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
query
stringlengths 16
163
| prequel
listlengths 0
20
| sequel
listlengths 0
20
| during
listlengths 0
16
| metadata
dict | num_of_frames
int64 16
16
| frame_captions
listlengths 16
16
| video_id
stringlengths 9
9
| frame2video_caption
stringlengths 141
2.1k
|
|---|---|---|---|---|---|---|---|---|
a person is connecting something to system
|
[
"A person holding a cable or connector during connection to a system",
"A system or device with available ports or sockets for connection to a system",
"A person approaching the system with the cable or connector for connection to a system",
"A person inserting the cable or connector into the system during connection to a system",
"The system's screen or indicators showing connection status or setup prompts during a connection to a system"
] |
[
"a person plugging in a cable to a computer port for connection to a system",
"A technician connecting wires to a circuit board during connection to a system",
"Someone inserting a USB drive into a laptop to establish a connection to a system",
"An engineer linking a device to a network router during connection to a system",
"A worker attaching a sensor to a machinery control system during connection to the system"
] |
[
"A person holding a cable or connector for connection to a system",
"The person plugging the cable into a port or socket for connection to a system",
"the person turning on the device or system during connection to a system",
"Person configuring settings on the device or system during connection to a system",
"The person testing the connection to a system to ensure it is working properly"
] |
{
"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 establishing a connection, as these can be visualized in a video. The events should focus on the specific steps or actions a person would take to connect an object or device to a system.\n\nEVENTS:\n1. A person holding a cable or connector\n2. The person plugging the cable into a port or socket\n3. The person turning on the device or system\n4. The person configuring settings on the device or system\n5. The person testing the connection to ensure it is working properly",
"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: It makes sense to extract events that are concrete and visual, such as physical actions or changes in the environment, that could lead to a person connecting something to a system. These events should be specific and relevant to the query, allowing for visualization in a video.\n\nEVENTS:\n1. A person holding a cable or connector\n2. A system or device with available ports or sockets\n3. A person approaching the system with the cable or connector\n4. A person inserting the cable or connector into the system\n5. The system's screen or indicators showing connection status or setup prompts",
"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, considering the physical and visual aspects of the process. The events should be specific and plausible to be visualized in a video, taking into account common scenarios where connections to systems are made.\n\nEVENTS:\n1. A person plugging in a cable to a computer port\n2. A technician connecting wires to a circuit board\n3. Someone inserting a USB drive into a laptop\n4. An engineer linking a device to a network router\n5. A worker attaching a sensor to a machinery control system",
"video_URL": "https://youtube.com/watch?v=video9770",
"video_description": null,
"video_id": "video9770"
}
| 16
|
[
"A person is using a vacuum cleaner on a large tower computer case that is partially open. The case has the word \"hp\" on the side.",
"In the current frame, the person continues to use the vacuum cleaner on the large tower computer case. The case remains partially open, with the \"hp\" logo still visible.",
"In the current frame, the person is seen interacting with a large tower computer case. The case remains partially open, exposing some internal components. The person appears to be either adjusting or handling something inside the computer case, continuing the activity related to cleaning or maintaining the computer. The \"hp\" logo is still visible on the case.",
"In this frame, the person is actively working on the internal components of the large tower computer case. The case remains open, and the person's hand is reaching inside, likely adjusting or handling parts within the computer. The focus continues to be on the maintenance or repair activity, with the \"hp\" logo still visible on the case, indicating the brand of the computer.",
"The person is still engaged in working on the internal components of the large tower computer case, which remains open. Their hand is now positioned differently, suggesting further adjustments or handling of parts within the computer. The \"hp\" logo is still visible on the case, indicating the brand of the computer, and the focus remains on the ongoing maintenance or repair activity.",
"The person is continuing to work on the internal components of the large tower computer case, which remains open. The person's hand is positioned differently, suggesting ongoing adjustments or handling of parts within the computer. The \"hp\" logo is still visible on the case, indicating the brand of the computer, and the focus remains on the maintenance or repair activity.",
