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
stringlengths 16
163
| prequel
listlengths 0
15
| sequel
listlengths 0
15
| during
listlengths 0
15
| metadata
dict | num_of_frames
int64 32
32
| frame_captions
listlengths 32
32
| video_id
stringlengths 9
9
| frame2video_caption
stringlengths 380
2.6k
|
|---|---|---|---|---|---|---|---|---|
a person is connecting something to system
|
[
"A person holding a cable and approaching a computer to establish a connection to a system",
"Plugging a USB device into a port for connection to a system",
"Configuring network settings on a device for connection to a system",
"Connecting a power cord to a socket for connection to a system",
"A person typing IP address into a device to connect to a system for network connection"
] |
[
"A person plugging a cable into a port for connection to a system",
"A person typing on a keyboard to configure the connection to a system",
"A device being attached to a network router during connection to a system",
"A person scanning a QR code to connect to a system",
"A person entering a password to authenticate a connection to a system"
] |
[
"A person holding a cable for connection to a system",
"A person plugging a cable into a port for connection to a system",
"A person turning on a device to connect to a system",
"A person configuring settings on a screen during connection to a system",
"A person testing their connection to a system"
] |
{
"article_url": null,
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a person is connecting something to system<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: To extract events from the query \"a person is connecting something to system\", it makes sense to consider the physical actions involved in connecting a device or object to a system, as these actions can be visualized in a video. The events should be specific and concrete, focusing on the physical interactions between the person and the system.\n\nEVENTS:\n1. A person holding a cable\n2. A person plugging a cable into a port\n3. A person turning on a device\n4. A person configuring settings on a screen\n5. A person testing the connection",
"en_article_excerpt": "a person is connecting something to system",
"en_article_url": null,
"event_category": null,
"event_name": null,
"language": null,
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a person is connecting something to system<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query \"a person is connecting something to system\", it makes sense to consider common scenarios where someone is linking a device or component to a larger network or infrastructure, such as a computer system or a power grid. This could involve physical actions like plugging in cables or configuring settings, which can be visualized in a video.\n\nEVENTS:\n1. A person holding a cable and approaching a computer\n2. Plugging a USB device into a port\n3. Configuring network settings on a device\n4. Connecting a power cord to a socket\n5. A person typing IP address into a device to connect to a network",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a person is connecting something to system<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the action of connecting something to a system, focusing on the physical or visual aspects of the connection process. This could include events that show the person interacting with the system or the object being connected, as these would be concrete and visualizable in a video.\n\nEVENTS:\n1. A person plugging a cable into a port\n2. A person typing on a keyboard to configure the connection\n3. A device being attached to a network router\n4. A person scanning a QR code to connect to a system\n5. A person entering a password to authenticate the connection",
"video_URL": "https://youtube.com/watch?v=video9770",
"video_description": null,
"video_id": "video9770"
}
| 32
|
[
"A person is plugging a cable into a desktop computer tower.",
"A person is plugging a cable into a desktop computer tower.",
"A person is connecting a component or cable to the side panel of the desktop computer tower.",
"The person is reaching towards the front of the desktop computer tower, possibly to adjust or secure a component inside.",
"The person is closing the side panel of the desktop computer tower, indicating that they have finished the adjustments or installations inside.",
"The person is securing the side panel of the desktop computer tower, ensuring it is properly attached after completing the adjustments or installations.",
"The person is finishing up the process of securing the side panel of the desktop computer tower, ensuring it is properly attached after completing the adjustments or installations.",
"The person is holding the side panel of the desktop computer tower in place, ensuring it is properly aligned and ready for reattachment after making the necessary adjustments or installations.",
"The person is securing the side panel of the desktop computer tower, pressing it firmly against the chassis to ensure it clicks into place, completing the reassembly process.",
"The person is still focusing on the desktop computer tower, likely ensuring that all components are properly secured and the side panel is fully attached to the chassis.",
"The person continues to work on the desktop computer tower, using their hand to secure the side panel, ensuring it is properly attached to the chassis.",
"The person is finishing up the installation by ensuring the side panel of the desktop computer tower is securely fastened to the chassis.",
"The person is tightening the screws on the side panel to complete the assembly of the desktop computer tower, making sure it is securely attached.",
"The person is attaching a side panel to the desktop computer tower, securing it in place.",
"The person is closing the side panel of the desktop computer tower, ensuring it is securely fastened.",
"The person is adjusting the side panel of the desktop computer tower to ensure it is properly aligned and securely fastened.",
"The person is securing the side panel of the desktop computer tower by tightening a screw with a screwdriver, ensuring the panel is firmly attached.",
"The person continues to secure the side panel of the desktop computer tower, using their hands to firmly press the panel into place while tightening the screws to ensure a secure fit.",
"The person is adjusting the side panel of the desktop computer tower, carefully aligning it to fit properly.",
"The person is attaching the side panel of the desktop computer tower, ensuring it is securely fastened.",
"The person is securing the side panel of the desktop computer tower with screws, ensuring it is properly attached.",
"The person is tightening the screws on the side panel of the desktop computer tower, ensuring it is firmly attached.",
"The person is adjusting the side panel of the desktop computer tower, making sure it is securely in place.",
"The person is now securing the side panel of the desktop computer tower with screws, using a screwdriver to tighten them.",
"The person continues to secure the side panel of the desktop computer tower, completing the reassembly process.",
"The person is in the process of closing the side panel of the desktop computer tower, completing the reassembly process.",
"The person is seen securing the side panel onto the desktop computer tower, ensuring it is properly aligned and fastened to complete the reassembly process.",
"The person is seen continuing the reassembly process of the desktop computer tower. The individual, now wearing a white shirt, is focusing on securing the side panel onto the tower, making sure it is properly aligned and fastened.",
"The person is still engaged in the reassembly of the desktop computer tower, ensuring the side panel is properly aligned and secured onto the tower.",
"The person is carefully holding the desktop computer tower, aligning the side panel to secure it back onto the tower.",
"The person is pressing down on the side panel of the desktop computer tower, ensuring it is securely fastened back onto the main unit.",
"The person is adjusting the monitor, likely ensuring it is properly positioned or aligned."
] |
video9770
|
A person is assembling or reassembling a desktop computer tower, focusing on connecting cables, installing components, and securing the side panel to the chassis. The individual ensures all parts are properly attached and aligned, using tools such as a screwdriver to tighten screws and secure the panel in place. The process involves multiple steps of adjustment and tightening to guarantee a secure fit. Once the side panel is attached, the person checks the overall assembly, making any necessary adjustments before completing the task and finally adjusting the monitor to its proper position.
|
a little girl does gymnastics
|
[
"A little girl runs towards a springboard during a gymnastics performance",
"little girl jumps over a hurdle during a gymnastics performance",
"little girl balances on a balance beam during a gymnastics performance",
"Little girl performs a cartwheel on a mat during a gymnastics performance",
"the little girl lands a dismount from the uneven bars during a gymnastics performance"
] |
[
"Little girl performs a cartwheel during a gymnastics performance",
"She balances on one foot on a balance beam during a gymnastics performance",
"The girl executes a backflip on a spring floor during a gymnastics performance",
"She hangs from the uneven bars during a gymnastics performance",
"The little girl lands a dismount from the vault during a gymnastics performance"
] |
[
"little girl runs towards a springboard during a gymnastics performance",
"She jumps over a mini hurdle during a gymnastics performance",
"Girl performs a cartwheel on a mat during a gymnastics performance",
"She balances on a balance beam during a gymnastics performance",
"The little girl lands a dismount from a mini trampoline during a gymnastics performance"
] |
{
"article_url": null,
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a little girl does gymnastics<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: To extract events from the query \"a little girl does gymnastics\", it makes sense to consider common gymnastics movements and routines that a young girl might perform, as these would be visually representative in a video. The extracted events should be specific and concrete enough to be captioned in a video frame, showcasing the girl's actions and movements.\n\nEVENTS:\n1. The little girl runs towards a springboard\n2. She jumps over a mini hurdle\n3. The girl performs a cartwheel on a mat\n4. She balances on a balance beam\n5. The little girl lands a dismount from a mini trampoline",
"en_article_excerpt": "a little girl does gymnastics",
"en_article_url": null,
"event_category": null,
"event_name": null,
"language": null,
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a little girl does gymnastics<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query \"a little girl does gymnastics\", it makes sense to consider common actions and movements typically performed in gymnastics, as well as the setting in which these activities usually take place. This will help to identify specific, visual events that could be captured in a video of a little girl participating in gymnastics.\n\nEVENTS:\n1. A little girl runs towards a springboard\n2. The little girl jumps over a hurdle\n3. The little girl balances on a balance beam\n4. The little girl performs a cartwheel on a mat\n5. The little girl lands a dismount from the uneven bars",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a little girl does gymnastics<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query \"a little girl does gymnastics\", it makes sense to extract events that are typical movements or poses seen in gymnastics, as they could be visualized in a video and are relevant to the activity. The extracted events should be specific to a young girl participating in gymnastics, taking into account common gymnastics moves and routines.\n\nEVENTS:\n1. The little girl performs a cartwheel\n2. She balances on one foot on a balance beam\n3. The girl executes a backflip on a spring floor\n4. She hangs from the uneven bars\n5. The little girl lands a dismount from the vault",
"video_URL": "https://youtube.com/watch?v=video9771",
"video_description": null,
"video_id": "video9771"
}
| 32
|
[
"A young child is standing on a gym floor, wearing a sleeveless athletic outfit. The child has their hair styled in two buns and appears to be smiling. The background includes a red and black stripe on the wall and a blue mat or equipment to the right.",
"The young child, still wearing the sleeveless athletic outfit, is captured in a dynamic pose with their arms raised above their head. They continue to stand on the gym floor, with the red and black stripe on the wall and the blue mat still visible in the background. The child's facial expression suggests focus and determination.",
"The young child, still wearing the sleeveless athletic outfit, is captured in a dynamic pose with one arm raised and the other behind their back. They continue to stand on the gym floor, with the red and black stripe on the wall and the blue mat still visible in the background. The child's facial expression suggests focus and determination.",
"The young child, still in the sleeveless athletic outfit, is now standing upright with both arms by their sides. They maintain focus and determination, standing on the gym floor with the red and black stripe on the wall and the blue mat visible in the background.",
"The young child, still in the sleeveless athletic outfit, is now standing upright with both arms by their sides. They maintain focus and determination, standing on the gym floor with the red and black stripe on the wall and the blue mat visible in the background.",
"The young child, still in the sleeveless athletic outfit, is walking towards the camera with one hand near their chest, maintaining focus and determination. The red and black stripe on the wall and the blue mat remain visible in the background.",
"The young child, now in the sleeveless athletic outfit, is still walking towards the camera, with one hand near their chest, displaying focus and determination. The red and black stripe on the wall and the blue mat remain visible in the background.",
"The young child continues walking towards the camera, maintaining focus and determination. The red and black stripe on the wall and the blue mat remain visible in the background.",
"The young child is walking towards the camera, showing determination and focus. The red and black stripe on the wall and the blue mat are still visible in the background.",
"The young child, now in a running motion, displays increased energy and enthusiasm. The red and black stripe on the wall and the blue mat remain visible in the background.",
"The young child continues running energetically, with legs extended in a sprint. The blue mat and red and black striped wall are still present in the background.",
"The young child is seen leaping towards the blue mat, arms outstretched in preparation for landing. The blue mat and red and black striped wall remain visible in the background.",
"The young child is in the air, having just jumped from the wooden beam, with arms outstretched and legs extended, preparing to land on the blue mat. The blue mat and red and black striped wall remain visible in the background.",
"The young child is in the midst of landing on the blue mat after jumping from the wooden beam, with arms extended and legs slightly bent to absorb the impact. The blue mat and red and black striped wall are still visible in the background.",
"The young child is now fully on the blue mat, having successfully landed after jumping from the wooden beam. Their legs are bent and arms are outstretched for balance, with the blue mat and red and black striped wall still in the background.",
"The young child, now standing upright on the blue mat, appears to be preparing for the next activity. They are raising their arms slightly, possibly stretching or getting ready for another exercise. The blue mat and the red and black striped wall remain in the background, consistent with the previous frame. The wooden beam is no longer in view, indicating the child may be transitioning to a different area of the gym.",
"The young child is now in mid-air, having launched off the blue mat. They are performing a jump or gymnastic maneuver, with their arms extended above their head. The blue mat and the red and black striped wall remain in the background, consistent with the previous frames. The child appears to be transitioning to a different activity or exercise within the gym.",
"The young child is captured mid-air, having completed their jump or gymnastic maneuver from the blue mat. Their arms remain extended above their head, and their body is positioned in a dynamic pose. The blue mat and the red and black striped wall are still visible in the background. The child appears to be landing or transitioning into the next part of their routine, possibly moving towards another gymnastics apparatus in the gym.",
"The young child is now standing on a blue mat in a gymnasium, their arms still extended, possibly signaling the completion of a routine or preparing for the next maneuver. The gym equipment and apparatuses remain visible in the background.",
"The young child is standing on the blue mat in the gymnasium, arms still extended, likely signaling the completion of a routine or preparing for the next maneuver. Gym equipment and apparatuses are visible in the background.",
"The young child, wearing a purple leotard, stands on the blue mat with arms raised in a poised position, possibly concluding a gymnastics routine or preparing for another action. The gymnasium setting includes visible equipment like mats and beams in the background.",
"The young child, still in a purple leotard, stands on the blue mat with arms raised, indicating the continuation of a gymnastics routine or a brief pause between movements. The gymnasium setting remains consistent, with equipment visible in the background.",
"The young child in a purple leotard is standing on the blue mat with arms raised, possibly preparing for the next part of the gymnastics routine or concluding the current sequence. The gymnasium setting is consistent, with gym equipment visible in the background.",
"The young child in a purple leotard is standing on the blue mat with arms raised high above her head. She appears to be in a pose, possibly celebrating or transitioning between parts of her gymnastics routine. The gymnasium setting remains consistent, with gym equipment visible in the background.",
"The young child in a purple leotard continues to stand on the blue mat, now with her arms extended outwards in a V-shape. Her pose suggests a moment of balance or a transition phase in her gymnastics routine. The gymnasium setting remains consistent, with gym equipment still visible in the background.",
"The young child in a purple leotard stands on the blue mat, with her hands positioned along her sides. The scene continues to be set in the gymnasium, with gym equipment still visible in the background, indicating a moment of pause or preparation in her gymnastics routine.",
"The young child in a purple leotard stands on the blue mat, with her hands slightly raised from her sides. The scene continues to be set in the gymnasium, with gym equipment still visible in the background, indicating a moment of pause or preparation in her gymnastics routine.",
"The young child in a purple leotard remains on the blue mat, now with her hands by her sides. She appears to be readying herself for her next move in her gymnastics routine.",
"The young child in a purple leotard stands on the blue mat with her hands by her sides, looking around, possibly preparing for her next action in her gymnastics routine.",
"The young child in a purple leotard is now lifting one leg slightly, maintaining balance on the blue mat, likely transitioning to the next part of her gymnastics routine.",
"The young child in a purple leotard is walking on the blue mat, likely transitioning between elements of her gymnastics routine.",
"The young child in a purple leotard is running on the blue mat, likely preparing to perform a gymnastics move or transition to another element of her routine."
