, likely providing further details on the incident or related news."
] |
5j_NI2eL3HA
|
A news broadcast is reporting on a flooding incident in North Korea, where 22 people have died and 4 are missing. The news anchor introduces the story in front of a screen displaying a coastal scene and relevant information in Korean. The footage then cuts to individuals in a wooded area, possibly discussing the incident, followed by images of a large wave and floodwaters. Construction vehicles, such as bulldozers or excavators, are shown navigating through the water, carrying debris or sandbags, as part of the efforts to manage the flood situation. The video also shows the flooded area, with turbulent water indicating strong currents or recent rainfall. Throughout the video, the screen displays updates on the incident, including the number of deaths and missing persons, and the time, with the "MBC" logo visible in the top right corner.
|
Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.
|
[
"Heavy rains and floods in the southern Korean Peninsula during summer 2020",
"Heavy rains pouring down in southern South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North and South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during the summer floods of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during heavy rains in summer 2020",
"Rescue teams navigating boats through flooded streets to reach stranded residents during the summer floods of 2020 in North and South Korea",
"Rescue teams navigating boats through flooded streets to reach stranded residents in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after floods in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after heavy rains in North and South Korea during the summer of 2020"
] |
[
"People evacuating flooded homes and buildings in the Korean Peninsula during the summer rainy season of 2020",
"People evacuating flooded homes and buildings in the Korean Peninsula during summer 2020 heavy rains",
"Cars and buildings submerged in floodwater in North Korea and South Korea during the summer floods of 2020",
"Cars and buildings submerged in floodwater during heavy rains in the Korean Peninsula in summer 2020",
"Emergency responders rescuing people from flooded areas in North Korea and South Korea during the summer rainy season of 2020",
"Emergency responders rescuing people from flooded areas in North and South Korea during heavy rains in the summer of 2020",
"Debris and wreckage from destroyed buildings and infrastructure due to floods in North and South Korea during the summer 2020 rainy season",
"Debris and wreckage from destroyed buildings and infrastructure in North Korea, South Korea, and the Korean Peninsula after heavy rains during the summer rainy season of June-August 2020",
"Residents clearing mud and water from their homes and streets after floods in the Korean Peninsula during the summer 2020 rainy season",
"Residents clearing mud and water from their homes and streets in North and South Korea after heavy rains during the summer rainy season of 2020"
] |
[
"Floodwaters inundating homes and buildings in southern Korea, particularly in South Korea, during the summer rainy season of 2020",
"Floodwaters inundating homes and buildings in southern Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North and South Korea during heavy rains in summer 2020",
"Rescue workers helping those stranded by the floods in North Korea and South Korea during the summer rainy season of 2020",
"Rescue workers helping those stranded by floods in the Korean Peninsula during the summer rainy season of 2020",
"Cars and buildings submerged in water during floods in North and South Korea, Korean Peninsula, Summer 2020",
"Cars and buildings submerged in water in North and South Korea during heavy rains in summer 2020",
"Emergency responders distributing aid and supplies to communities affected by floods in North Korea and South Korea during the summer rainy season of June to August 2020",
"Emergency responders distributing aid and supplies to affected communities in North and South Korea during heavy rains in the summer of 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2020%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact of floods and heavy rains in Korea, such as scenes of flooding, damage, and rescue efforts, as these are likely to be visualized in a video about the event. The extracted events should be specific to the region and the time of year, taking into account the regional rainy season and the areas most affected by the floods.\n\nEVENTS:\n1. Floodwaters inundating homes and buildings in southern Korea\n2. People evacuating flooded areas by boat\n3. Rescue workers helping those stranded by the floods\n4. Cars and buildings submerged in water\n5. Emergency responders distributing aid and supplies to affected communities",
"en_article_excerpt": "Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Korean_floods",
"event_category": "disasters",
"event_name": "2020_korean_floods",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the cause and effects of the flooding, such as scenes of heavy rainfall, flooded areas, and rescue efforts. These events are likely to be visualized in a video documenting the floods and their impact on the region.\n\nEVENTS:\n1. Heavy rains pouring down in the southern parts of the Korean Peninsula\n2. Rivers overflowing and flooding nearby cities and towns\n3. People evacuating their homes and seeking higher ground\n4. Rescue teams navigating boats through flooded streets to reach stranded residents\n5. Cars and buildings submerged in water with debris scattered around",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the consequences of flooding and heavy rainfall, such as damage to infrastructure, evacuation efforts, and scenes of flooding. These events are likely to be visualized in a video capturing the impact of the floods on the region.\n\nEVENTS:\n1. People evacuating flooded homes and buildings\n2. Cars and buildings submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Debris and wreckage from destroyed buildings and infrastructure\n5. Residents clearing mud and water from their homes and streets",