"The person continues working on the internal components of the large tower computer case, which remains open. The individual's hand is now positioned differently, indicating further adjustments or handling of parts within the computer. The \"hp\" logo is still visible, reinforcing the brand of the computer, and the focus remains on the maintenance or repair activity.",
"The person continues working on the internal components of the large tower computer case, which remains open. The individual's hand is positioned differently, indicating further adjustments or handling of parts within the computer. The \"hp\" logo is still visible, reinforcing the brand of the computer.",
"The person is adjusting the internal components of the open tower computer case. The individual's arm is extended, indicating they are continuing to handle and adjust parts inside the computer. The \"hp\" logo is still visible on the computer case, reinforcing the brand of the computer.",
"The person is continuing to work on the open tower computer case. They are reaching into the case, likely adjusting or installing a component. The \"hp\" logo remains visible, indicating the ongoing work is still with the same computer brand.",
"The person is still working on the open tower computer case. They are using a tool to secure or adjust a component inside the case. The \"hp\" logo is still visible, indicating the continued work on the same computer.",
"The person continues to work on the open tower computer case, using a tool to secure or adjust a component inside the case. The \"hp\" logo is still visible, indicating ongoing work on the same computer.",
"The person is still working on the open tower computer case, but their arm is now extended outward, possibly moving or adjusting a component. The \"hp\" logo remains visible, suggesting continuous work on the computer.",
"The person is still working on the open tower computer case, with their arm extended outward, indicating they are continuing to adjust or move a component. The \"hp\" logo remains visible, suggesting ongoing work on the computer.",
"The person continues working on the open computer case, with their arm still extended, indicating ongoing adjustments or component movement.",
"The person's arm is extended, continuing to work on the open computer case, suggesting ongoing adjustments or component movement."
] |
video9770
|
A person is performing maintenance or repair on an HP tower computer. The process involves vacuuming the case and then manually adjusting and handling internal components. The person uses tools to secure or adjust parts inside the case, indicating a detailed and potentially complex repair or upgrade process. Throughout the activity, the computer case remains open, and the person's focus is on the internal components, suggesting a thorough and hands-on approach to the task. The video depicts a single, uninterrupted sequence of the person working on the computer, with no changes in setting or participants.
|
a little girl does gymnastics
|
[
"little girl mounts a balance beam during a gymnastics performance",
"She performs a cartwheel on a mat during a gymnastics performance",
"girl hangs from uneven bars during a gymnastics performance",
"She executes a flip on a springboard during a gymnastics performance",
"The little girl strikes a pose after a gymnastics performance routine"
] |
[
"Cartwheeling across a mat during a gymnastics performance",
"Balancing techniques on a balance beam during a gymnastics performance",
"Performing a backflip on a springboard during a gymnastics performance",
"Twirling on the floor with a ribbon during a gymnastics performance",
"Landing a dismount from a mini trampoline in a gymnastics performance"
] |
[
"A little girl running towards a springboard during a gymnastics performance",
"girl jumping over mini hurdle during gymnastics performance",
"girl performing a cartwheel on a mat during a gymnastics performance",
"girl balancing on a balance beam during a gymnastics performance",
"girl landing 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 decompose the query \"a little girl does gymnastics\" into simple events, it makes sense to extract concrete actions that are visually representative of gymnastics and can be reasonably captioned in a video frame. This will involve identifying common gymnastics movements that a little girl might perform, considering typical environments and equipment used in the sport.\n\nEVENTS:\n1. A little girl running towards a springboard\n2. The girl jumping over a mini hurdle\n3. The girl performing a cartwheel on a mat\n4. The girl balancing on a balance beam\n5. The girl landing 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 gymnastics movements and routines that a young girl might perform, as these would be visually captivating and concrete enough to be depicted in a video. The extracted events should be specific and relevant to the context of a child participating in gymnastics.\n\nEVENTS:\n1. The little girl mounts a balance beam\n2. She performs a cartwheel on a mat\n3. The girl hangs from uneven bars\n4. She executes a flip on a springboard\n5. The little girl strikes a pose after a routine",