] |
video9771
|
A young child, initially wearing a sleeveless athletic outfit and later a purple leotard, is participating in a gymnastics routine in a gymnasium. The child begins by standing on the gym floor, displaying focus and determination, before transitioning into various dynamic poses and movements. They perform a series of jumps, leaps, and landings on a blue mat, showcasing their gymnastics skills. The child also runs, walks, and stands on the mat, transitioning between different elements of their routine. Throughout the video, the child maintains a focused and determined expression, indicating their engagement and concentration on the gymnastics activities. The setting remains consistent, with a red and black striped wall and various gym equipment visible in the background, emphasizing the athletic and competitive nature of the event.
|
a woman creating a fondant baby and flower
|
[
"Kneading the fondant to soften it when creating a fondant baby",
"Kneading the fondant to soften it for creating a flower",
"How to shape fondant into a baby figure when creating a fondant baby",
"Shaping the fondant into a baby figure while creating a flower decoration",
"Coloring the fondant to add details to the baby's face and body when creating a fondant baby",
"Coloring the fondant to add details to the baby's face and body",
"Creating flower petals from fondant and assembling them into a flower for decorating a fondant baby",
"Creating a flower by making flower petals from fondant and assembling them into a flower",
"How to place a fondant flower in the baby's hand or near the baby figure when creating a fondant baby",
"Placing a fondant flower created for a decoration in the baby's hand or near the baby figure while creating a flower arrangement"
] |
[
"Kneading and coloring the fondant for creating a fondant baby",
"Kneading and coloring the fondant for creating a flower",
"Shaping the fondant into a baby figure while creating a fondant baby",
"Shaping the fondant into a baby figure for cake decorating",
"Creating delicate flower petals from fondant for a fondant baby decoration",
"Creating delicate flower petals from fondant for creating a flower",
"Assembling the flower and adding details when creating a fondant baby",
"Assembling the flower and adding details when creating a flower",
"Creating a fondant baby and placing it in a scene with the finished flower",
"Placing a fondant baby in a scene with a finished flower after creating a flower"
] |
[
"Kneading the fondant to soften it when creating a fondant baby",
"Kneading the fondant to soften it for creating a flower",
"Shaping the fondant into a baby figure while creating a fondant baby",
"Shaping the fondant into a baby figure while creating a flower decoration",
"Adding details to the fondant baby's face while creating a fondant baby",
"Adding details to the fondant baby's face",
"Creating flower petals from colored fondant for a fondant baby decoration",
"Creating flower petals from colored fondant for creating a flower",
"Assembling fondant flowers into a decorative arrangement for creating a fondant baby",
"Assembling fondant flowers into a decorative arrangement while creating a flower"
] |
{
"article_url": null,
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a woman creating a fondant baby and flower<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: To decompose the event of a woman creating a fondant baby and flower, it makes sense to extract specific steps or actions involved in the process that could be visually represented in a video, considering the typical techniques and materials used in fondant modeling. This will allow for a clear and concrete visualization of the event in a video.\n\nEVENTS:\n1. Kneading the fondant to soften it\n2. Shaping the fondant into a baby figure\n3. Adding details to the fondant baby's face\n4. Creating flower petals from colored fondant\n5. Assembling the fondant flowers into a decorative arrangement",
"en_article_excerpt": "a woman creating a fondant baby and flower",
"en_article_url": null,
"event_category": null,
"event_name": null,
"language": null,
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a woman creating a fondant baby and flower<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query \"a woman creating a fondant baby and flower\", it makes sense to focus on the specific steps involved in the creative process of working with fondant, as these steps can be visually represented in a video. The events should be concrete and detailed enough to be captioned in a frame of a video showcasing the woman's creative process.\n\nEVENTS:\n1. Kneading the fondant to soften it\n2. Shaping the fondant into a baby figure\n3. Coloring the fondant to add details to the baby's face and body\n4. Creating flower petals from fondant and assembling them into a flower\n5. Placing the fondant flower in the baby's hand or near the baby figure",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a woman creating a fondant baby and flower<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the process of creating a fondant baby and flower, as these are specific and visual tasks that can be captured in a video. The events should focus on the steps involved in shaping and decorating the fondant to create the desired designs.\n\nEVENTS:\n1. Kneading and coloring the fondant\n2. Shaping the fondant into a baby figure\n3. Creating delicate flower petals from fondant\n4. Assembling the flower and adding details\n5. Placing the fondant baby in a scene with the finished flower",
"video_URL": "https://youtube.com/watch?v=video7020",
"video_description": null,
"video_id": "video7020"
}
| 32
|
[
"A pair of hands is shaping a piece of dough or clay, using a tool to refine its form on a work surface.",
"A pair of hands is continuing to shape a piece of dough or clay, pressing and smoothing it with their fingers on a work surface.",
"The hands are now carefully placing a green dough piece, possibly a leaf, onto a small dough figure resembling a turtle, indicating the final decorative stage of the creation process.",
"The hands are adjusting the green dough piece to ensure it is securely placed on the small dough figure, emphasizing the completion of the decorative stage in the creation process.",
"The hands are finishing the placement of the green dough piece, ensuring it is securely attached to the small dough figure, marking the completion of the decorative stage in the creation process.",
"The hands are gently pressing and shaping the green dough piece on top of the small dough figure, further refining its placement and ensuring it is securely attached, completing the decorative stage in the creation process.",
"The hands are finishing the positioning of the green dough leaf on top of the small dough figure, making final adjustments to ensure it is firmly attached and aesthetically pleasing, completing the decorative process.",
"The hands are making final adjustments to the green dough leaf on the small dough figure, ensuring it is securely placed and visually appealing, completing the decorative process.",
"The hands are smoothing out the green dough leaf, ensuring it adheres well and looks polished on the small dough figure, completing the final decorative touches.",
"The hands are finishing the final adjustments to the green dough leaf, making sure it is properly shaped and positioned on the small dough figure, ensuring the decoration looks polished and complete.",
"The hands are carefully positioning the green dough leaf on top of the small pink dough figure, completing the decoration to make it look polished and complete.",
"The hands are adjusting the green dough leaf to ensure it is securely placed on the small pink dough figure, giving the decoration a polished and finished look.",
"The hands continue to adjust the green dough leaf on the pink dough figure, ensuring it is properly positioned and securely attached.",
"The hands are placing the green dough leaf on the pink dough figure, ensuring it is properly positioned and securely attached.",
"The hands are adjusting the green dough leaf on the pink dough figure, carefully smoothing out any wrinkles and ensuring a snug fit around the figure.",
"The hands are continuing to adjust the green dough leaf on the pink dough figure, further smoothing out the surface to ensure it lies flat and adheres properly around the figure.",
"The hands are carefully positioning a green dough leaf over the pink dough figure, ensuring it covers the figure adequately and maintains a smooth appearance.",
"The hands are now smoothing out the green dough leaf on the pink dough figure to ensure a neat and uniform surface.",
"The hands are now smoothing out the yellow dough circle on the pink dough figure to ensure a neat and uniform surface.",
"The hands are using a rolling pin to further flatten and smooth the yellow dough circle on the pink dough figure, ensuring an even and consistent surface.",
"The hands are using a rolling pin to further flatten and smooth the yellow dough circle on the pink dough figure, ensuring an even and consistent surface.",
"The hands continue to use the rolling pin, focusing on flattening and smoothing the yellow dough to achieve an even and consistent surface, maintaining the process from the previous frame.",
"The hands are now using a flower-shaped cutter to cut out shapes from the flattened yellow dough, maintaining the process of preparing the dough by shaping it into decorative pieces.",
"The hands are continuing to use the flower-shaped cutter to cut out shapes from the flattened yellow dough, further shaping the dough into decorative pieces.",
"The hands are pressing a flower-shaped cutter into a small, flattened piece of yellow dough on a baking mat, cutting it into a decorative shape.",
"The hands are removing the flower-shaped cutter from the small, flattened piece of yellow dough on a baking mat, revealing the decorative shape.",
"The hands are using a flower-shaped cutter to imprint a pattern into the small, flattened piece of yellow dough on a baking mat.",
"In the current frame, the hands are using a pair of scissors to carefully cut along the edges of the flower-shaped imprint on the flattened yellow dough, ensuring the shape is well-defined and ready for further crafting or baking.",
"The hands continue to use the scissors to precisely cut around the yellow dough, maintaining the flower shape, with the focus on creating a neat and accurate outline for the next step in the dough crafting process.",
"The hands are using the scissors to make additional cuts around the yellow dough flower, ensuring the petals are evenly shaped and well-defined. The focus remains on achieving a clean and precise outline, advancing the flower crafting process.",
"The hands continue to use the scissors to make additional cuts around the yellow dough flower, ensuring the petals are evenly shaped and well-defined. The focus remains on achieving a clean and precise outline, advancing the flower crafting process.",
"The hands are using scissors to refine the cuts around the yellow dough flower, focusing on perfecting the shape of each petal. The process aims to create a detailed and symmetrical appearance, advancing the floral design."