"video_URL": "http://youtube.com/watch?v=nR08Eart4vo",
"video_description": "댐 관리를 담당하는 한국수자원공사가 이번 수해와 관련해 댐 수위 조절에는 문제가 없었다고 밝혔습니다. 수자원공사는 댐관리규정 등에 따라 홍수기 기상변화와 댐 상·하류 상황, 댐 안전과 민원 등을 고려해 홍수 대응이 가능하도록 댐 수위를 관리했다고 설명했습니다. 섬진강댐은 집중호우 전부터 홍수기제한수위보다 3m 낮게 유지했고, 용담댐이나 합천댐도 제한 수위를 지켜 전혀 이상이 없었다고 강조했습니다. 다만, 유례없는 최장 기간의 장마로 제방이 무너지고 물이 넘치는 등 복합적인 요인 탓에 홍수 피해가 난 것으로 보인다고 덧붙였습니다. 이에 관련 기관과 함께 원인 조사를 한 뒤 대책 수립에 적극 협조하고, 복구 지원에 노력하겠다고 전했습니다. ※ '당신의 제보가 뉴스가 됩니다' YTN은 여러분의 소중한 제보를 기다립니다. [카카오톡] YTN을 검색해 채널 추가 [전화] 02-398-8585 [메일] [email protected] [온라인 제보] www.ytn.co.kr ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0103_202008121704378843 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, [email protected], #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN & YTN PLUS 무단 전재 및 재배포금지",
"video_id": "nR08Eart4vo"
}
| 8
|
[
"The image shows a news broadcast featuring a news anchor in a studio. The background includes a building labeled \"K water\" and the text in Korean at the top of the screen reads \"수도권 영서 모레부터 비,\" which translates to \"Rain from tomorrow in the Seoul area of the capital region.\" The text at the bottom of the screen reads \"담, 홍수기 제한수위 이하 유지...피해 원인 조사,\" which translates to \"The water level remained below the restricted level during the flood season...Investigating the cause of damage.\" The news anchor appears to be delivering a report on weather or flood-related news.",
"The image shows an aerial view of a flood-stricken area. The scene depicts a large body of water covering fields and buildings, with a partially submerged bridge visible. The text at the top of the screen repeats the message \"수도권 영서 모레부터 비,\" indicating ongoing coverage of the weather forecast. The text at the bottom of the screen remains the same, emphasizing the water level and the investigation into the cause of the damage. The overall context suggests a severe flood situation in the region.",
"The image shows an aerial view of a flood-stricken area with significant water coverage over fields, buildings, and roads. The water level appears to be high, with a partially submerged bridge and scattered debris visible in the water. The text at the top of the screen repeats the message \"수도권 영서 모레부터 비,\" indicating ongoing coverage of the weather forecast. The text at the bottom of the screen remains the same, emphasizing the water level and the investigation into the cause of the damage. The overall context suggests a severe flood situation in the region.",
"The image continues to depict an aerial view of a flood-stricken area, with widespread inundation affecting fields, buildings, and roads. The water level remains high, and the partially submerged bridge along with scattered debris are still visible. The text at the top of the screen now reads \"내일까지 장마 소강 전국 사망 33. 실종 9,\" indicating a focus on the current flood situation and the number of casualties. The bottom text again emphasizes the water level and the ongoing investigation into the cause of the damage. The scene remains consistent with the severe flood conditions described in the previous frame, with an additional update on the human impact of the disaster.",
"The video continues to show an aerial view of the flood-affected area, with the water level still high and inundation persisting over fields, buildings, and roads. The partially submerged bridge and scattered debris remain visible, indicating the ongoing severity of the flooding. The text at the top of the screen, \"내일까지 장마 소강 전국 사망 33. 실종 9,\" emphasizes the extent of the disaster and the casualties, while the bottom text reinforces the investigation into the causes and the current water level. The scene remains consistent with the previous frames, highlighting the continuous impact of the flood and the efforts to manage the situation.",
"The aerial view continues to show the flood-affected area, with water still covering fields and roads. A bridge partially submerged and surrounded by debris indicates ongoing flood severity. Text at the top mentions '내일까지 장마 소강,' and at the bottom, '최장 기간 장마에 독 무너지고 물 넘치는 복합 재난,' emphasizing the prolonged heavy rain and related disasters like bridge collapse and water overflow.",
"The current frame continues the aerial view of the flood-affected area, showing a river with muddy water flowing rapidly, reflecting the severity of the flooding. The surrounding landscape includes green fields and trees, with a visible power pole and a path leading towards the river. The text at the top reads '내일까지 장마 소강' (Until tomorrow, the flood will ease), and the bottom text '최장 기간 장마에 독 무너지고 물 넘치는 복합 재난' (A composite disaster of collapsing dams and overflowing water during the longest rainy season), reinforcing the prolonged flood conditions and related disasters.",
"The current frame shows a close-up view of people working amidst debris, likely clearing or assessing the damage caused by the flood. The individuals are wearing orange vests, suggesting they are part of a rescue or cleanup team. The background shows more tangled debris and structures, indicating the extent of the damage. The text at the top reads '내일까지 장마 소강' (Until tomorrow, the flood will ease), and the bottom text '최장 기간 장마에 독 무너지고 물 넘치는 복합 재난' (A composite disaster of collapsing dams and overflowing water during the longest rainy season), indicating the context of the cleanup efforts following the prolonged flood conditions and related disasters."