"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: It makes sense to extract events that are specific and concrete actions related to gymnastics that a little girl could be performing, as these would be easily visualized in a video. The events should be common gymnastics movements or routines that are suitable for a young girl.\n\nEVENTS:\n1. Cartwheeling across a mat\n2. Balancing on a balance beam\n3. Performing a backflip on a springboard\n4. Twirling on the floor with a ribbon\n5. Landing a dismount from a mini trampoline",
"video_URL": "https://youtube.com/watch?v=video9771",
"video_description": null,
"video_id": "video9771"
}
| 16
|
[
"A young gymnast is performing a routine on a gymnastics mat. The gymnast is in a dynamic pose, with one arm extended upwards and the other hand touching her hair, showcasing flexibility and balance. She is wearing a sleeveless leotard. The background shows a gym setting with a wall featuring horizontal stripes.",
"The young gymnast is continuing her routine on the gymnastics mat. She is standing with her hands on her hips, possibly preparing for the next movement. The background remains consistent with the gym setting, featuring horizontal stripes on the wall.",
"The young gymnast is performing a routine on the gymnastics mat. She is standing with her hands on her hips, possibly preparing for the next movement. The background remains consistent with the gym setting, featuring horizontal stripes on the wall.",
"The young gymnast appears to be in motion, possibly executing a jump or a leap as part of her routine on the gymnastics mat. Her hair is flowing, indicating movement, and she seems focused on her performance. The gym setting with horizontal stripes on the wall remains consistent in the background.",
"The young gymnast is captured in mid-air, likely performing a flip or twist during her routine on the gymnastics mat. Her hair is still flowing, suggesting she is in the midst of a dynamic movement. She appears focused and determined, maintaining her form. The consistent gym setting with horizontal stripes on the wall remains in the background, providing continuity.",
"The young gymnast is now on the ground, having completed her flip or twist. She is seen landing on the blue gymnastics mat, demonstrating control and precision. Her hair has settled, indicating the completion of her dynamic movement. The gym setting with horizontal stripes on the wall remains consistent, providing continuity with the previous frame. The focus is on her landing technique and the aftermath of her performance.",
"The young gymnast is positioned on a blue gymnastics mat, with her arms extended and legs bent, appearing to have just completed a maneuver. She maintains a poised stance, indicating the continuation of her routine. The gym setting with horizontal stripes on the wall remains unchanged, providing continuity. The focus is on her stable posture and the precision of her technique.",
"The young gymnast stands on a blue gymnastics mat, arms raised above her head and legs slightly apart, continuing her routine. The gym setting, marked by horizontal stripes on the wall, remains consistent. Her poised stance suggests she is either transitioning between maneuvers or preparing for the next part of her routine. The gymnastics equipment in the background indicates the ongoing practice session.",
"The young gymnast is captured in mid-air, having leapt off the blue gymnastics mat, arms still raised above her head in a graceful arc. The gym setting remains unchanged, with its distinctive horizontal stripes on the wall. This moment likely represents a dynamic transition within her routine, demonstrating her skill and agility as she moves towards the next phase of her performance.",
"The young gymnast is standing confidently on the blue gymnastics mat with her arms raised above her head, completing a part of her routine. The gym setting remains consistent, featuring the same horizontal stripes on the wall. This frame captures her poised and ready for her next move, showcasing her precision and control.",
"The young gymnast maintains her confident stance on the blue gymnastics mat, with her arms still raised above her head. She appears poised and ready for her next move, demonstrating her precision and control in the consistent gym setting with the same horizontal stripes on the wall.",
"The young gymnast stands on the blue gymnastics mat with her arms raised confidently above her head, maintaining her poised and controlled stance. The consistent gym setting with horizontal stripes on the wall remains unchanged, indicating a continuous performance.",
"The young gymnast stands on the blue gymnastics mat with her arms at her sides, appearing relaxed and poised. The gym setting with horizontal stripes on the wall remains unchanged, indicating a continuous performance.",
"The young gymnast continues to stand on the blue gymnastics mat, maintaining her relaxed and poised stance. The gym setting with the horizontal stripes on the wall remains consistent, indicating continuity in her performance.",
"The young gymnast remains on the blue gymnastics mat, standing in a poised and relaxed stance. The gym setting with the horizontal stripes on the wall continues to provide a consistent backdrop, emphasizing the ongoing nature of her performance.",
"The young gymnast is actively running across the blue gymnastics mat, likely preparing for a subsequent routine or movement. The gym setting with the horizontal stripes on the wall remains consistent, highlighting her agility and readiness for the next part of her performance."