] |
video7020
|
A person is creating a decorative figure using dough, starting with shaping a small dough figure resembling a turtle. They then add a green dough leaf to the figure, carefully positioning and smoothing it out to ensure it is securely attached and visually appealing. After completing the decoration of the turtle figure, the person moves on to work with yellow dough, flattening it into a circle and smoothing out its surface using a rolling pin. They then use a flower-shaped cutter to cut out decorative shapes from the yellow dough and refine the edges using scissors, aiming to create a precise and symmetrical floral design. Throughout the process, the person carefully handles the dough, making adjustments and refinements to achieve a polished and finished look for their creations.
|
a boy plays grand theft auto 5
|
[
"A boy sitting in front of a TV or computer screen playing a video game",
"The boy holding a gaming controller while playing a video game",
"The Grand Theft Auto 5 game loading screen appearing on the screen while playing a video game",
"The boy's character in the game walking or driving around the virtual city while playing a video game",
"The boy reacting to gameplay, such as jumping back in surprise or smiling at a successful mission completion while playing a video game"
] |
[
"The boy's character drives a car when playing a video game",
"The boy's character shoots at enemies while playing a video game",
"The boy's character completes a mission while playing a video game",
"The boy's character interacts with non-playable characters (NPCs) while playing a video game",
"The boy's character crashes a car while playing a video game"
] |
[
"A boy sitting in front of a TV or computer screen playing a video game",
"The boy holding a gaming controller while playing a video game",
"What does the Grand Theft Auto 5 game interface look like when playing a video game",
"The boy's character driving a car while playing a video game",
"The boy's character in the game engaging in a shootout with non-player characters while playing a video game"
] |
{
"article_url": null,
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a boy plays grand theft auto 5<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: To extract events from the query \"a boy plays Grand Theft Auto 5\", it makes sense to consider the actions and scenes that are likely to occur when someone is playing this video game, taking into account the game's content and typical gameplay. The extracted events should be specific and visual, allowing them to be easily captioned in a video frame.\n\nEVENTS:\n1. A boy sitting in front of a TV or computer screen\n2. The boy holding a gaming controller\n3. The Grand Theft Auto 5 game interface displayed on the screen\n4. The boy's character in the game driving a car\n5. The boy's character in the game engaging in a shootout with non-player characters",
"en_article_excerpt": "a boy plays grand theft auto 5",
"en_article_url": null,
"event_category": null,
"event_name": null,
"language": null,
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a boy plays grand theft auto 5<|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 action of playing a video game, specifically Grand Theft Auto 5, as these events can be visually represented in a video. The extracted events should be concrete and specific to the game and the setting of a boy playing it.\n\nEVENTS:\n1. A boy sitting in front of a TV or computer screen\n2. The boy holding a gaming controller\n3. The Grand Theft Auto 5 game loading screen appearing on the screen\n4. The boy's character in the game walking or driving around the virtual city\n5. The boy reacting to gameplay, such as jumping back in surprise or smiling at a successful mission completion",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a boy plays grand theft auto 5<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the gameplay of Grand Theft Auto 5, as the query specifies that the boy is playing the game. The extracted events should be concrete and visual, such as actions performed by the player character or interactions within the game environment.\n\nEVENTS:\n1. The boy's character drives a car in the game\n2. The boy's character shoots at enemies\n3. The boy's character completes a mission\n4. The boy's character interacts with non-playable characters (NPCs) in the game\n5. The boy's character crashes a car in the game",
"video_URL": "https://youtube.com/watch?v=video9773",
"video_description": null,
"video_id": "video9773"
}
| 32
|
[
"The image depicts a police motorcycle chase on a city street. Multiple police officers on motorcycles are pursuing another motorcycle. The scene takes place in an urban environment with tall buildings lining the street. There is a police car also visible in the chase. The road appears wet, suggesting recent rain.",
"The image continues to depict the police motorcycle chase on a city street. The pursuit continues with police motorcycles and a police car actively engaged in the chase. The wet road persists, indicating ongoing or recent rain. The focus remains on the dynamic and high-speed chase through the urban environment.",
"The image continues to depict the police motorcycle chase on a city street. The pursuit continues with police motorcycles and a police car actively engaged in the chase. The wet road persists, indicating ongoing or recent rain. The focus remains on the dynamic and high-speed chase through the urban environment.",
"The image is a black screen with the text \"MARCH 10\" displayed in white.",
"The scene transitions to a video game showing a green sports car driving on a road, with the text \"MARCH 10\" overlaid on the image.",
"The green sports car continues to drive on a winding road, with the environment shifting to a more rural setting.",
"The green sports car is now driving on a straight road, continuing through a rural landscape with trees and hills. The road appears to be leading towards a large, distinctive structure in the distance.",
"The green sports car is still driving on the straight road, getting closer to the large, distinctive structure. The road continues through the rural landscape with trees and hills. The car's speed is indicated by the visible speedometer, and the destination appears to be the structure ahead.",
"The green sports car continues driving on the winding road, approaching the large, distinctive structure in the distance. The road is flanked by trees and hills, maintaining the rural setting. The car's speed is still indicated by the visible speedometer, suggesting it is moving steadily towards the structure ahead.",
"The green sports car is now closer to the large, distinctive structure in the distance, still driving on the winding road flanked by trees and hills. The car's speedometer remains visible, indicating steady progression towards the structure ahead.",
"The green sports car is now closer to the large, distinctive structure in the distance, still driving on the winding road flanked by trees and hills. The car's speedometer remains visible, indicating steady progression towards the structure ahead.",
"The green sports car has reached the top of a large ramp, positioned for a significant jump, with a clear view of the landscape and sky in the background.",
"The green sports car is airborne, having launched off the ramp with the landscape and sky visible in the background.",
"The green sports car is still airborne, now positioned above a set of bleachers and distant cityscape, maintaining its trajectory in mid-flight.",
"The green sports car continues to soar through the air, still above the set of bleachers and the distant cityscape, maintaining its trajectory in mid-flight.",
"The green sports car is in mid-air, continuing its trajectory away from the set of bleachers, with a cityscape visible in the distance.",
"The green sports car is still airborne, maintaining its flight path away from the bleachers with the cityscape in the background.",
"The green sports car continues to be airborne, maintaining its flight trajectory over the cityscape with the same mountainous terrain in the background.",
"The green sports car remains airborne, continuing its flight trajectory over the cityscape with the same mountainous terrain in the background. The car's elevated position suggests it is still soaring through the air, possibly after performing a stunt or jump. The scene captures the sense of motion and adventure, with the car positioned centrally and the landscape below providing a dynamic backdrop.",
"The green sports car continues to be airborne, maintaining its flight trajectory over the cityscape with the same mountainous terrain in the background. The car's elevated position suggests it is still soaring through the air, possibly after performing a stunt or jump. The scene captures the sense of motion and adventure, with the car positioned centrally and the landscape below providing a dynamic backdrop.",
"The green sports car remains airborne, continuing its flight trajectory over the cityscape. The mountainous terrain in the background remains consistent with the previous frame, indicating the car is still soaring through the air, likely following a stunt or jump. The car is centrally positioned, with the dynamic landscape below adding to the sense of motion and adventure.",
"The green sports car continues its flight over the cityscape, maintaining its airborne trajectory. The mountainous terrain remains in the background, confirming the car is still in mid-air. The car is centrally positioned, with the dynamic landscape below enhancing the sense of motion and adventure.",
"The green sports car remains airborne over the cityscape, continuing its dynamic flight. The mountainous terrain still serves as the backdrop, and the car is centrally positioned, emphasizing the ongoing sense of motion and adventure.",
"The green sports car continues its flight, now positioned slightly higher and farther from the buildings, maintaining its dynamic trajectory over the cityscape. The mountainous backdrop remains consistent, reinforcing the adventurous atmosphere as the car soars above the urban environment.",
"The green sports car is still in flight, continuing its dynamic trajectory over the cityscape. The car remains slightly higher and farther from the buildings, with the mountainous backdrop still visible, reinforcing the adventurous atmosphere.",
"The green sports car is in mid-air, continuing its flight over the cityscape. The car is slightly lower and closer to the buildings, with the mountainous backdrop still visible, reinforcing the adventurous atmosphere.",
"The green sports car continues its flight over the city, now slightly lower with buildings becoming more prominent. The mountainous backdrop remains visible, adding to the adventurous setting.",
"The green sports car is still airborne, descending closer to the road amidst urban surroundings. The car's trajectory remains consistent, with buildings and trees below, capturing the ongoing high-speed pursuit.",
"The green sports car is now on the road, having landed smoothly and continuing its high-speed pursuit amidst the urban surroundings. The car is positioned on the right side of the road, with the trajectory consistent, and buildings and trees visible on the sides.",
"The green sports car continues to drive on the road, maintaining its high speed. The car remains on the right side of the road, with the trajectory consistent. The surrounding environment includes buildings and trees, indicating the urban setting. The car's shadow is visible on the road, suggesting the presence of sunlight. The scene suggests the car is still in pursuit or racing mode, as indicated by the steady, forward momentum.",
"The green sports car continues to drive on the road, maintaining its high speed. The car remains on the right side of the road, with the trajectory consistent. The surrounding environment includes buildings and trees, indicating the urban setting. The car's shadow is visible on the road, suggesting the presence of sunlight. The scene suggests the car is still in pursuit or racing mode, as indicated by the steady, forward momentum.",
"The green sports car continues to drive on the road, maintaining its high speed. The car remains on the right side of the road, with the trajectory consistent. The surrounding environment includes buildings and trees, indicating the urban setting. The car's shadow is visible on the road, suggesting the presence of sunlight. The scene suggests the car is still in pursuit or racing mode, as indicated by the steady, forward momentum."
] |
video9773
|
The video depicts two distinct scenes. The first part shows a high-speed police motorcycle chase on a wet city street, involving multiple police officers on motorcycles and a police car pursuing another motorcycle. The scene is set in an urban environment with tall buildings.
The video then transitions to a video game scenario where a green sports car is driven on various roads, initially in a rural setting and later in a cityscape. The car performs a significant jump from a ramp and soars through the air, flying over a set of bleachers and the cityscape, before landing back on the road and continuing at high speed through an urban environment. The car's journey is dynamic, capturing a sense of motion and adventure as it navigates through different landscapes.
|
a man is giving a review on a vehicle
|
[
"The man walking around the vehicle to inspect its exterior during a review of a vehicle",
"The man sitting in the driver's seat and starting the engine during a review of a vehicle",
"The man test driving the vehicle on a road or test track during a review of a vehicle",
"The man pointing out specific features of the vehicle's interior during a review of a vehicle",
"The man speaking directly to the camera to share his review and opinions of a vehicle"
] |
[
"The man walking around the vehicle to inspect it during a review of a vehicle",
"The man sitting in the driver's seat and starting the engine during a review of a vehicle",
"The man driving the vehicle to test its performance during a review of a vehicle",
"The man pointing out specific features of the vehicle, such as the infotainment system or safety features during a review of a vehicle",
"The man checking the vehicle's trunk space or cargo area during a review of a vehicle"
] |
[
"A man standing next to a vehicle during a review of a vehicle",
"The man walking around the vehicle to inspect it during a review of a vehicle",
"The man sitting in the driver's seat of the vehicle during a review",
"The man gesturing to the vehicle's features while speaking during a review of a vehicle",
"The man test-driving the vehicle during a review of a vehicle"
] |
{
"article_url": null,
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a man is giving a review on a vehicle<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are visually related to a person providing a review of a vehicle, such as interacting with the vehicle or expressing their opinions. These events should be concrete and easily visualizable in a video, focusing on the reviewer's actions and the vehicle itself.\n\nEVENTS:\n1. A man standing next to a vehicle\n2. The man walking around the vehicle to inspect it\n3. The man sitting in the driver's seat of the vehicle\n4. The man gesturing to the vehicle's features while speaking\n5. The man test-driving the vehicle",
"en_article_excerpt": "a man is giving a review on a vehicle",
"en_article_url": null,
"event_category": null,
"event_name": null,
"language": null,
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a man is giving a review on a vehicle<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query \"a man is giving a review on a vehicle\", it makes sense to consider actions that are typically involved in reviewing a vehicle, such as inspecting the vehicle's features, test driving, and sharing opinions. These events should be concrete and visual, allowing them to be reasonably captioned in a video frame associated with the query.\n\nEVENTS:\n1. The man walking around the vehicle to inspect its exterior\n2. The man sitting in the driver's seat and starting the engine\n3. The man test driving the vehicle on a road or test track\n4. The man pointing out specific features of the vehicle's interior\n5. The man speaking directly to the camera to share his review and opinions",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a man is giving a review on a vehicle<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the action of reviewing a vehicle, such as the man inspecting the vehicle, driving it, or pointing out its features. These events are likely to be visual and concrete, making them suitable for a video caption.\n\nEVENTS:\n1. The man walking around the vehicle to inspect it\n2. The man sitting in the driver's seat and starting the engine\n3. The man driving the vehicle to test its performance\n4. The man pointing out specific features of the vehicle, such as the infotainment system or safety features\n5. The man checking the vehicle's trunk space or cargo area",
"video_URL": "https://youtube.com/watch?v=video7026",
"video_description": null,
"video_id": "video7026"
}
| 32
|
[
"A person is off-roading or driving in a rugged, rocky terrain. The vehicle is on a rocky surface surrounded by large boulders and sparse vegetation, indicating a desert or rocky environment.",
"The vehicle continues its off-roading journey through the rugged, rocky terrain, navigating around large boulders and sparse vegetation. The landscape remains arid and rocky, suggesting the vehicle is still traversing through a desert or mountainous area.",
"The vehicle continues its off-roading journey through rugged, rocky terrain. It navigates around large boulders and sparse vegetation. The landscape remains arid and rocky, indicating the vehicle is still traversing through a desert or mountainous area.",
"The vehicle continues its off-roading journey through rugged, rocky terrain. It navigates around large boulders and sparse vegetation. The landscape remains arid and rocky, indicating the vehicle is still traversing through a desert or mountainous area.",
"The vehicle continues its off-roading journey through a rugged, rocky terrain, maintaining its course as it navigates around large boulders and sparse vegetation. The landscape remains arid and rocky, indicating the vehicle is still traversing through a desert or mountainous area.",
"The vehicle's dashboard display shows a speed of 1.2 MPH, indicating a slow movement through the rugged terrain. The text \"Descent available\" is visible, suggesting the vehicle's descent control system is ready for use. The environment appears to be the same arid and rocky landscape from the previous frame.",