] |
nR08Eart4vo
|
A severe flood hits the Seoul area of the capital region, with the news anchor reporting on the weather forecast and flood-related news. The flood causes widespread inundation, affecting fields, buildings, and roads, with a partially submerged bridge and scattered debris visible. The water level remains high, and the situation is described as a composite disaster with collapsing dams and overflowing water during the longest rainy season. The flood results in significant casualties, with 33 deaths and 9 missing persons reported. As the flood is expected to ease by the next day, rescue and cleanup efforts are underway, with teams working to clear debris and assess damage. The video provides an overview of the flood's impact and the ongoing response to the disaster.
|
Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.
|
[
"Heavy rains and floods in the southern Korean Peninsula during summer 2020",
"Heavy rains pouring down in southern South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North and South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during the summer floods of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during heavy rains in summer 2020",
"Rescue teams navigating boats through flooded streets to reach stranded residents during the summer floods of 2020 in North and South Korea",
"Rescue teams navigating boats through flooded streets to reach stranded residents in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after floods in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after heavy rains in North and South Korea during the summer of 2020"
] |
[
"People evacuating flooded homes and buildings in the Korean Peninsula during the summer rainy season of 2020",
"People evacuating flooded homes and buildings in the Korean Peninsula during summer 2020 heavy rains",
"Cars and buildings submerged in floodwater in North Korea and South Korea during the summer floods of 2020",
"Cars and buildings submerged in floodwater during heavy rains in the Korean Peninsula in summer 2020",
"Emergency responders rescuing people from flooded areas in North Korea and South Korea during the summer rainy season of 2020",
"Emergency responders rescuing people from flooded areas in North and South Korea during heavy rains in the summer of 2020",
"Debris and wreckage from destroyed buildings and infrastructure due to floods in North and South Korea during the summer 2020 rainy season",
"Debris and wreckage from destroyed buildings and infrastructure in North Korea, South Korea, and the Korean Peninsula after heavy rains during the summer rainy season of June-August 2020",
"Residents clearing mud and water from their homes and streets after floods in the Korean Peninsula during the summer 2020 rainy season",
"Residents clearing mud and water from their homes and streets in North and South Korea after heavy rains during the summer rainy season of 2020"
] |
[
"Floodwaters inundating homes and buildings in southern Korea, particularly in South Korea, during the summer rainy season of 2020",
"Floodwaters inundating homes and buildings in southern Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North and South Korea during heavy rains in summer 2020",
"Rescue workers helping those stranded by the floods in North Korea and South Korea during the summer rainy season of 2020",
"Rescue workers helping those stranded by floods in the Korean Peninsula during the summer rainy season of 2020",
"Cars and buildings submerged in water during floods in North and South Korea, Korean Peninsula, Summer 2020",
"Cars and buildings submerged in water in North and South Korea during heavy rains in summer 2020",
"Emergency responders distributing aid and supplies to communities affected by floods in North Korea and South Korea during the summer rainy season of June to August 2020",
"Emergency responders distributing aid and supplies to affected communities in North and South Korea during heavy rains in the summer of 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2020%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact of floods and heavy rains in Korea, such as scenes of flooding, damage, and rescue efforts, as these are likely to be visualized in a video about the event. The extracted events should be specific to the region and the time of year, taking into account the regional rainy season and the areas most affected by the floods.\n\nEVENTS:\n1. Floodwaters inundating homes and buildings in southern Korea\n2. People evacuating flooded areas by boat\n3. Rescue workers helping those stranded by the floods\n4. Cars and buildings submerged in water\n5. Emergency responders distributing aid and supplies to affected communities",
"en_article_excerpt": "Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Korean_floods",
"event_category": "disasters",