] |
video9771
|
A young gymnast performs a dynamic routine on a blue gymnastics mat in a gym setting with horizontal stripes on the wall. The routine involves various movements, including poses, jumps, leaps, flips, and twists, showcasing her flexibility, balance, and control. Throughout the performance, the gymnast maintains focus and determination, demonstrating precision and skill in her technique. The routine includes moments of dynamic motion, such as running and jumping, as well as poised stances, highlighting her agility and readiness for each subsequent movement. The consistent gym setting provides a backdrop for her performance, which appears to be a practice session or a competition routine. The gymnast's confidence and control are evident throughout, as she transitions seamlessly between different parts of her routine, ultimately concluding in a relaxed and poised stance.
|
a woman creating a fondant baby and flower
|
[
"Kneading fondant to soften it for creating a fondant baby",
"Kneading fondant to soften it for creating a flower",
"Shaping fondant into a baby figure for creating a fondant baby",
"Shaping fondant into a baby figure",
"Coloring fondant for flower petals when creating a fondant baby",
"Coloring fondant for flower petals when creating a flower",
"Creating intricate details on the fondant baby's face while creating a fondant baby",
"Creating intricate details on the fondant baby's face including adding floral elements",
"Assembling the fondant flower petals into a complete flower for creating a fondant baby",
"Assembling the fondant flower petals into a complete flower while 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",
"Creating intricate details on the baby's face when creating a fondant baby",
"Creating intricate details on a baby's face while drawing or painting",
"Molding fondant into flower petals for creating a fondant baby",
"Molding fondant into flower petals for creating a flower",
"Assembling the flower and attaching it to the baby figurine when creating a fondant baby",
"Assembling and attaching a handmade flower to a baby figurine while creating the flower decoration"
] |
[
"A woman kneading fondant on a work surface while creating a fondant baby",
"A woman kneading fondant on a work surface while creating a flower",
"The woman shaping fondant into a baby figure while creating a fondant baby",
"The woman shaping fondant into a baby figure while creating a flower",
"The woman creating petals for the flower out of fondant while making a fondant baby",
"Woman creating petals for a flower out of fondant while creating a flower",
"The woman assembling and decorating the fondant flower while creating a fondant baby",
"The woman assembling and decorating the fondant flower while creating a flower",
"Woman adding final details to the fondant baby while creating a fondant baby",
"The woman adding final details to the fondant baby 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 extract events from the query \"a woman creating a fondant baby and flower\", it makes sense to break down the process of creating fondant decorations into individual, visualizable steps, considering the typical actions involved in working with fondant. This will involve identifying specific actions that can be reasonably captured in a video frame, such as molding, shaping, and decorating.\n\nEVENTS:\n1. A woman kneading fondant on a work surface\n2. The woman shaping fondant into a baby figure\n3. The woman creating petals for the flower out of fondant\n4. The woman assembling and decorating the fondant flower\n5. The woman adding final details to the fondant baby",
"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 steps involved in the process of creating fondant decorations, as these would be concrete and visual events that could be captured in a video. The events should be specific to the task of shaping and decorating fondant to create a baby and flower, using common techniques and tools associated with fondant decoration.\n\nEVENTS:\n1. Kneading fondant to soften it\n2. Shaping fondant into a baby figure\n3. Coloring fondant for the flower petals\n4. Creating intricate details on the fondant baby's face\n5. Assembling the fondant flower petals into a complete flower",