"The vehicle's dashboard indicates a speed of 1.2 MPH, maintaining slow movement through the rugged terrain. The text \"Descent available\" is visible, suggesting the descent control system is ready. The environment continues to be an arid and rocky landscape.",
"The vehicle's dashboard displays a speed of 1 MPH, indicating very slow movement through the rugged terrain. The text \"Descent available\" remains visible, suggesting the descent control system is still ready. The environment continues to be an arid and rocky landscape.",
"The vehicle's dashboard now displays a speed of 1.2 MPH, indicating a slight increase in movement through the rugged terrain. The text \"Descent available\" remains visible, suggesting the descent control system is still ready. The environment continues to be an arid and rocky landscape.",
"The vehicle's dashboard continues to show a speed of 1.2 MPH, maintaining the slow progress through the rough terrain. The text \"P-R-N\" is now visible, indicating the vehicle is in neutral gear. The environment remains arid and rocky, with no significant changes.",
"The vehicle's dashboard displays a speed of 0 MPH, indicating that the vehicle is stationary. The text \"P-R-N\" remains visible, confirming that the vehicle is still in neutral gear. The environment continues to be arid and rocky, with no significant changes. The text \"E\" is also visible, suggesting the vehicle is in electric mode or an energy-saving feature is activated.",
"The vehicle's dashboard shows a speed of 1.2 MPH, indicating that the vehicle has started to move slowly. The text \"P-R-N\" is still visible, confirming that the vehicle is in neutral gear. The environment remains arid and rocky, with no significant changes. The text \"E\" is still visible, suggesting the vehicle is in electric mode or an energy-saving feature is activated.",
"The vehicle's dashboard shows a speed of 1.2 MPH, indicating that the vehicle is still moving slowly. The text \"P-R-N\" is still visible, confirming that the vehicle remains in neutral gear. The environment remains arid and rocky, with no significant changes. The text \"E\" is still visible, suggesting the vehicle is in electric mode or an energy-saving feature is activated. The message \"Speed unavailable\" is displayed, indicating a potential issue with the speedometer or a temporary glitch.",
"The vehicle's dashboard shows a speed of 2.5 MPH, indicating that the vehicle is still moving slowly. The text \"P-R-N\" is still visible, confirming that the vehicle remains in neutral gear. The environment remains arid and rocky, with no significant changes. The text \"E\" is still visible, suggesting the vehicle is in electric mode or an energy-saving feature is activated. The message \"Speed unavailable\" continues to be displayed, indicating a potential issue with the speedometer or a temporary glitch.",
"The vehicle's dashboard shows a speed of 1.2 MPH, indicating a slight decrease in speed. The text \"P-R-N\" remains visible, confirming the vehicle is still in neutral gear. The environment continues to be arid and rocky with no significant changes. The text \"E\" is still present, suggesting the vehicle is in electric mode or an energy-saving feature is activated. The message \"Speed unavailable\" continues to be displayed, indicating a potential issue with the speedometer or a temporary glitch.",
"The vehicle's dashboard indicates a speed of 4.2 MPH, showing a slight increase from the previous frame. The text \"P-R-N\" is still visible, confirming the vehicle remains in neutral gear. The environment remains arid and rocky, consistent with the previous frame. The text \"E\" continues to be present, suggesting the vehicle is in electric mode or an energy-saving feature is still activated. The message \"Speed unavailable\" is still displayed, indicating the ongoing issue with the speedometer or a temporary glitch.",
"The person is inside a vehicle, holding the steering wheel, indicating they are either driving or preparing to drive. The interior of the car is visible with a black dashboard, center console, and seats. The exterior environment is not fully visible, but some trees can be seen through the windows, suggesting the vehicle is parked or moving through a forested or wooded area. The person appears to be focused on the road ahead, suggesting they are engaged in the driving activity.",
"The person is inside a vehicle, no longer holding the steering wheel, and appears to be engaging in a conversation or explaining something. Their hands are raised in a gesturing manner, indicating they are actively speaking. The interior of the car remains visible with a black dashboard, center console, and seats. The exterior environment is still partially visible, with trees seen through the windows, suggesting the vehicle is still in a forested or wooded area. The person seems more relaxed and less focused on the road, suggesting they are not actively driving at this moment.",
"The person is still inside the vehicle, continuing their conversation or explanation. They are gesturing with both hands, emphasizing their points. The interior remains the same with a black dashboard and seats, and the wooded area is still visible outside. The person's posture and hand movements suggest they are deeply engaged in the discussion.",
"The person is inside the vehicle, gesturing with their right hand while speaking. The interior remains consistent with black dashboard and seats, and the wooded area is visible outside. Their posture and hand movements indicate ongoing engagement in the conversation.",
"The person continues inside the vehicle, gesturing with their right hand and left hand while speaking. The interior remains consistent with black dashboard and seats, and the wooded area is visible outside. Their posture and hand movements indicate ongoing engagement in the conversation.",
"The person is inside the vehicle, seated in the driver's seat, holding the steering wheel with their left hand and gesturing with their right hand. The vehicle's interior remains consistent with black dashboard and seats. The wooded area is visible outside. The person's posture and hand movements indicate ongoing engagement in the conversation.",
"The person is still inside the vehicle, seated in the driver's seat, holding the steering wheel with their left hand. They are gesturing with their right hand while talking, indicating ongoing engagement in the conversation. The vehicle's interior remains consistent with black dashboard and seats, and a wooded area is visible outside through the windows.",
"The person remains seated in the driver's seat, holding the steering wheel with their left hand. They continue to gesture with their right hand while talking, maintaining engagement in the conversation. The vehicle's interior remains consistent with the previous frame, featuring a black dashboard and seats, and a wooded area is still visible outside through the windows.",
"The person is still seated in the driver's seat, holding the steering wheel with their left hand. They are gesturing with their right hand while talking, maintaining engagement in the conversation. The vehicle's interior remains consistent, with a black dashboard and seats, and a wooded area is visible outside through the windows.",
"The person is still seated in the driver's seat, holding the steering wheel with their left hand. They are gesturing with their right hand while talking, maintaining engagement in the conversation. A black thermos cup is visible on the center console. The vehicle's interior remains consistent, with a black dashboard and seats, and a wooded area is visible outside through the windows.",
"The person remains seated in the driver's seat, with their left hand still on the steering wheel. They continue to gesture with their right hand while talking, maintaining engagement in the conversation. The black thermos cup is still visible on the center console. The vehicle's interior remains consistent, and the wooded area is still visible outside through the windows.",
"The person remains seated in the driver's seat, with their right hand on the steering wheel. They continue to gesture with their left hand while talking, maintaining engagement in the conversation. The black thermos cup is still visible on the center console. The vehicle's interior remains consistent, and the wooded area is still visible outside through the windows.",
"The person is still seated in the driver's seat, with their right hand on the steering wheel. They continue to gesture with their left hand while talking, maintaining engagement in the conversation. The black thermos cup remains visible on the center console. The vehicle's interior remains consistent, and the wooded area is still visible outside through the windows.",
"The person is seated in the driver's seat, with their right hand on the steering wheel. They are gesturing with their left hand while talking, indicating they are still engaged in conversation. The black thermos cup is still visible on the center console. The vehicle's interior remains unchanged, and the wooded area is still visible outside through the windows.",
"The person is still seated in the driver's seat, with their right hand on the steering wheel and their left hand raised as if gesturing. The black thermos cup remains on the center console. The vehicle's interior is unchanged, and the wooded area is still visible outside through the windows.",
"The scene shows the interior of a vehicle, focusing on the driver's area. The driver is seated with their right hand on the steering wheel. The left hand is raised, suggesting a gesture or conversation. The black thermos cup is still on the center console. The vehicle's interior, including the dashboard, remains consistent with the previous frame."
] |
video7026
|
The video depicts a person driving a vehicle through a rugged, rocky terrain, likely in a desert or mountainous area, at a slow speed. The vehicle navigates around large boulders and sparse vegetation, with the driver occasionally checking the dashboard, which displays information such as speed and gear. The speed remains relatively slow, around 1-2 MPH, with occasional increases and decreases. The vehicle's descent control system is available, and the dashboard displays various messages, including "Descent available" and "Speed unavailable," indicating potential issues with the speedometer.
After driving through the rocky terrain, the scene shifts to the person inside the vehicle, parked or moving slowly through a forested or wooded area. The driver is engaged in a conversation, gesturing with their hands while seated in the driver's seat and occasionally holding the steering wheel. The vehicle's interior remains consistent throughout, with a black dashboard, center console, and seats. A black thermos cup is visible on the center console during the conversation. The person continues to talk and gesture, indicating an ongoing engagement in the conversation, as the vehicle remains stationary or moves slowly through the wooded area.
|
a man speaks to children in a classroom
|
[
"A man writes on a blackboard while teaching",
"A man writes on a blackboard during a public speaking engagement",
"Children raising their hands to answer a question during teaching",
"Children raising their hands to answer a question during public speaking",
"The man hands out worksheets to the students during a teaching session",
"The man hands out worksheets to the students during a public speaking event",
"Children take notes while the man lectures during a teaching session",
"Children take notes while the man lectures during a public speaking event",
"The man helps a student with a problem on their desk during a teaching moment",
"The man helps a student with a problem on their desk"
] |
[
"The man writes on the blackboard while teaching",
"The man writes on the blackboard during a public speaking engagement",
"Children taking notes during teaching",
"Children taking notes during public speaking events",
"The man distributes handouts to the students during a teaching session",
"The man distributes handouts to the students during a public speaking event",
"Students ask the man questions during a teaching session",
"Students ask the man questions during a public speaking event",
"The man uses visual aids to explain a concept while teaching",
"The man uses visual aids to explain a concept during public speaking"
] |
[
"A man stands at the front of the classroom teaching and writes on the blackboard",
"A man stands at the front of the classroom and writes on the blackboard while engaged in public speaking",
"Children look up at the man with interest and take notes during a teaching session",
"Children look up at the man with interest and take notes during a public speaking event",
"A man gestures as he explains a concept to the class while teaching",
"The man gestures as he explains a concept to the class during a public speaking engagement",
"Children raise their hands to ask questions during teaching",
"Children raising their hands to ask questions during public speaking",
"A man walks around the classroom to assist individual students during teaching",
"The man walks around the classroom to assist individual students during a public speaking lesson"
] |
{
"article_url": null,
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a man speaks to children in a classroom<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a classroom setting and involve interaction between a teacher and students, as these are common and visual elements that could be captured in a video. The events should focus on the man's actions and the children's reactions or responses to create a clear and concrete visualization.\n\nEVENTS:\n1. A man stands at the front of the classroom and writes on the blackboard\n2. Children look up at the man with interest and take notes\n3. The man gestures as he explains a concept to the class\n4. Children raise their hands to ask questions\n5. The man walks around the classroom to assist individual students",
"en_article_excerpt": "a man speaks to children in a classroom",
"en_article_url": null,
"event_category": null,
"event_name": null,
"language": null,
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a man speaks to children in a classroom<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical in a classroom setting and involve interaction between a teacher and students, as these events are likely to be visualized in a video associated with the query. The extracted events should be concrete and specific, such as actions the man or children might be doing, to serve as reasonable captions for a frame of a video.\n\nEVENTS:\n1. A man writes on a blackboard\n2. Children raise their hands to answer a question\n3. The man hands out worksheets to the students\n4. Children take notes while the man lectures\n5. The man helps a student with a problem on their desk",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a man speaks to children in a classroom<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical interactions or activities that occur in a classroom setting, considering the context of a man speaking to children. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. The man writes on the blackboard\n2. Children take notes\n3. The man distributes handouts to the students\n4. Students ask the man questions\n5. The man uses visual aids to explain a concept",
"video_URL": "https://youtube.com/watch?v=video9775",
"video_description": null,
"video_id": "video9775"
}
| 32
|
[
"In the image, a group of five children is sitting in a classroom setting. They appear to be engaged in an activity or listening to someone off-camera. The children are seated on shelves filled with books and storage bins. The classroom is decorated with educational posters and charts on the walls.",
"The children remain seated in the classroom, still engaged in their activity or listening to someone off-camera. The classroom environment remains consistent, with educational materials and posters in the background.",
"The children are seated in the classroom, actively participating in an activity or listening attentively to someone off-camera. The classroom setting is consistent with educational materials and posters in the background.",
"The children are still seated in the classroom, continuing to participate in the activity or listen attentively to someone off-camera. The classroom environment remains educational with materials and posters in the background.",
"The children are still seated in the classroom, continuing to participate in the activity or listen attentively to someone off-camera. The classroom environment remains educational with materials and posters in the background.",
"The man is seated at a table in the classroom, engaged in an activity or conversation, likely interacting with the children or discussing an educational topic.",
"The man is seated at a table in the classroom, speaking and likely engaging with the children or discussing an educational topic.",
"The man is still seated at the table in the classroom, continuing his discussion with the children or explaining an educational topic.",
"The man is still seated at the table in the classroom, continuing his discussion with the children or explaining an educational topic.",
"In the classroom setting, a man continues his discussion with the children, who are attentively engaging with him. Several children are seated around a table, listening and possibly participating in the conversation. One child in a pink outfit and another in a purple top appear to be interacting with the man, while others observe the exchange. The classroom environment, with educational posters and a calendar on the wall, suggests an ongoing learning session.",
"In the classroom, a man is conversing with a group of children, who are seated and actively participating in the discussion. The children show interest by facing the man and engaging with him, while the classroom setting, complete with educational posters and a calendar, indicates a continuous learning session.",
"In the classroom, a group of children is engaged in a lively discussion, with one girl in a pink top actively participating and smiling. The children are facing towards each other, indicating active interaction. The classroom remains filled with educational materials, and the calendar on the wall shows that the session continues.",
"In the classroom, a group of children is engaged in a lively discussion. The girl in the pink top continues to actively participate and smile. The children are facing towards each other, indicating ongoing interaction. The classroom remains filled with educational materials, and the calendar on the wall confirms that the session continues.",
