Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual
Collection
Datasets used in the paper: Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video Retrieval
•
36 items
•
Updated
Dataset Viewer
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.
|
End of preview. Expand
in Data Studio
README.md exists but content is empty.
- Downloads last month
- 3
Size of downloaded dataset files:
6.24 MB
Size of the auto-converted Parquet files:
6.24 MB
Number of rows:
2,394