"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 that are specific steps or moments in the process of creating a fondant baby and flower, as these would be concrete and visual elements that could be captured in a video. The events should be related to the creative process, such as shaping, molding, or decorating, and should be relevant to the subject matter of working with fondant.\n\nEVENTS:\n1. Kneading the fondant to soften it\n2. Shaping the fondant into a baby figure\n3. Creating intricate details on the baby's face\n4. Molding fondant into flower petals\n5. Assembling the flower and attaching it to the baby figurine",
"video_URL": "https://youtube.com/watch?v=video7020",
"video_description": null,
"video_id": "video7020"
}
| 16
|
[
"A person is making a craft or decoration using green and pink materials.",
"The person is shaping a green material around a pink object, which appears to be a small figurine, as part of their craft project.",
"The person continues to work on their craft project, carefully molding the green material around the pink figurine to ensure a smooth and even cover.",
"The person continues to work on their craft project, using their hands to shape the green material over the pink figurine, ensuring it is smooth and even.",
"The person is carefully placing a green leaf-shaped material onto a pink figurine, ensuring it adheres smoothly and evenly to the figure's back.",
"The person continues to position the green leaf-shaped material on the pink figurine, making sure it attaches securely and appears neat.",
"The person adjusts the green leaf-shaped material on the pink figurine, ensuring it is properly aligned and securely attached to create a neat appearance.",
"The person is carefully placing a green leaf-shaped material on top of the pink figurine, ensuring it is properly aligned and securely attached to create a neat appearance.",
"The person is applying pressure on a small rectangular object placed between their hands, likely to flatten or shape it further, ensuring it is properly aligned on the grid-patterned surface.",
"The person is using a rolling pin to flatten a small rectangular object placed on the grid-patterned surface, ensuring it is evenly rolled out.",
"The person's hands are pressing down on a white rectangular object with a rolling pin, continuing to flatten it on the grid-patterned surface. A yellow object is partially visible in the background.",
"The person's hands are using a white flower-shaped cutter to press into a yellow piece of dough on the grid-patterned surface. The white rolling pin is placed to the side.",
"The person's hands have removed the white flower-shaped cutter from the yellow dough, revealing the cut-out flower shape on the grid-patterned surface. The white rolling pin remains to the side.",
"The person is using purple scissors to trim the edges of the yellow flower-shaped dough piece on the grid-patterned surface.",
"The person is continuing to use purple scissors to trim the edges of the yellow flower-shaped dough piece on the grid-patterned surface.",
"The person is using purple scissors to further shape the edges of the yellow flower-shaped dough piece on the grid-patterned surface."
] |
video7020
|
A person is engaged in a crafting activity, initially working with green and pink materials to decorate a small figurine. They carefully shape and mold the green material around the pink figurine, adding leaf-shaped details to create a smooth and even appearance. The person then shifts their attention to working with dough, using a rolling pin to flatten a rectangular object on a grid-patterned surface. They proceed to cut out a flower shape from yellow dough using a white flower-shaped cutter and then trim the edges of the cut-out flower using purple scissors, refining its shape. Throughout the video, the person is focused on precision and detail, working diligently to create their craft projects.