"In the classroom, a group of children continues their lively discussion. The girl in the pink top remains actively engaged, smiling and interacting with her peers. The children are still facing each other, maintaining their ongoing interaction. The classroom is filled with educational materials, and the calendar on the wall still indicates the continuity of the session.",
"In the classroom, a man is seated at a round table, appearing to be engaged in a conversation or interview. The table has papers on it, and he is holding a clipboard. The classroom is decorated with colorful educational materials, and a calendar on the wall indicates the ongoing session.",
"The man remains seated at the round table in the classroom, continuing his conversation or interview. He is still holding the clipboard and appears to be listening or responding to someone off-camera. The classroom setting remains consistent, with educational materials and a calendar visible in the background.",
"The man continues to be seated at the round table in the classroom, maintaining his conversation or interview. He is still holding the clipboard and appears to be engaging in the discussion, possibly listening or responding to someone off-camera. The classroom setting remains the same, with educational materials and a calendar visible in the background.",
"The young boy is seated in the classroom, likely participating in a discussion or interview. He is wearing a white shirt and appears to be listening or responding to someone off-camera. The classroom setting remains consistent with educational materials, including a colorful banner with images of food, visible in the background.",
"The young boy is speaking in the classroom. He is wearing a white shirt and appears to be engaged in a conversation or presentation. The classroom setting remains consistent with educational materials, including a colorful banner with images of food, visible in the background.",
"The young boy is continuing his speech or presentation in the classroom. He is still wearing a white shirt and appears to be engaged in the conversation. The classroom setting remains consistent with educational materials, including a colorful banner with images of food, visible in the background.",
"The young boy is actively speaking, continuing his presentation in the classroom. He is still wearing a white shirt and remains engaged in his speech. The classroom setting is consistent with educational materials, including a colorful banner with images of food in the background.",
"The young boy is standing in a classroom, appearing thoughtful or contemplative while speaking. He is still wearing a white shirt, and the classroom setting with educational materials, including a colorful banner with images of food, remains unchanged.",
"The young boy is still standing in the classroom, wearing a white shirt. He continues to appear thoughtful or contemplative while speaking, maintaining the same posture as before. The classroom setting remains consistent, with the colorful banner featuring images of food in the background.",
"The young boy stands in the classroom, wearing a white shirt. He appears thoughtful or contemplative while speaking, maintaining the same posture as before. The classroom setting remains consistent, with the colorful banner featuring images of food in the background.",
"The young boy continues to stand in the classroom, still wearing his white shirt. He appears to be in the middle of speaking, maintaining a thoughtful expression. The classroom setting remains consistent, with the colorful banner featuring images of food still visible in the background.",
"The young boy stands in the classroom, wearing his white shirt. He seems to be speaking, maintaining a thoughtful expression. The colorful banner with food images remains visible in the background.",
"The young boy continues to stand in the classroom, still wearing his white shirt, and appears to be engaged in speaking. He maintains a thoughtful expression, suggesting he is sharing an idea or answering a question. The colorful banner with food images remains visible in the background, indicating the educational setting.",
"The young boy, identified by his name tag as \"Alton,\" continues to stand in the classroom, still wearing his white shirt. He appears to be engaged in speaking, maintaining a thoughtful expression. The colorful banner with food images remains visible in the background, reinforcing the educational setting.",
"The young boy, identified by his name tag as \"Alton,\" continues to stand in the classroom. He appears to be actively speaking, maintaining a thoughtful expression. The colorful banner with food images remains visible in the background, reinforcing the educational setting.",
"The young boy, identified by his name tag as \"Alton,\" continues to stand in the classroom, actively speaking with a thoughtful expression. The colorful banner with food images remains visible in the background, reinforcing the educational setting.",
"The young boy, identified by his name tag as \"Alton,\" continues to speak in the classroom, still maintaining a thoughtful expression. The colorful banner with food images remains visible in the background, reinforcing the educational setting.",
"Alton, the young boy, is seated in the classroom, engaged in a discussion. He maintains a thoughtful expression, suggesting he is actively participating in the conversation. The colorful banner with food images is still visible in the background, indicating the educational context remains consistent."
] |
video9775
|
A group of children, approximately five in number, are engaged in a learning session in a classroom setting. The session involves active participation and discussion, led by a man who interacts with the children, explaining educational topics and facilitating their engagement. The children, including a girl in a pink top and a boy named Alton, show interest and enthusiasm, asking questions and sharing ideas. The classroom environment is filled with educational materials, posters, and a calendar, indicating a structured learning environment. Throughout the session, Alton is particularly active, standing up to speak and share his thoughts, demonstrating his engagement and participation in the discussion. The overall context suggests a supportive and interactive learning environment where children are encouraged to express themselves and learn from each other and the adult facilitator.
|
one micky mouse is talking to other
|
[
"Mickey Mouse walking up to a group of friends in a park and starting a conversation with them",
"Mickey Mouse shaking hands with Goofy while talking to him and other characters",
"Mickey Mouse having a conversation with Minnie Mouse while talking to others",
"Mickey Mouse laughing with Pluto and Donald Duck while talking to them",
"Mickey Mouse waving at a crowd of Disney characters while talking to others"
] |
[
"Mickey Mouse shaking hands with another character while talking to others",
"Mickey Mouse laughing with his friends while talking to them",
"Mickey Mouse having a conversation with Minnie Mouse while talking to others",
"Mickey Mouse gesturing to a group of characters while talking to them",
"Mickey Mouse listening to Pluto bark in response while talking to others"
] |
[
"Mickey Mouse standing in front of a colorful background and speaking while talking to others",
"Other Disney characters gathering around Mickey Mouse as he talks to them",
"Mickey Mouse gesturing with his hands while talking to his friends",
"Other characters responding or reacting to what Mickey Mouse is saying when he talks to them",
"Mickey Mouse laughing or smiling while interacting with other characters when talking to them"
] |
{
"article_url": null,
"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: one micky mouse is talking to other<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query \"one Mickey Mouse is talking to other\", it makes sense to extract events that are typical of a scene where Mickey Mouse is interacting with others, likely in a cartoon or theme park setting. The events should be concrete and visual, such as Mickey Mouse engaging in conversation or interacting with his friends.\n\nEVENTS:\n1. Mickey Mouse standing in front of a colorful background and speaking\n2. Other Disney characters gathering around Mickey Mouse to listen\n3. Mickey Mouse gesturing with his hands while talking to his friends\n4. Other characters responding or reacting to what Mickey Mouse is saying\n5. Mickey Mouse laughing or smiling while interacting with the other characters",
"en_article_excerpt": "one micky mouse is talking to other",
"en_article_url": null,
"event_category": null,
"event_name": null,
"language": null,
"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: one micky mouse is talking to other<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that involve Mickey Mouse interacting with other characters, as this is a common scenario in cartoons and animated videos. Given the context of Mickey Mouse, it's likely that the events will be lighthearted and family-friendly, and may involve other well-known Disney characters.\n\nEVENTS:\n1. Mickey Mouse walking up to a group of friends in a park\n2. Mickey Mouse shaking hands with Goofy\n3. Mickey Mouse having a conversation with Minnie Mouse\n4. Mickey Mouse laughing with Pluto and Donald Duck\n5. Mickey Mouse waving at a crowd of Disney characters",
"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: one micky mouse is talking to other<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical interactions or scenarios involving Mickey Mouse, given his character and common portrayals in media. The events should be concrete and visual, considering what could be reasonably depicted in a video featuring Mickey Mouse conversing with others.\n\nEVENTS:\n1. Mickey Mouse shaking hands with another character\n2. Mickey Mouse laughing with his friends\n3. Mickey Mouse having a conversation with Minnie Mouse\n4. Mickey Mouse gesturing to a group of characters\n5. Mickey Mouse listening to Pluto bark in response",
"video_URL": "https://youtube.com/watch?v=video9776",
"video_description": null,
"video_id": "video9776"
}
| 32
|
[
"The image shows an animated character resembling a cow, wearing a yellow hat and an orange cape. The background is colorful, featuring a pink and purple pattern. There is no visible text or additional context in the image.",
"The animated character, still resembling a cow, is now seen smiling and winking, maintaining the yellow hat and orange cape. The background remains colorful with a pink and purple pattern.",
"The animated cow character continues to smile broadly, with eyes wide open, maintaining its cheerful demeanor. The yellow hat and orange cape are still present, and the background remains colorful with pink and purple patterns, enhancing the vibrant atmosphere of the scene.",
"The animated cow character continues to smile broadly, with eyes wide open, maintaining its cheerful demeanor. The yellow hat and orange cape are still present, and the background remains colorful with pink and purple patterns, enhancing the vibrant atmosphere of the scene.",
"The animated cow character is now seen with its mouth open in a wide, joyful expression, possibly laughing or singing, while maintaining its broad smile. The yellow hat and orange cape are still present, and the background continues to display colorful patterns, enhancing the cheerful atmosphere of the scene.",
"The animated cow character is looking forward with a cheerful expression, maintaining its yellow hat and orange cape. The background displays colorful patterns, continuing the vibrant and joyful atmosphere.",
"The animated cow character appears surprised or curious, with its eyes wide open and mouth slightly ajar. It still wears the yellow hat and orange cape. The background remains vibrant with colorful patterns.",
"The animated cow character, still wearing the yellow hat and orange cape, is now looking more attentive, with eyes slightly narrowed and mouth closed. The background continues to display colorful patterns, maintaining a vibrant atmosphere.",
"The animated cow character, still adorned with the yellow hat and orange cape, now appears to be more focused and alert. The character's eyes are wide open and directed forward, with a slight furrow indicating concentration. The background remains vibrant with colorful patterns, contributing to the lively atmosphere.",
"The animated cow character, maintaining its yellow hat and orange cape, displays a determined expression with a furrowed brow. The character's eyes are wide open, indicating focus and readiness. The background continues to be vibrant with colorful patterns, maintaining the lively atmosphere. The character's posture and expression suggest active engagement, possibly in a task or confrontation.",
"The animated cow character, still wearing its yellow hat and orange cape, now appears with a surprised or curious expression. Its eyes are wide open, conveying a sense of wonder or discovery. The character's posture remains engaged, indicating that it is still actively involved in the situation. The background continues with vibrant colors and patterns, maintaining the lively atmosphere.",
"The animated cow character, still wearing its yellow hat and orange cape, maintains its curious expression. Its wide eyes suggest ongoing wonder or discovery. The character's engaged posture indicates continuous active involvement in the situation. The vibrant background with colorful patterns persists, sustaining the lively atmosphere.",
"The animated cow character, still in its yellow hat and orange cape, shows an open mouth, possibly indicating speech or surprise. Its eyes are wide, maintaining the expression of wonder or discovery. The character remains actively engaged, suggesting ongoing interaction in the lively, colorful setting.",
"The animated cow character continues in the same colorful setting, now with a closed mouth and a slight smile, indicating a calm or satisfied demeanor. Its eyes are still wide but appear more relaxed than in the previous frame. The character seems to be in a moment of pause or reflection, possibly after a conversation or interaction.",
"The animated cow character maintains its calm demeanor, now with a slight smile and relaxed wide eyes, appearing to be in a moment of pause or reflection.",
"The animated cow character continues to maintain a calm and content demeanor, with a slight smile and relaxed wide eyes, suggesting it is still in a moment of pause or reflection. The character is wearing a yellow hat, adding a whimsical touch to the scene. The background features a purple and pink color scheme, with a windmill partially visible, reinforcing the playful and serene atmosphere of the setting.",
"The animated cow character maintains its calm and content demeanor with a slight smile and wide eyes, suggesting it is still in a moment of pause or reflection. The character remains wearing a yellow hat, adding a whimsical touch to the scene. The background features a purple and pink color scheme, with a windmill partially visible, reinforcing the playful and serene atmosphere of the setting.",
"The animated cow character is now engaged in a joyful and lively action. It is seen with its mouth wide open, as if it is laughing or cheering, and its eyes are closed, indicating happiness and excitement. The character's head is tilted slightly to one side, adding to the animated and playful expression. The background remains consistent with a purple and pink color scheme, and the windmill is still partially visible. The overall atmosphere suggests a moment of celebration or amusement, continuing the whimsical and cheerful tone of the video.",
"The animated cow character, with a yellow hat and a joyful expression, continues to tilt its head slightly to one side. Its eyes are now open, and its mouth remains wide, further suggesting laughter or excitement. The background retains the purple and pink color scheme with the partially visible windmill, maintaining the cheerful and whimsical atmosphere of the video.",
"In this animated scene, the cow character maintains its joyful demeanor, with a slightly tilted head and an open mouth, continuing to suggest laughter or excitement. The character's yellow hat and the whimsical purple and pink background remain consistent, preserving the cheerful atmosphere. The windmill in the background remains partially visible, adding to the playful setting.",
"The cow character continues to exhibit a joyful expression, now with its head tilted slightly to the side. The character's yellow hat and the whimsical purple and pink background remain consistent, maintaining the cheerful atmosphere. The windmill in the background remains partially visible, adding to the playful setting.",
"The cow character now displays a surprised expression, with wide eyes and a slightly open mouth. The yellow hat and whimsical purple and pink background continue to provide a cheerful setting. The windmill remains partially visible, contributing to the playful atmosphere.",
"The cow character is now holding a wand with a star on top, still showing a surprised expression with wide eyes and a slightly open mouth. The whimsical purple and pink background remains consistent, maintaining the playful atmosphere.",
"The cow character continues to hold the wand with a star on top, maintaining a surprised expression with wide eyes and a slightly open mouth. The playful atmosphere is sustained with the whimsical purple and pink background.",
"The cow character maintains its expression of surprise with wide eyes and a slightly open mouth, still holding the wand with a star on top. The playful and whimsical atmosphere is continued with the colorful background.",
"The cow character now has a cheerful expression with a wide smile and closed eyes, still holding the wand with a star on top. The playful and whimsical atmosphere continues with the colorful background.",
"The cow character is still holding the wand with a star on top, maintaining its cheerful expression with a wide smile and closed eyes. The whimsical and playful atmosphere persists with the colorful background.",
"The cow character maintains its cheerful expression with a wide smile and open eyes. The whimsical and playful atmosphere persists with the colorful background.",
"The cow character continues to smile and look cheerful, holding a yellow star wand, reinforcing the playful atmosphere with the vibrant background.",
"The cow character is smiling and holding a yellow star wand, reinforcing the playful atmosphere with the vibrant background.",
"The cow character is still smiling and holding the yellow star wand, maintaining the playful atmosphere with the vibrant background.",
"The cow character continues to smile while holding the yellow star wand, enhancing the playful atmosphere with a vibrant background."