"event_name": "2020_korean_floods",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the cause and effects of the flooding, such as scenes of heavy rainfall, flooded areas, and rescue efforts. These events are likely to be visualized in a video documenting the floods and their impact on the region.\n\nEVENTS:\n1. Heavy rains pouring down in the southern parts of the Korean Peninsula\n2. Rivers overflowing and flooding nearby cities and towns\n3. People evacuating their homes and seeking higher ground\n4. Rescue teams navigating boats through flooded streets to reach stranded residents\n5. Cars and buildings submerged in water with debris scattered around",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the consequences of flooding and heavy rainfall, such as damage to infrastructure, evacuation efforts, and scenes of flooding. These events are likely to be visualized in a video capturing the impact of the floods on the region.\n\nEVENTS:\n1. People evacuating flooded homes and buildings\n2. Cars and buildings submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Debris and wreckage from destroyed buildings and infrastructure\n5. Residents clearing mud and water from their homes and streets",
"video_URL": "http://youtube.com/watch?v=GwY9HYVEQIk",
"video_description": "전국 하천 홍수특보 전부 해제…상수도 93곳 피해 중부지방 집중호우가 소강상태에 접어든 가운데 전국 하천 주요 지점의 홍수특보가 전부 해제됐습니다. 환경부는 낙동강이 흐르는 경남 밀양시 삼랑진교에 내려졌던 홍수주의보가 오늘(12일) 오후 5시30분 해제된 것을 끝으로 전국 하천 주요지점에 내려진 홍수특보가 모두 해제됐다고 밝혔습니다. 한강과 임진강 비룡대교·영평교, 왕숙천 진관교 등지에 발령됐던 홍수주의보와 섬진강 하동군 읍내리 지점의 홍수주의보는 각각 지난 11일 오후 6시와 오후 5시 해제됐습니다. 이번 호우로 27개 시·군의 상수도 시설 93곳에서 피해가 발생했습니다. 연합뉴스TV 기사문의 및 제보 : 카톡/라인 jebo23 ▣ 연합뉴스TV 유튜브 채널 구독 https://goo.gl/VuCJMi ▣ 대한민국 뉴스의 시작 연합뉴스TV / Yonhap News TV http://www.yonhapnewstv.co.kr/",
"video_id": "GwY9HYVEQIk"
}
| 8
|
[
"The frame shows a flood with turbulent waters under a bridge, indicating significant water levels. The text in Korean suggests flooding in various locations, with mentions of bridges and 93 buildings affected. The weather is indicated to be rainy, and there are temperatures displayed.",
"The frame continues to show turbulent floodwaters flowing rapidly under a bridge, with the scene indicating severe flooding. The text in Korean at the top states, \"역대 최장 장마, 당정청 '재난지원금 2배로'\" which translates to \"Record-breaking long rainy season, government triples disaster relief fund.\" The text at the bottom reinforces the severe impact, noting \"전국 하천 홍수특보 전부 해제...상수도 93곳 피해\" which means \"All flood warnings for rivers nationwide lifted... 93 water supply facilities damaged.\" The weather update in the corner shows heavy rainfall of 278 mm and a temperature of 29.9°C, emphasizing the ongoing adverse weather conditions.",
"The current frame shows a river with rapid and muddy floodwaters. A pink barrier floats on the water, likely indicating attempts at containment or safety. The text at the top reads, \"역대 최장 장마, 당정청 '재난지원금 2배로'\" which means \"Record-breaking long rainy season, government triples disaster relief fund.\" The text at the bottom mentions, \"전국 하천 홍수특보 전부 해제...상수도 93곳 피해\" meaning \"All flood warnings for rivers nationwide lifted... 93 water supply facilities damaged.\" The weather information in the top right indicates a rainfall of 107 mm and a temperature of 28.2°C, highlighting the ongoing severe weather conditions.",
"The current frame shows a river with muddy floodwaters, reflecting the recent heavy rainfall. A bridge spans the river, supported by numerous concrete pillars. The text at the top reads, \"역대 최장 장마, 당정청 '재난지원금 2배로'\" meaning \"Record-breaking long rainy season, government triples disaster relief fund.\" The text at the bottom mentions, \"전국 하천 홍수특보 전부 해제...상수도 93곳 피해\" indicating \"All flood warnings for rivers nationwide lifted... 93 water supply facilities damaged.\" The weather information in the top right shows a rainfall of 107 mm and a temperature of 28.2°C, emphasizing the severe weather conditions. The pink barrier is no longer visible, suggesting it may have been removed or moved out of the frame.",
"The current frame shows a river with muddy floodwaters, reflecting the recent heavy rainfall. A bridge spans the river, supported by numerous concrete pillars. The text at the top reads, \"역대 최장 장마, 당정청 '재난지원금 2배로'\" meaning \"Record-breaking long rainy season, government triples disaster relief fund.\" The text at the bottom mentions, \"전국 하천 홍수특보 전부 해제...상수도 93곳 피해\" indicating \"All flood warnings for rivers nationwide lifted... 93 water supply facilities damaged.\" The weather information in the top right shows a rainfall of 104 mm and a temperature of 25.8°C, emphasizing the severe weather conditions.",
"The current frame depicts an industrial facility with machinery and equipment, likely related to the water supply system mentioned in the text at the bottom of the previous frame. The machinery includes large pipes and valves, some of which are connected to yellow hoses or pipes. The text at the bottom of the frame repeats, \"전국 하천 홍수특보 전부 해제...상수도 93곳 피해\" meaning \"All flood warnings for rivers nationwide lifted... 93 water supply facilities damaged.\" This suggests the facility may be affected by the flooding, contributing to the damage mentioned. The weather information in the top right corner indicates a rainfall of 53 mm and a temperature of 27.8°C, reflecting the ongoing weather conditions impacting the facility.",
"The current frame continues to show an industrial facility, specifically focusing on a pump and valve system that is part of a water supply system. The machinery includes large pipes and valves, some of which are connected to yellow hoses or pipes. The text at the bottom of the frame states, \"전국 하천 홍수특보 전부 해제...상수도 93곳 피해\" meaning \"All flood warnings for rivers nationwide lifted... 93 water supply facilities damaged.\" This indicates the facility might have been affected by the flooding, which is likely contributing to the damage mentioned. The weather information in the top right corner shows a rainfall of 98 mm and a temperature of 28.6°C, reflecting the current weather conditions impacting the facility.",