|
a boy plays grand theft auto 5
|
[
"A boy sitting in front of a TV or computer with a controller in his hand playing a video game",
"The boy playing a video game and navigating the menu to start a new game or load a saved file",
"The boy's character in the game walking or driving through the virtual city of Los Santos while playing a video game",
"The boy engaging in a shootout or car chase while playing a video game",
"The boy pausing the game or adjusting the settings on his console or computer while playing a video game"
] |
[
"The boy holding a controller and focusing on the screen while playing a video game",
"The boy's character in a video game driving a car and crashing into other vehicles",
"The boy's character engaging in a shootout with non-player characters while playing a video game",
"The boy playing a video game and navigating the menu to select a mission or customize his character",
"boy reacting emotionally to an intense or surprising moment 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",
"Scenes from Grand Theft Auto 5 displayed on the screen while playing the video game, such as driving cars or interacting with characters",
"The boy's hands moving the controller to control gameplay while playing a video game",
"The boy reacting to playing a video game, such as looking excited or concentrated"
] |
{
"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 focus on the actions and scenes that are likely to occur while someone is playing the game, as well as the environment in which the game is being played. This will involve considering common aspects of the game and the setting in which a boy would typically play it.\n\nEVENTS:\n1. A boy sitting in front of a TV or computer screen\n2. The boy holding a gaming controller\n3. Scenes from Grand Theft Auto 5 displayed on the screen, such as driving cars or interacting with characters\n4. The boy's hands moving the controller to control gameplay\n5. The boy reacting to the game, such as looking excited or concentrated",
"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 act of playing a video game, specifically Grand Theft Auto 5, as these events would likely be visualized in a video of someone playing the game. The extracted events should focus on the boy's interactions with the game and the game's environment.\n\nEVENTS:\n1. A boy sitting in front of a TV or computer with a controller in his hand\n2. The boy navigating the game's menu to start a new game or load a saved file\n3. The boy's character in the game walking or driving through the virtual city of Los Santos\n4. The boy engaging in a shootout or car chase within the game\n5. The boy pausing the game or adjusting the settings on his console or computer",
"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: Given the query \"a boy plays Grand Theft Auto 5\", it makes sense to extract events that are directly related to the gameplay or the environment in which the boy is playing, as these would be the most visual and relevant aspects of a video on this topic. The events should reflect common scenarios or actions that occur while playing the game or interacting with the gaming setup.\n\nEVENTS:\n1. The boy holding a controller and focusing on the screen\n2. The boy's character in the game driving a car and crashing into other vehicles\n3. The boy's character engaging in a shootout with non-player characters\n4. The boy navigating the game's menu to select a mission or customize his character\n5. The boy reacting emotionally to a intense or surprising moment in the game",
"video_URL": "https://youtube.com/watch?v=video9773",
"video_description": null,
"video_id": "video9773"
}
| 16
|
[
"Several motorcyclists are riding on a wet street at night, with their headlights on. They appear to be moving at a moderate speed.",
"The current frame displays the date \"MARCH 10\" against a black background, likely indicating a transition or a title card within the video. There are no visible motorcyclists or street scenes, suggesting a pause or a shift in the narrative, possibly setting the context for the events that follow or referencing a specific date important to the video's storyline.",
"The current frame shows a green sports car driving on a curvy, rural road. The car is in motion, following the road's bends as it travels through a hilly landscape. The surrounding area is lush with greenery, including trees and bushes. The road is marked with a yellow center line, indicating a two-way traffic route. There are no other visible vehicles or people, focusing the scene on the car's journey. The bottom left corner of the image contains a mini-map, suggesting this is a gameplay screenshot from a racing video game.",