] |
video9776
|
The video features an animated cow character wearing a yellow hat and an orange cape, set against a vibrant and colorful background with pink and purple patterns. The character's expressions and actions change throughout the video, ranging from smiling and winking to looking surprised, curious, and determined. At one point, the character appears to be engaged in a task or interaction, then transitions to a moment of pause or reflection. The setting later includes a windmill in the background, adding to the whimsical atmosphere. The character also holds a wand with a star on top at some points, further enhancing the playful and magical tone. Throughout the video, the cow character's expressions and actions convey a sense of joy, wonder, and engagement, creating a lively and cheerful atmosphere.
|
a naked child runs through a field
|
[
"A child takes off their clothes while running through a field",
"A child plays outside without clothes on a warm day while running through a field",
"child runs away from lake or pool without clothes",
"a child being chased while running through a field",
"A child playing tag or catch while running through a field without clothes"
] |
[
"A child running through a field of tall grass",
"A child laughing and spinning while running through a field",
"A parent or guardian chasing after a child running through a field",
"A child running through a field playing with flowers or wild plants",
"A child running through a field and eventually stopping to look back or play with an object found in the field"
] |
[
"A child runs through a field without clothes",
"The child's legs and arms move as they run through a field",
"A child's hair flowing in the wind as they run through a field",
"A child laughs or smiles while running through the field",
"A child running through a field with their bare feet touching the grass or dirt"
] |
{
"article_url": null,
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a naked child runs through a field<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query \"a naked child runs through a field\", it makes sense to extract events that are directly related to the action of a child running in a field without clothes, considering typical scenes that could be visualized in a video. The extracted events should focus on the child's movement and interaction with the field environment.\n\nEVENTS:\n1. A child runs through a field without clothes\n2. The child's legs and arms move as they run\n3. The child's hair flows in the wind as they run\n4. The child laughs or smiles while running through the field\n5. The child's bare feet touch the grass or dirt in the field",
"en_article_excerpt": "a naked child runs through a field",
"en_article_url": null,
"event_category": null,
"event_name": null,
"language": null,
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a naked child runs through a field<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query \"a naked child runs through a field\", it makes sense to extract events that could lead to this scene, such as the child removing their clothes or being in a situation where they would not be wearing clothes, and then running through the field. These events should be concrete and visual, allowing them to be reasonably captioned in a video frame.\n\nEVENTS:\n1. A child takes off their clothes near a field\n2. A child plays outside without clothes on a warm day\n3. A child runs away from a body of water, such as a lake or pool, without clothes\n4. A child is chased by someone or something while running through the field\n5. A child is playing tag or a game of catch in the field without clothes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a naked child runs through a field<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query \"a naked child runs through a field\", it makes sense to extract events that are visually plausible and related to the action of a child running in a field without clothes, considering typical scenarios and environments where such an event might occur. The extracted events should be concrete and capable of being depicted in a video, taking into account common aspects of a field setting and the implications of a child running naked.\n\nEVENTS:\n1. A child running through tall grass\n2. The child laughing and spinning in the field\n3. A parent or guardian chasing after the child\n4. The child playing with flowers or wild plants in the field\n5. The child eventually stopping to look back or play with an object found in the field",
"video_URL": "https://youtube.com/watch?v=video7025",
"video_description": null,
"video_id": "video7025"
}
| 32
|
[
"A young child is running across a grassy area near a body of water, with several people lounging and sitting in the background. The setting appears to be a beach or park area.",
"The young child continues to run across the grassy area near the body of water. The child's motion suggests they are engaged in play, moving swiftly through the open space. In the background, several people remain lounging and sitting, enjoying the sunny day. The setting remains consistent with a beach or park environment, with the calm water visible beyond the grassy area.",
"The young child is still running across the grassy area near the body of water. The child's motion continues to suggest they are engaged in play, moving swiftly through the open space. In the background, several people are still lounging and sitting, enjoying the sunny day. The setting remains consistent with a beach or park environment, with the calm water visible beyond the grassy area.",
"In the current frame, the young child continues to run across the grassy area near the body of water, maintaining their swift and playful motion. The background still shows several people lounging and sitting, enjoying the sunny day. The setting remains consistent with a beach or park environment, with the calm water visible beyond the grassy area. The scene depicts a lively, sunny day at the beach with people relaxing and enjoying the outdoors.",
"In the current frame, the young child continues to run across the grassy area near the body of water, maintaining their swift and playful motion. The background still shows several people lounging and sitting, enjoying the sunny day. The setting remains consistent with a beach or park environment, with the calm water visible beyond the grassy area. The scene depicts a lively, sunny day at the beach with people relaxing and enjoying the outdoors.",
"The current frame depicts a lively scene at the beach or park with several people relaxing and enjoying the sunny day. In the foreground, a woman is walking towards the camera, while a young child continues to run across the grassy area near the body of water. Several colorful umbrellas are visible, providing shade for the people lounging on the grass. The calm water remains visible in the background, and the overall setting continues to convey a sense of leisure and enjoyment in an outdoor environment.",
"In this frame, the scene remains at the beach or park with several people still relaxing and enjoying the sunny day. The woman is now jogging towards the camera, while the young child continues to run across the grassy area near the body of water. The colorful umbrellas still provide shade for the people lounging on the grass. The calm water remains visible in the background, and the overall setting continues to convey a sense of leisure and enjoyment in an outdoor environment.",
"The scene continues at the beach or park, with people still enjoying the sunny day. The woman who was jogging is now standing in the foreground, appearing relaxed. The young child continues to run across the grassy area near the body of water. Colorful umbrellas still provide shade for the people lounging on the grass, and the calm water remains visible in the background. The overall setting maintains a sense of leisure and enjoyment in an outdoor environment.",
"In the current frame, the scene remains at the beach or park, where the woman in the foreground is now walking, possibly having completed her jog. The young child is still running across the grassy area near the body of water, suggesting continuous play. Colorful umbrellas continue to provide shade for people lounging on the grass, and the calm water remains visible in the background. The atmosphere continues to exude leisure and enjoyment in an outdoor setting.",
"The scene continues at the beach or park, where people are relaxing under colorful umbrellas on the grass. The woman in the foreground is bent over, possibly picking something up or adjusting her attire. The young child is no longer visible, indicating they may have moved out of the frame. The atmosphere remains leisurely and enjoyable, with the calm water still visible in the background.",
"The scene remains at the beach, where a larger group of people are now visible, relaxing on the sand near the water. Some individuals are sitting or lying down, while others are standing or walking. The atmosphere continues to be leisurely and relaxed, with a clear view of the calm water in the background. There are no visible umbrellas in this frame, indicating a shift in the setting or time of day.",
"The scene continues at the beach with a larger group of people gathered. Individuals are seen sitting, lying, and standing along the shoreline. The atmosphere remains relaxed, with people enjoying the beach and the calm water in the background. There are no visible umbrellas, suggesting a consistent setting and time of day as in the previous frame.",
"The scene remains at the beach, with a large group of people still gathered along the shoreline. Individuals are seen sitting, lying, and standing, continuing to enjoy the relaxed atmosphere. Some people are near the water's edge, while others are further back on the sand. The calm water in the background adds to the serene environment, maintaining the consistency of the setting and time of day as previously described.",
"The beach scene continues with people leisurely enjoying the sunny day. The crowd remains spread along the shoreline, with some sitting and relaxing on the sand, while others are standing or walking near the water. The water's gentle waves and the consistent setting indicate the scene persists in a relaxed, sunny atmosphere, with no significant changes from the previous frame.",
"The beach scene persists with people leisurely enjoying the sunny day. The crowd remains spread along the shoreline, with some sitting and relaxing on the sand, while others are standing or walking near the water. The water's gentle waves and the consistent setting indicate the scene persists in a relaxed, sunny atmosphere, with no significant changes from the previous frame.",
"The beach scene continues with people leisurely enjoying the sunny day. The crowd remains spread along the shoreline, with some sitting and relaxing on the sand, while others are standing or walking near the water. The water's gentle waves and the consistent setting indicate the scene persists in a relaxed, sunny atmosphere, with no significant changes from the previous frame.",
"The beach scene continues with people leisurely enjoying the sunny day. The crowd remains spread along the shoreline, with some sitting and relaxing on the sand, while others are standing or walking near the water. The water's gentle waves and the consistent setting indicate the scene persists in a relaxed, sunny atmosphere, with no significant changes from the previous frame.",
"The beach scene continues with people leisurely enjoying the sunny day. The crowd remains spread along the shoreline, with some sitting and relaxing on the sand, while others are standing or walking near the water. The water's gentle waves and the consistent setting indicate the scene persists in a relaxed, sunny atmosphere, with no significant changes from the previous frame.",
"The current frame shows a portrait of a young man looking directly at the camera with a serious expression. The image is black and white, suggesting it might be historical or archival in nature. There is no visible text in the image. The context appears to be focused solely on this individual, contrasting with the previous beach scene descriptions.",
"The current frame continues to show a portrait of a young man looking directly at the camera with a serious expression. The image remains black and white, maintaining the historical or archival feel. There is no visible text in the image. The focus remains solely on this individual, consistent with the previous frame's description, with no additional context or elements introduced.",
"The current frame continues to show a portrait of a young man looking directly at the camera with a serious expression. The image remains black and white, maintaining the historical or archival feel. There is no visible text in the image. The focus remains solely on this individual, consistent with the previous frame's description, with no additional context or elements introduced.",
"The frame shows a close-up portrait of a young man with a serious expression, looking directly at the camera. The image is black and white, maintaining a historical or archival feel. There is no visible text, and the focus remains solely on the individual, consistent with the previous frame’s depiction.",
"The current frame continues to feature a close-up portrait of a young man with a serious expression, looking directly at the camera. The image remains black and white, reinforcing the historical or archival ambiance established in the previous frame. The individual’s attire appears to be formal or uniform-like, suggesting a context of significance or ceremony. The consistent focus on the individual and lack of visible text maintain the continuity of the video's narrative.",
"The current frame continues to feature a close-up portrait of a young man with a serious expression, looking directly at the camera. The image remains black and white, reinforcing the historical or archival ambiance established in the previous frame. The individual's attire appears to be formal or uniform-like, suggesting a context of significance or ceremony. The consistent focus on the individual and lack of visible text maintain the continuity of the video's narrative.",
"The current frame continues to focus on a close-up portrait of the young man, maintaining the same serious expression and direct gaze at the camera. The black and white imagery persists, enhancing the historical or archival feel. The individual's formal or uniform-like attire is still prominent, reinforcing the sense of significance or ceremony. The absence of visible text and the steady camera work contribute to the continuity of the video's narrative.",
"The current frame continues to showcase a close-up portrait of the young man, maintaining the same serious expression and direct gaze at the camera. The black and white imagery persists, enhancing the historical or archival feel. The individual's formal or uniform-like attire is still prominent, reinforcing the sense of significance or ceremony. The absence of visible text and the steady camera work contribute to the continuity of the video's narrative.",
"The current frame continues to showcase a close-up portrait of the young man, maintaining the same serious expression and direct gaze at the camera. The black and white imagery persists, enhancing the historical or archival feel. The individual's formal or uniform-like attire is still prominent, reinforcing the sense of significance or ceremony. The absence of visible text and the steady camera work contribute to the continuity of the video's narrative.",
"The current frame continues to feature a close-up portrait of the young man, who maintains a serious expression and direct gaze at the camera. The black and white imagery persists, enhancing the historical or archival feel. The individual's formal or uniform-like attire is still prominent, reinforcing the sense of significance or ceremony. The absence of visible text and the steady camera work contribute to the continuity of the video's narrative.",
"The current frame continues to feature a close-up portrait of the young man, who maintains a serious expression and direct gaze at the camera. The black and white imagery persists, enhancing the historical or archival feel. The individual's formal or uniform-like attire is still prominent, reinforcing the sense of significance or ceremony. The absence of visible text and the steady camera work contribute to the continuity of the video's narrative.",
"The current frame continues to feature a close-up portrait of the young man, who maintains a serious expression and direct gaze at the camera. The black and white imagery persists, enhancing the historical or archival feel. The individual's formal or uniform-like attire is still prominent, reinforcing the sense of significance or ceremony. The absence of visible text and the steady camera work contribute to the continuity of the video's narrative.",
"The current frame continues to feature a close-up portrait of the young man, who maintains a serious expression and direct gaze at the camera. The black and white imagery persists, enhancing the historical or archival feel. The individual's formal or uniform-like attire is still prominent, reinforcing the sense of significance or ceremony. The absence of visible text and the steady camera work contribute to the continuity of the video's narrative.",
"The current frame continues to feature a close-up portrait of the young man, who maintains a serious expression and direct gaze at the camera. The black and white imagery persists, enhancing the historical or archival feel. The individual's formal or uniform-like attire is still prominent, reinforcing the sense of significance or ceremony. The absence of visible text and the steady camera work contribute to the continuity of the video's narrative."