"The current frame continues to show an industrial facility, specifically focusing on a pump and valve system that is part of a water supply system. The machinery includes large pipes and valves, some of which are connected to yellow hoses or pipes. The text at the bottom of the frame states, \"전국 하천 홍수특보 전부 해제...상수도 93곳 피해\" meaning \"All flood warnings for rivers nationwide lifted... 93 water supply facilities damaged.\" This indicates the facility might have been affected by the flooding, which is likely contributing to the damage mentioned. The weather information in the top right corner shows a rainfall of 98 mm and a temperature of 28.6°C, reflecting the current weather conditions impacting the facility."
] |
GwY9HYVEQIk
|
The video depicts a severe flooding event in South Korea, caused by a record-breaking long rainy season. The floodwaters are shown flowing rapidly under bridges and in rivers, with a significant impact on the surrounding areas. The government has announced plans to triple the disaster relief fund in response to the crisis. The flooding has damaged 93 water supply facilities nationwide, and all flood warnings for rivers have been lifted. The video shows the aftermath of the flooding, with muddy waters and damaged infrastructure, including industrial facilities related to the water supply system. The weather conditions continue to be severe, with heavy rainfall and high temperatures. Overall, the video highlights the extent of the flooding and its effects on the community, as well as the government's response to the disaster.
|
Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.
|
[
"Heavy rains and floods in the southern Korean Peninsula during summer 2020",
"Heavy rains pouring down in southern South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North and South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during the summer floods of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during heavy rains in summer 2020",
"Rescue teams navigating boats through flooded streets to reach stranded residents during the summer floods of 2020 in North and South Korea",
"Rescue teams navigating boats through flooded streets to reach stranded residents in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after floods in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after heavy rains in North and South Korea during the summer of 2020"
] |
[
"People evacuating flooded homes and buildings in the Korean Peninsula during the summer rainy season of 2020",
"People evacuating flooded homes and buildings in the Korean Peninsula during summer 2020 heavy rains",
"Cars and buildings submerged in floodwater in North Korea and South Korea during the summer floods of 2020",
"Cars and buildings submerged in floodwater during heavy rains in the Korean Peninsula in summer 2020",
"Emergency responders rescuing people from flooded areas in North Korea and South Korea during the summer rainy season of 2020",
"Emergency responders rescuing people from flooded areas in North and South Korea during heavy rains in the summer of 2020",
"Debris and wreckage from destroyed buildings and infrastructure due to floods in North and South Korea during the summer 2020 rainy season",
"Debris and wreckage from destroyed buildings and infrastructure in North Korea, South Korea, and the Korean Peninsula after heavy rains during the summer rainy season of June-August 2020",
"Residents clearing mud and water from their homes and streets after floods in the Korean Peninsula during the summer 2020 rainy season",
"Residents clearing mud and water from their homes and streets in North and South Korea after heavy rains during the summer rainy season of 2020"
] |
[
"Floodwaters inundating homes and buildings in southern Korea, particularly in South Korea, during the summer rainy season of 2020",
"Floodwaters inundating homes and buildings in southern Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North and South Korea during heavy rains in summer 2020",
"Rescue workers helping those stranded by the floods in North Korea and South Korea during the summer rainy season of 2020",
"Rescue workers helping those stranded by floods in the Korean Peninsula during the summer rainy season of 2020",
"Cars and buildings submerged in water during floods in North and South Korea, Korean Peninsula, Summer 2020",
"Cars and buildings submerged in water in North and South Korea during heavy rains in summer 2020",
"Emergency responders distributing aid and supplies to communities affected by floods in North Korea and South Korea during the summer rainy season of June to August 2020",