"The green sports car continues its journey on the curvy, rural road, maintaining its position on the road's center line. The hilly landscape with greenery remains consistent, with no other vehicles or people in sight. The mini-map in the bottom left corner is still visible, reinforcing the gameplay context. The car approaches a checkpoint marked by a blue banner, indicating progression in the race.",
"The green sports car is driving towards a large ramp, indicating an upcoming stunt or jump. The car remains on the center line of the road, and the hilly landscape is still visible. The mini-map in the bottom left corner is present, suggesting this is a race scenario. The car's speed is displayed on the right, showing 65.79, indicating a steady pace as it approaches the ramp.",
"The green sports car is approaching the top of the ramp. The car remains centered on the ramp, and the hilly landscape is still visible in the background. The mini-map in the bottom left corner remains present, suggesting the ongoing race scenario. The car's speed is displayed on the right, showing 92.2, indicating an acceleration as it reaches the peak of the ramp.",
"The green sports car has reached the peak of the ramp and is now in mid-air, soaring above the hilly landscape. The car's acceleration continues, with its speed displayed as 96.2. The mini-map remains visible, indicating the car is still part of the race scenario. The background shows a clear view of the distant mountains and some buildings below, suggesting the car is at a significant height.",
"The green sports car is still airborne, having just launched off the ramp. Its speed has increased to 108.5, as shown on the screen. The car continues to soar over the hilly terrain with the mini-map still visible, indicating it is still in the race scenario. The background remains consistent with distant mountains and buildings visible below, suggesting the car is at a significant height.",
"The green sports car continues to fly through the air with its speed increasing to 130.5, as shown on the screen. The car maintains its trajectory over the hilly landscape, with the mini-map still visible, suggesting it remains within the race scenario. The background still features distant mountains and buildings below, indicating the car is at a significant height.",
"The green sports car is airborne, maintaining its flight over a hilly landscape with a speed of 127.7. The car is slightly higher in the air than before, and the mini-map is still visible, indicating the ongoing race scenario. The background shows distant mountains and buildings, emphasizing the car's elevation.",
"The green sports car continues to fly through the air, now over a hilly landscape with a cityscape visible in the background. The car remains airborne, with a speed of 202. The mini-map and HUD elements are visible, indicating the ongoing race scenario.",
"The green sports car maintains its flight over a city, with structures and roads becoming more visible below. The car's speed is now 212, indicating it is still airborne and likely participating in a high-speed race or stunt.",
"The green sports car continues to fly through the air, now approaching a city with buildings and roads clearly visible below. The car's speed is 212, suggesting it is still airborne and participating in a high-speed race or stunt.",
"The green sports car is still airborne, now flying over a road lined with trees and buildings. The car's speed remains high at 202, indicating it is still in the midst of a daring aerial stunt or race, maintaining a high level of speed and excitement.",
"The green sports car is now flying over a road with a clear path ahead, lined with grass and trees. The car's speed is still high at 218, indicating it continues the daring aerial stunt, maintaining speed and excitement.",
"The green sports car is now back on the road, traveling at a speed of 218, indicating a continuation from its aerial stunt. The car maintains its momentum, with a clear path ahead on the road, flanked by grass and trees."
] |
video9773
|
The video depicts a racing scenario, primarily focusing on a green sports car navigating through a curvy, rural road in a hilly landscape. The car participates in a high-speed race, complete with checkpoints and ramps for performing aerial stunts. At one point, the car launches off a ramp, soaring over the hilly terrain and even a cityscape, reaching high speeds during its airborne sequence. The car eventually lands back on the road, continuing its high-speed journey. The video also includes a brief scene of motorcyclists riding at night and a title card displaying the date "MARCH 10," which may set the context or serve as a narrative pause. The majority of the video, however, centers around the green sports car's racing and stunt performance, captured in what appears to be a gameplay scenario from a racing video game.