] |
video7025
|
The video depicts two distinct scenes. The first part of the video shows a young child playing and running in a grassy area near a body of water, likely a beach or park, on a sunny day. Several people are lounging and sitting in the background, enjoying the outdoors under colorful umbrellas. As the scene progresses, a woman is seen jogging and then standing, and the child continues to play. The atmosphere is leisurely and relaxed, with people enjoying the sunny day.
The scene then shifts to a beach setting where a larger group of people are gathered, sitting, lying, and standing along the shoreline. The atmosphere remains relaxed, with people enjoying the beach and the calm water.
The video then abruptly changes to a black and white portrait of a young man with a serious expression, looking directly at the camera. He is dressed in formal or uniform-like attire, suggesting a context of significance or ceremony. This portrait continues for an extended period, with no changes in the individual's expression or the camera's focus, maintaining a historical or archival feel. The contrast between the lively, outdoor beach scenes and the solemn, black and white portrait is striking, suggesting a narrative that may be exploring different themes or periods.
|
a little boy singing in front of judges and crowd
|
[
"A little boy standing on a stage with a microphone during a singing performance",
"A little boy standing on a stage with a microphone at a talent show or competition",
"Judges seated at a table with scorecards and pens during a singing performance",
"Judges seated at a table with scorecards and pens at a talent show or competition",
"A crowd of people cheering and applauding in the audience during a singing performance",
"A crowd of people cheering and applauding in the audience at a talent show or competition",
"The little boy taking a deep breath before starting his singing performance",
"little boy taking a deep breath before singing at a talent show or competition",
"Confetti and balloons falling from the ceiling after a singing performance",
"Confetti and balloons falling from the ceiling after a talent show or competition performance"
] |
[
"The little boy stepping up to the microphone for a singing performance",
"The little boy stepping up to the microphone at a talent show or competition",
"Judges taking notes and giving feedback during a singing performance",
"Judges taking notes and giving feedback at a talent show or competition",
"the crowd cheering and applauding during a singing performance",
"crowd cheering and applauding at a talent show or competition",
"The little boy singing with passion and emotion during a singing performance",
"little boy singing with passion and emotion in a talent show or competition",
"Confetti falling or trophies being awarded after a singing performance",
"Confetti falling or trophies being awarded after a performance at a talent show or competition"
] |
[
"A little boy stepping up to a microphone for a singing performance",
"a little boy stepping up to a microphone at a talent show or competition",
"The boy beginning to sing in front of the crowd during a singing performance",
"the boy beginning to sing in front of the crowd at a talent show or competition",
"Judges looking at the boy with expressions of interest or surprise during his singing performance",
"Judges looking at the boy with expressions of interest or surprise at a talent show or competition",
"audience applauding or cheering the boy on during his singing performance",
"audience applauding or cheering the boy on at a talent show or competition",
"boy finishing his song and bowing to the audience at a singing performance",
"boy finishing his song and bowing to the audience at a talent show or competition"
] |
{
"article_url": null,
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a little boy singing in front of judges and crowd<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: This query appears to be related to a talent show or competition setting, where a young boy is performing in front of an audience and a panel of judges, making it reasonable to extract events that are typical of such a scenario. The events extracted should be concrete and visual, allowing them to be easily captioned in a video frame.\n\nEVENTS:\n1. A little boy stepping up to a microphone\n2. The boy beginning to sing in front of the crowd\n3. Judges looking at the boy with expressions of interest or surprise\n4. The audience applauding or cheering the boy on\n5. The boy finishing his song and bowing to the audience",
"en_article_excerpt": "a little boy singing in front of judges and crowd",
"en_article_url": null,
"event_category": null,
"event_name": null,
"language": null,
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a little boy singing in front of judges and crowd<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to a talent show or competition setting, as the presence of judges and a crowd suggests a performance-based scenario. The events should be concrete and visual, allowing for a clear mental image of what the scene might look like in a video.\n\nEVENTS:\n1. A little boy standing on a stage with a microphone\n2. Judges seated at a table with scorecards and pens\n3. A crowd of people cheering and applauding in the audience\n4. The little boy taking a deep breath before starting to sing\n5. Confetti and balloons falling from the ceiling after the performance",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: a little boy singing in front of judges and crowd<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a talent show or competition setting, where a child is performing in front of an audience and judges, and the events should be concrete and visual enough to be captured in a video. The extracted events should reflect the emotions, actions, and reactions of the participants and the audience in this setting.\n\nEVENTS:\n1. The little boy stepping up to the microphone\n2. Judges taking notes and giving feedback\n3. The crowd cheering and applauding\n4. The little boy singing with passion and emotion\n5. Confetti falling or trophies being awarded after the performance",
"video_URL": "https://youtube.com/watch?v=video9778",
"video_description": null,
"video_id": "video9778"
}
| 32
|
[
"A woman with curly hair is sitting in a red chair, smiling and laughing, seemingly reacting to something happening off-camera. She is wearing a black outfit and is seated in what appears to be a television studio setting.",
"The woman continues to sit in the red chair, still smiling and laughing, maintaining her reaction to the off-camera event. She remains in the television studio setting, with her body language relaxed and engaged.",
"The woman is standing at a podium, appearing engaged and possibly reacting to an event or conversation happening off-camera. She maintains a focused expression, consistent with the television studio setting, with the audience visible in the background.",
"The woman is standing at the podium, facing slightly to her right, possibly reacting to someone or something off-camera. Her posture suggests she is engaged and listening intently, consistent with the ongoing event or conversation in the television studio setting. The audience remains visible in the background.",
"The woman is still standing at the podium, now leaning slightly forward, maintaining her focus on the off-camera event or person. Her posture suggests active engagement and attentiveness, possibly preparing to respond or react. The audience in the background continues to watch attentively, indicating the ongoing interactive nature of the event.",
"The woman remains at the podium, still leaning slightly forward, with a more pronounced engagement indicated by her hand gestures. The audience continues to watch attentively, suggesting an ongoing interactive event where she is actively participating or responding.",
"The woman is still at the podium, with her body slightly turned and her hand gestures more pronounced. She appears to be engaging more dynamically with the audience, indicating an ongoing interactive event where she is actively participating or responding.",
"The woman is still at the podium, her body slightly turned and her hand gestures more pronounced, engaging more dynamically with the audience.",
"The woman continues to address the audience, now gesturing with both hands, possibly emphasizing a key point or adding enthusiasm to her speech. The audience appears attentive, indicating ongoing engagement in her presentation.",
"In the current frame, the woman is standing and leaning slightly forward, indicating a shift in her posture. She continues to engage with the audience, possibly in response to their reactions. The audience remains attentive, suggesting that her presentation or interaction is still captivating their interest.",
"The woman is now standing upright and facing the audience, appearing to be in the midst of speaking or addressing them. Her posture and expression suggest she is maintaining an engaging and dynamic interaction with the crowd. The audience continues to be attentive and responsive, indicating that her engagement is still effective.",
"The woman continues to stand upright, now with a slight smile and a more relaxed posture, suggesting she is winding down from her speech or interaction with the audience. The audience remains engaged, with some individuals smiling or clapping, indicating they are enjoying the event and are still attentive to her presence.",
"The woman is now seated on a red chair, still smiling and appearing relaxed. She has a hand raised near her chest, possibly gesturing or reacting to something. The audience remains engaged, with several people visible and some still clapping, indicating ongoing enjoyment and attentiveness.",
"The current frame shows a young boy standing on stage, holding a microphone. He appears to be addressing the audience, possibly singing or speaking, as he is positioned in front of a backdrop featuring the \"X Factor\" logo. The boy is dressed casually in a denim shirt and light-colored pants, with his curly hair styled naturally. His demeanor suggests he is performing or participating in the event.",
"The current frame shows the same young boy on stage, still holding the microphone. He continues to address the audience, likely singing or speaking, maintaining his casual outfit and natural hairstyle. The \"X Factor\" backdrop remains visible, indicating his ongoing participation in the event.",
"The young boy on stage is still holding the microphone, continuing his performance. He appears to be either singing or speaking, maintaining the same casual outfit and natural hairstyle. The \"X Factor\" backdrop remains visible, indicating his ongoing participation in the event.",
"The young boy on stage continues his performance, still holding the microphone. He appears to be singing, maintaining his casual outfit and natural hairstyle. The \"X Factor\" backdrop remains visible, indicating his ongoing participation in the event.",
"The young boy on stage is still engaged in his performance, holding the microphone and singing. He maintains the same casual outfit and natural hairstyle. The \"X Factor\" backdrop remains visible, indicating his ongoing participation in the event.",
"The young boy on stage continues his performance, holding the microphone and singing. He is dressed casually and maintains his natural hairstyle. The \"X Factor\" backdrop is still visible, indicating his ongoing participation in the event.",
"The young boy continues his performance on stage, holding a microphone. He is dressed casually in a blue denim shirt and beige pants. The \"X Factor\" backdrop remains visible, indicating his ongoing participation in the event.",
"The young boy stands confidently on stage, holding a microphone in his right hand. He maintains his casual attire of a blue denim shirt and beige pants. The \"X Factor\" backdrop is prominently visible behind him, emphasizing his participation in the competition.",
"The young boy continues to stand confidently on stage, holding the microphone in his right hand. His casual attire of a blue denim shirt and beige pants remains consistent. The \"X Factor\" backdrop is still prominently visible behind him, reinforcing his presence in the competition.",
"The young boy continues to stand confidently on stage, holding the microphone in his right hand. His casual attire of a blue denim shirt and beige pants remains consistent. The \"X Factor\" backdrop is still prominently visible behind him, reinforcing his presence in the competition.",
"The man, wearing a black T-shirt with the word \"GUILTY\" on it, is seated in a judge's chair. He is clapping, possibly reacting to the performance on stage, suggesting he is evaluating the young boy's singing.",
"The man, still wearing the black T-shirt with the word \"GUILTY\" on it, remains seated in the judge's chair. He continues to clap, indicating his ongoing reaction to the young boy's singing performance. His posture and expression suggest he is impressed and entertained by the performance.",
"The man continues to sit in the judge's chair, maintaining his clapping, which reinforces his positive response to the ongoing performance. His posture and facial expressions remain consistent, reflecting his continued engagement and enjoyment.",
"The man in the judge's chair is clapping enthusiastically, indicating his strong approval of the current performance. His posture and facial expressions remain engaged and positive, showing his continued enjoyment and enthusiasm.",
"The man in the judge's chair is smiling broadly and clapping enthusiastically, maintaining his strong approval of the current performance. His posture and facial expressions continue to show his engagement and enjoyment, reinforcing his positive reaction.",
"The man in the judge's chair is still smiling and clapping, indicating his ongoing approval and enjoyment of the performance. He remains engaged and enthusiastic, continuing to show his positive reaction.",
"The man in the judge's chair is clapping, indicating his continued approval and enjoyment of the performance. He remains engaged and enthusiastic, showing his positive reaction.",
"The man in the judge's chair is still clapping, further displaying his approval and enthusiasm for the performance. He maintains an engaged and positive expression.",
"The woman with long hair is singing passionately, while another woman stands close behind her, clapping and showing support. A man on the right claps and smiles, appearing pleased with the performance. The scene suggests a supportive and engaging atmosphere on the show."