"Emergency responders distributing aid and supplies to affected communities in North and South Korea during heavy rains in the summer of 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2020%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact of floods and heavy rains in Korea, such as scenes of flooding, damage, and rescue efforts, as these are likely to be visualized in a video about the event. The extracted events should be specific to the region and the time of year, taking into account the regional rainy season and the areas most affected by the floods.\n\nEVENTS:\n1. Floodwaters inundating homes and buildings in southern Korea\n2. People evacuating flooded areas by boat\n3. Rescue workers helping those stranded by the floods\n4. Cars and buildings submerged in water\n5. Emergency responders distributing aid and supplies to affected communities",
"en_article_excerpt": "Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Korean_floods",
"event_category": "disasters",
"event_name": "2020_korean_floods",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the cause and effects of the flooding, such as scenes of heavy rainfall, flooded areas, and rescue efforts. These events are likely to be visualized in a video documenting the floods and their impact on the region.\n\nEVENTS:\n1. Heavy rains pouring down in the southern parts of the Korean Peninsula\n2. Rivers overflowing and flooding nearby cities and towns\n3. People evacuating their homes and seeking higher ground\n4. Rescue teams navigating boats through flooded streets to reach stranded residents\n5. Cars and buildings submerged in water with debris scattered around",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the consequences of flooding and heavy rainfall, such as damage to infrastructure, evacuation efforts, and scenes of flooding. These events are likely to be visualized in a video capturing the impact of the floods on the region.\n\nEVENTS:\n1. People evacuating flooded homes and buildings\n2. Cars and buildings submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Debris and wreckage from destroyed buildings and infrastructure\n5. Residents clearing mud and water from their homes and streets",
"video_URL": "http://youtube.com/watch?v=FG82wp__uZ8",
"video_description": "#홍수 #성금 ●BTN불교TV 유튜브 구독하기 https://bit.ly/3k5nt10 (링크 누르고 구독 버튼 클릭!) ●BTN불교TV는? BTN불교TV(주)는 25년의 시간 동안 부처님의 법음을 널리 홍포해온 한국을 대표하는 불교방송국입니다. 불자님들의 소중한 후원금과 광고수입은 더 나은 방송 포교와 불교문화 진흥, 다양한 컨텐츠를 제작하는데 사용되고 있습니다. BTN은 앞으로도 방송 포교사의 소임을 다하겠습니다. ●BTN불교TV 채널번호 안내 IPTV: KTolleh:233번, SK B TV:305번, LGU+TV:275번(전국공통) SKYLIFE: 181번(전국공통) 지역케이블: 케이블 가입자의 경우 BTN채널번호가 지역별로 달라서 아래 주소를 클릭하셔서 확인하시면 됩니다 https://blog.naver.com/btnii/221391809765 ●다양한 경로로 BTN불교TV를 만나보세요! 홈페이지:http://www.btn.co.kr/index.asp 유튜브:https://www.youtube.com/channel/UCOozqNhXDcb6gg6oaU7uImA?view_as=subscriber 페이스북:https://www.facebook.com/BTNkorea/ 블로그:https://blog.naver.com/btnii 카카오스토리:https://story.kakao.com/ch/btntv",
"video_id": "FG82wp__uZ8"
}
| 8
|
[
"The image shows a dramatic sky filled with dark clouds, illuminated by a bolt of lightning. Below the clouds, silhouetted mountains are visible. The text \"2020년 8월\" (August 2020) is prominently displayed in the center, indicating the date of the event.",
"The current frame depicts a news anchor standing in front of a green screen with an image of a traditional building that has sustained significant damage. The building's roof is partially collapsed, and debris is scattered around the structure. The news anchor appears to be reporting on the aftermath of a disaster, likely related to the storm indicated in the previous frame. The presence of the traditional building suggests a cultural or historical context to the news story. The text \"B NEWS\" is visible, indicating the news channel broadcasting the report.",
"The current frame shows a traditional building with its roof collapsed and debris scattered around, emphasizing the damage caused by a disaster. The setting appears to be rural or semi-rural, with greenery in the background. The text \"대통령의 기와가 떨어지고\" is visible, suggesting the damage is being reported in a news segment, likely discussing the impact of the disaster on significant structures or landmarks.",
"The current frame shows the interior of a building with water flooding the floor, emphasizing the extent of the damage caused by the disaster. The setting appears to be a religious or ceremonial room with statues and a large mural on the wall, indicating the significance of the location. The text \"마당은 토사로 매워지고\" suggests that efforts are being made to manage the floodwaters, possibly by sealing off the entrance or redirecting the water flow.",
"The current frame shows a bright, abstract, and blurred background that does not depict any clear action, participants, or context related to the previous frame's description of flooding damage in a ceremonial room. There is no visible text in the image to enhance the interpretation of the frame. The image is not connected to the overall flow of the video.",
"The current frame depicts three individuals actively involved in a cleanup effort following a flood. They are engaged in removing mud and debris from the ground outside a structure, which appears to be a small building or shed. The individuals are using various tools to scrape and clear the mud, and one person is seen shoveling the material. The text in Korean, \"자비행을 실천해야 할 때입니다,\" translates to \"It is time to practice loving-kindness,\" suggesting a message of compassion and community service in response to the flooding situation.",