] |
video9778
|
A woman appears to be a guest or participant on a television show, likely "The X Factor," given the setting and the presence of a judge and audience. Initially, she is seated and then stands at a podium, engaging with the audience and possibly responding to questions or participating in a discussion. Her interaction with the audience and her body language suggest a dynamic and engaging presentation or conversation.
The scene then shifts to a young boy performing on stage, singing in front of an "X Factor" backdrop. He is dressed casually and maintains a confident demeanor throughout his performance. A judge, wearing a "GUILTY" T-shirt, is shown clapping and reacting positively to the boy's singing, indicating his approval and enjoyment of the performance.
The video depicts an interactive and engaging atmosphere, with participants and judges showing enthusiasm and support for the performances. The setting of a television studio with a live audience and the presence of judges suggest that the event is a competition or talent show, where contestants perform and receive feedback from the judges and audience. Overall, the video captures the energy and excitement of a live performance event, highlighting the interactions between participants, judges, and the audience.
|
fireworks are being lit and exploding in a night sky
|
[
"Fireworks being set up on the ground or on a fireworks launch pad at night for a fireworks display",
"People gathering at night to watch the fireworks display",
"A fuse being lit, igniting a firework during a nighttime fireworks display",
"Fireworks exploding in the night sky with bursts of color and light during a fireworks display at night",
"Sparks and embers falling to the ground after a firework has exploded during a nighttime fireworks display"
] |
[
"Fireworks display at night with explosions into colorful patterns in the sky",
"Sparks and embers falling from the explosions during a nighttime fireworks display",
"People watching the nighttime fireworks display with reactions of amazement and delight",
"Fireworks rockets shooting up into the air before exploding during a nighttime fireworks display",
"The night sky being illuminated by the bright colors of the fireworks during a fireworks display at night"
] |
[
"Fireworks shooting up into the night sky during a fireworks display at night",
"Explosions of colorful lights and patterns in the sky during a nighttime fireworks display",
"Sparks and embers falling back down to the ground during a nighttime fireworks display",
"People watching and reacting to the nighttime fireworks display",
"The night sky being illuminated by the colorful explosions of a fireworks display at night"
] |
{
"article_url": null,
"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: fireworks are being lit and exploding in a night sky<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query, it makes sense to extract events that describe the visual and dynamic aspects of fireworks exploding in the night sky, as these events can be easily visualized in a video. The extracted events should focus on the actions and movements of the fireworks, as well as the surrounding environment.\n\nEVENTS:\n1. Fireworks shooting up into the night sky\n2. Explosions of colorful lights and patterns in the sky\n3. Sparks and embers falling back down to the ground\n4. People watching and reacting to the fireworks display\n5. The night sky being illuminated by the colorful explosions",
"en_article_excerpt": "fireworks are being lit and exploding in a night sky",
"en_article_url": null,
"event_category": null,
"event_name": null,
"language": null,
"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: fireworks are being lit and exploding in a night sky<|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 preparation and display of fireworks, as these are the most likely to be visualized in a video of fireworks being lit and exploding in a night sky. Events that involve people setting up or reacting to the fireworks could also be relevant, as they provide context and add to the visual narrative of the video.\n\nEVENTS:\n1. Fireworks being set up on the ground or on a fireworks launch pad\n2. People gathering to watch the fireworks display\n3. A fuse being lit, igniting a firework\n4. Fireworks exploding in the night sky, with bursts of color and light\n5. Sparks and embers falling to the ground after a firework has exploded",
"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: fireworks are being lit and exploding in a night sky<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query \"fireworks are being lit and exploding in a night sky\", it makes sense to extract events that are directly related to the visual and auditory experience of a fireworks display, as these events can be easily visualized in a video. The extracted events should focus on the fireworks themselves, the surrounding environment, and the potential reactions of people watching the display.\n\nEVENTS:\n1. Fireworks exploding into colorful patterns in the night sky\n2. Sparks and embers falling from the explosions\n3. People watching the fireworks display with reactions of amazement and delight\n4. Fireworks rockets shooting up into the air before exploding\n5. The night sky being illuminated by the bright colors of the fireworks",
"video_URL": "https://youtube.com/watch?v=video9779",
"video_description": null,
"video_id": "video9779"
}
| 32
|
[
"The image shows a night sky with fireworks exploding. There are three bright bursts of light and one trail of sparks moving upwards. A section of a boat with flags is visible in the lower right corner.",
"The image captures a night sky filled with fireworks, showing two bursts of light and one trail of sparks moving upwards. A section of a boat with colorful flags is visible in the lower right corner, continuing from the previous frame.",
"The image depicts a continuation of the fireworks display in the night sky, with another burst of light and a trail of sparks moving upwards. The boat with colorful flags is still visible in the lower right corner, maintaining the maritime setting. The fireworks add a celebratory atmosphere to the scene.",
"The current frame captures another burst of fireworks in the night sky, radiating brightly against the darkness. The boat with colorful flags remains in the lower right corner, reinforcing the maritime setting. The fireworks contribute to the festive and celebratory atmosphere, continuing the visual theme established in the previous frame.",
"The current frame captures another burst of fireworks in the night sky, radiating brightly against the darkness. The boat with colorful flags remains in the lower right corner, reinforcing the maritime setting. The fireworks contribute to the festive and celebratory atmosphere, continuing the visual theme established in the previous frame.",
"The current frame shows a fireworks display in the night sky, with bright, golden fireworks exploding. In the lower right corner, a part of a boat with colorful flags is visible, maintaining the maritime setting. The fireworks add to the festive and celebratory atmosphere, continuing the visual theme from the previous frame.",
"The current frame shows a fireworks display in the night sky, with bright, golden fireworks exploding. In the lower right corner, a part of a boat with colorful flags is visible, maintaining the maritime setting. The fireworks add to the festive and celebratory atmosphere, continuing the visual theme from the previous frame.",
"The current frame continues to show a fireworks display in the night sky, with bright, golden fireworks exploding, maintaining the festive and celebratory atmosphere. The maritime setting is consistent, with a part of a boat and colorful flags visible in the lower right corner, connecting with the previous frame's description.",
"The current frame continues to show a fireworks display in the night sky, with bright, golden fireworks exploding, maintaining the festive and celebratory atmosphere. The maritime setting is consistent, with a part of a boat and colorful flags visible in the lower right corner, connecting with the previous frame's description.",
"The current frame continues to show a fireworks display in the night sky, with bright, golden fireworks exploding, maintaining the festive and celebratory atmosphere. The maritime setting is consistent, with a part of a boat and colorful flags visible in the lower right corner, connecting with the previous frame's description.",
"The current frame depicts another phase of the fireworks display in the night sky, showcasing large, bright, and golden fireworks that have just burst, adding to the festive and celebratory atmosphere. The maritime setting is consistent, with a part of a boat and colorful flags visible in the lower right corner, maintaining continuity with the previous frames' descriptions.",
"The current frame captures the continuation of the fireworks display against the night sky, featuring bright golden fireworks that are expanding outward in a radiant burst. The maritime setting remains consistent, with part of a boat and colorful flags visible in the lower right corner, reinforcing the festive and celebratory atmosphere established in previous frames.",
"The current frame captures the continuation of the fireworks display against the night sky, featuring bright golden fireworks that are expanding outward in a radiant burst. The maritime setting remains consistent, with part of a boat and colorful flags visible in the lower right corner, reinforcing the festive and celebratory atmosphere established in previous frames.",
"The current frame captures a continuation of the fireworks display against the night sky, showcasing bright golden fireworks that are expanding outward in a radiant burst. The maritime setting remains consistent, with part of a boat and colorful flags visible in the lower right corner, reinforcing the festive and celebratory atmosphere established in previous frames. The fireworks appear to be at their peak, creating a mesmerizing spectacle above the water, enhancing the overall celebratory mood of the event.",
"The current frame continues to depict the fireworks display against the night sky, with the fireworks now appearing to be slightly larger and more dispersed, indicating they are in the later stages of their burst. The maritime setting is still prominent, with the boat and colorful flags remaining visible, maintaining the festive atmosphere. The fireworks are still creating a visually captivating scene, reinforcing the celebratory mood of the event.",
"The fireworks display continues to expand and illuminate the night sky, with the bursts now appearing even larger and more widespread, suggesting they are nearing the peak of their burst. The maritime setting remains evident, with the boat and colorful flags still in view, contributing to the festive and celebratory atmosphere. The scene continues to be visually captivating, reinforcing the ongoing celebration.",
"The fireworks display reaches its peak, with a vibrant and dense cluster of lights bursting in the night sky. The boat and colorful flags remain visible, enhancing the festive and celebratory atmosphere. The scene is visually captivating, reinforcing the ongoing celebration.",
"The fireworks display continues to captivate, with a large burst of golden and orange lights dominating the night sky. The boat and colorful flags are still visible, maintaining the festive atmosphere. The scene remains visually captivating, reinforcing the ongoing celebration.",
"The fireworks display continues, now featuring a vibrant burst of red and orange lights illuminating the night sky. The boat and colorful flags are still visible, reinforcing the festive atmosphere. The scene remains visually captivating, maintaining the sense of ongoing celebration.",
"The fireworks display persists, showcasing a large, golden-hued burst of lights against the dark sky. The boat with colorful flags remains in the foreground, contributing to the festive atmosphere. The scene continues to be visually engaging, sustaining the ongoing celebration.",
"The fireworks display continues, now featuring a vibrant orange burst of lights against the dark sky. The boat with colorful flags remains in the foreground, maintaining the festive atmosphere. The scene remains visually engaging, sustaining the ongoing celebration.",
"The fireworks display continues, now featuring a red burst of lights against the dark sky. The boat with colorful flags remains in the foreground, maintaining the festive atmosphere. The scene remains visually engaging, sustaining the ongoing celebration.",
"The fireworks display continues with a golden burst of lights illuminating the dark sky. The boat with colorful flags remains in the foreground, maintaining the festive atmosphere. The scene remains visually engaging, sustaining the ongoing celebration.",
"The fireworks display persists with another burst of lights in the dark sky. The boat with colorful flags stays in the foreground, continuing to enhance the festive atmosphere. The scene remains visually engaging, maintaining the ongoing celebration.",
"The fireworks continue to illuminate the dark sky, adding to the festive atmosphere. The boat with colorful flags remains in the foreground, maintaining the celebratory mood. The scene remains visually engaging, with the fireworks providing a dynamic display.",
"The fireworks continue their spectacular display, with a bright trail of light ascending into the night sky, illuminating the dark surroundings. The boat with colorful flags remains prominently in the foreground, contributing to the festive ambiance. The scene retains its visual dynamism, with the ongoing fireworks enhancing the celebratory mood.",
"A bright firework explodes in the sky, creating a radiant burst of light against the dark background. The trail from the firework is visible, leading up to the explosion. The boat with colorful flags is still in the foreground, maintaining the festive atmosphere. The scene continues to be vibrant and lively, with the firework display adding to the celebratory mood.",
"The scene continues with another bright firework exploding in the sky, emitting a radiant burst of light against the dark background. The trail from the firework is visible, leading up to the explosion. The boat with colorful flags remains in the foreground, maintaining the festive atmosphere. The scene remains vibrant and lively, with the ongoing firework display enhancing the celebratory mood.",
"The scene features a vibrant firework explosion in the sky, casting a bright light against the dark background. The trail from the firework is visible, leading up to the explosion. A boat adorned with colorful flags remains in the foreground, contributing to the festive atmosphere. The ongoing firework display continues to enhance the celebratory mood of the video.",
"A firework explodes in the sky, adding to the festive atmosphere. The boat with colorful flags remains visible in the foreground, enhancing the celebratory mood. The firework's trail is still noticeable, adding continuity to the ongoing display.",
"Another firework explodes in the sky, further intensifying the festive atmosphere. The boat with colorful flags remains in the foreground, continuing to enhance the celebratory mood. The firework's trail is still visible, adding continuity to the ongoing display.",
"A vibrant firework bursts in the night sky, creating a striking display of golden sparks that illuminate the surroundings. The boat with colorful flags remains prominently in the foreground, contributing to the festive and celebratory atmosphere. The firework's trail, still visible from the previous explosion, adds a sense of continuity and excitement to the ongoing display."
] |
video9779
|
A fireworks display takes place over a body of water, with a boat adorned with colorful flags visible in the foreground. The video depicts a continuous and vibrant display of fireworks, with bursts of light and trails of sparks illuminating the night sky. The maritime setting and the festive atmosphere created by the fireworks suggest a celebratory event, such as a national holiday, festival, or special occasion. The video showcases a dynamic and visually engaging display of fireworks, with a variety of colors and patterns, maintaining a consistent and captivating visual theme throughout. The presence of the boat with colorful flags reinforces the festive and celebratory mood, creating a sense of excitement and joy. Overall, the video captures a lively and entertaining fireworks display in a maritime setting, conveying a sense of celebration and festivity.
|
End of preview. Expand
in Data Studio
README.md exists but content is empty.
- Downloads last month
- 3
Size of downloaded dataset files:
5.34 MB
Size of the auto-converted Parquet files:
5.34 MB
Number of rows:
1,000