"The current frame displays a bright and clear sky with the sun shining through the branches of a lush green tree. The text in Korean reads, \" BTN 불법화와 드림아이 아름다운운동행이 도움의 손길을 기다립니다,\" which translates to \"BTN, Dreaminus, and Beautiful Movement Project are waiting for your help.\" This image likely serves as a call to action, encouraging viewers to participate in or support the cleanup efforts after a flood. The contrast between this serene image and the previous frame's active cleanup scene suggests a hopeful message about community involvement and the collective effort required to restore the area.",
"The current frame shows a silhouette of a person against a setting sun with the sky bathed in a warm glow. Overlaid on the image is Korean text that reads, \"문의 1855-0108,\" which translates to \"Inquiry 1855-0108.\" Below that, additional text states, \"수재민모금 827-01-0332-638 국민은행 (예금주: 불교텔레비전전)\" translating to \"Disaster Relief Donation 827-01-0332-638 Kookmin Bank (Account holder: Buddhist Television Fund).\" This frame likely serves as an informational segment, providing viewers with a phone number and bank account details to make donations for disaster relief, maintaining the theme of community support and assistance from the previous frames."
] |
FG82wp__uZ8
|
A severe storm hit in August 2020, causing significant damage to traditional buildings and infrastructure. News reports showed the aftermath of the disaster, with a traditional building's roof partially collapsed and debris scattered around. The damage extended to a ceremonial room, which was flooded, and efforts were made to manage the floodwaters. Community members came together for a cleanup effort, removing mud and debris from the affected areas. The video concluded with a call to action, encouraging viewers to support the relief efforts through donations, providing contact information and bank account details for those wishing to contribute to the disaster relief fund. The overall tone of the video emphasized community service, compassion, and the importance of collective action in responding to natural disasters.
|
Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.
|
[
"Heavy rains and floods in the southern Korean Peninsula during summer 2020",
"Heavy rains pouring down in southern South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North and South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during the summer floods of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during heavy rains in summer 2020",
"Rescue teams navigating boats through flooded streets to reach stranded residents during the summer floods of 2020 in North and South Korea",
"Rescue teams navigating boats through flooded streets to reach stranded residents in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after floods in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after heavy rains in North and South Korea during the summer of 2020"
] |
[
"People evacuating flooded homes and buildings in the Korean Peninsula during the summer rainy season of 2020",
"People evacuating flooded homes and buildings in the Korean Peninsula during summer 2020 heavy rains",
"Cars and buildings submerged in floodwater in North Korea and South Korea during the summer floods of 2020",
"Cars and buildings submerged in floodwater during heavy rains in the Korean Peninsula in summer 2020",
"Emergency responders rescuing people from flooded areas in North Korea and South Korea during the summer rainy season of 2020",
"Emergency responders rescuing people from flooded areas in North and South Korea during heavy rains in the summer of 2020",
"Debris and wreckage from destroyed buildings and infrastructure due to floods in North and South Korea during the summer 2020 rainy season",
"Debris and wreckage from destroyed buildings and infrastructure in North Korea, South Korea, and the Korean Peninsula after heavy rains during the summer rainy season of June-August 2020",
"Residents clearing mud and water from their homes and streets after floods in the Korean Peninsula during the summer 2020 rainy season",
"Residents clearing mud and water from their homes and streets in North and South Korea after heavy rains during the summer rainy season of 2020"
] |
[
"Floodwaters inundating homes and buildings in southern Korea, particularly in South Korea, during the summer rainy season of 2020",
"Floodwaters inundating homes and buildings in southern Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North and South Korea during heavy rains in summer 2020",
"Rescue workers helping those stranded by the floods in North Korea and South Korea during the summer rainy season of 2020",
"Rescue workers helping those stranded by floods in the Korean Peninsula during the summer rainy season of 2020",
"Cars and buildings submerged in water during floods in North and South Korea, Korean Peninsula, Summer 2020",
"Cars and buildings submerged in water in North and South Korea during heavy rains in summer 2020",
"Emergency responders distributing aid and supplies to communities affected by floods in North Korea and South Korea during the summer rainy season of June to August 2020",
"Emergency responders distributing aid and supplies to affected communities in North and South Korea during heavy rains in the summer of 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2020%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact of floods and heavy rains in Korea, such as scenes of flooding, damage, and rescue efforts, as these are likely to be visualized in a video about the event. The extracted events should be specific to the region and the time of year, taking into account the regional rainy season and the areas most affected by the floods.\n\nEVENTS:\n1. Floodwaters inundating homes and buildings in southern Korea\n2. People evacuating flooded areas by boat\n3. Rescue workers helping those stranded by the floods\n4. Cars and buildings submerged in water\n5. Emergency responders distributing aid and supplies to affected communities",
"en_article_excerpt": "Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Korean_floods",
"event_category": "disasters",
"event_name": "2020_korean_floods",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the cause and effects of the flooding, such as scenes of heavy rainfall, flooded areas, and rescue efforts. These events are likely to be visualized in a video documenting the floods and their impact on the region.\n\nEVENTS:\n1. Heavy rains pouring down in the southern parts of the Korean Peninsula\n2. Rivers overflowing and flooding nearby cities and towns\n3. People evacuating their homes and seeking higher ground\n4. Rescue teams navigating boats through flooded streets to reach stranded residents\n5. Cars and buildings submerged in water with debris scattered around",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the consequences of flooding and heavy rainfall, such as damage to infrastructure, evacuation efforts, and scenes of flooding. These events are likely to be visualized in a video capturing the impact of the floods on the region.\n\nEVENTS:\n1. People evacuating flooded homes and buildings\n2. Cars and buildings submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Debris and wreckage from destroyed buildings and infrastructure\n5. Residents clearing mud and water from their homes and streets",
"video_URL": "http://twitter.com/i/status/1291976724456992776",
"video_description": "섬진강이 난리네요 ㅠ#섬진강#유등면#섬진강 홍수",
"video_id": "1291976724456992776"
}
| 8
|
[
"The frame depicts a flooded area with water submerged under a structure with a blue roof. Cows are visible standing in the floodwater under the structure, which appears to be partially destroyed or damaged. A tree is also visible in the foreground, partially submerged in water.",
"The frame continues to depict the flooded area with water still submerged under the structure with a blue roof. The cows remain visible, still standing in the floodwater under the structure, which appears to be partially destroyed or damaged. The tree in the foreground remains partially submerged in water, maintaining the continuity of the scene from the previous frame.",
"The scene continues to show the flooded area, with the water still submerged under the structure with a blue roof. The cows are still visible, standing in the floodwater under the structure, which appears to be partially destroyed or damaged. The tree in the foreground remains partially submerged in water, maintaining the continuity of the scene from the previous frame.",
"The scene continues to depict the flooded area, with the water level maintaining its submersion under the structure with a blue roof. The cows remain visible, still standing in the floodwater under the structure, which continues to appear partially destroyed or damaged. The tree in the foreground remains partially submerged in water, maintaining the continuity of the scene from the previous frame.",
"The cows continue to stand in the floodwater under the structure with the blue roof, which remains partially destroyed. The water level remains high, submerging the cows up to their bellies. The tree in the foreground remains partially submerged, showing the ongoing impact of the flood.",
"The cows are still standing in the floodwater under the structure with the blue roof, which is still partially destroyed. The water level remains high, submerging the cows up to their bellies. The tree in the foreground is still partially submerged, continuing to show the ongoing impact of the flood.",
"The cows continue to stand in the floodwater under the blue-roofed structure, which remains partially destroyed. The water level remains high, submerging the cows up to their bellies. The tree in the foreground is still partially submerged, indicating the ongoing impact of the flood.",
"The cows are still standing in the floodwater under the blue-roofed structure, which remains partially destroyed. The water level is unchanged, submerging the cows up to their bellies. A tree in the foreground is partially submerged, and there are additional items floating in the water, indicating the ongoing impact of the flood."
] |
1291976724456992776
|
A flooded area is depicted, with water submerged under a partially destroyed structure with a blue roof. Cows are standing in the floodwater, up to their bellies, under the structure. A tree in the foreground is partially submerged, and the scene remains relatively static throughout, indicating a stagnant flood situation with no visible changes or rescue efforts. The video shows the ongoing impact of the flood on the area, with the cows and the tree remaining in the water, and additional items floating in the water in the later frames.
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.