|
a man is giving a review on a vehicle
|
[
"The man walking around the vehicle to point out its features during a review of a vehicle",
"The man sitting in the driver's seat and adjusting the controls during a review of a vehicle",
"The man starting the engine and listening to its sound during a review of a vehicle",
"The man driving the vehicle to test its performance during a review of a vehicle",
"The man standing in front of the vehicle, speaking to the camera about its pros and cons 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 and adjusting the controls during a review of a vehicle",
"Review of a vehicle's trunk space and features",
"The man test-driving the vehicle on the road during a review of a vehicle",
"The man speaking directly to the camera to share his thoughts on the vehicle during a review"
] |
[
"A man standing next to a vehicle, pointing out its features during a review of a vehicle",
"The man sitting in the driver's seat, testing the vehicle's controls during a review of a vehicle",
"The man walking around the vehicle, inspecting its exterior during a review of a vehicle",
"The man driving the vehicle, testing its performance during a review of the vehicle",
"The man speaking directly to the camera, sharing his thoughts on 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 directly related to the act of reviewing a vehicle, such as the man interacting with the vehicle or expressing his opinions. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. A man standing next to a vehicle, pointing out its features\n2. The man sitting in the driver's seat, testing the vehicle's controls\n3. The man walking around the vehicle, inspecting its exterior\n4. The man driving the vehicle, testing its performance\n5. The man speaking directly to the camera, sharing his thoughts on 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 the typical actions and scenes that would be involved in a video review of a vehicle, such as the reviewer interacting with the vehicle and sharing their opinions. The extracted events should be concrete and visual, allowing them to be easily captioned and depicted in a video frame.\n\nEVENTS:\n1. The man walking around the vehicle to point out its features\n2. The man sitting in the driver's seat and adjusting the controls\n3. The man starting the engine and listening to its sound\n4. The man driving the vehicle to test its performance\n5. The man standing in front of the vehicle, speaking to the camera about its pros and cons",
"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 act of reviewing a vehicle, such as the man interacting with the vehicle or expressing his opinion. These events should be concrete and visual, allowing them to be easily captioned and depicted in a video.\n\nEVENTS:\n1. The man walking around the vehicle to inspect it\n2. The man sitting in the driver's seat and adjusting the controls\n3. The man checking the vehicle's trunk space and features\n4. The man test-driving the vehicle on the road\n5. The man speaking directly to the camera to share his thoughts on the vehicle",
"video_URL": "https://youtube.com/watch?v=video7026",
"video_description": null,
"video_id": "video7026"
}
| 16
|
[
"The current frame depicts a vehicle driving through a rocky, natural landscape with large boulders and sparse vegetation. The car's hood is visible in the foreground, suggesting that the perspective is from inside the vehicle.",
"The vehicle continues to drive through the rocky, natural landscape, maintaining its steady course among the large boulders and sparse vegetation. The car's hood remains prominently visible in the foreground, indicating that the perspective is still from inside the vehicle.",
"The vehicle is driving at a slow speed of 1.2 mph, with the dashboard displaying \"Descent available\" and a small bird icon. The car is in park (P) mode, suggesting preparation for a controlled descent or maneuver.",
"The vehicle is still in park (P) mode, with the dashboard now displaying \"Descent available\" and a slightly different icon resembling a mountain, indicating that a controlled descent is possible. The speed is not visible, but the overall setting suggests the car is preparing for a descent or maneuver on a sloped terrain.",
"The vehicle remains in park (P) mode, with the dashboard showing \"Speed available,\" indicating that it is ready to move or is currently in motion at a low speed of 1.2 MPH. The display also includes a baby icon, suggesting a child safety feature is active. The car appears to be preparing for or in the initial stages of moving, likely related to the descent mentioned in the previous frame.",
"The vehicle remains in park (P) mode, with the dashboard still showing \"Speed available\" and the low speed of 1.2 MPH. The baby icon remains visible, indicating the child safety feature is active. The car appears to be in the initial stages of moving or preparing to move, likely continuing the descent mentioned in the previous frames.",
"The vehicle is still in park (P) mode, with the dashboard displaying \"Speed available.\" The speedometer shows 0 MPH, indicating the vehicle is stationary. The child safety feature remains active, as indicated by the baby icon. The car continues to prepare to move, possibly still in the initial stages of the descent.",
"The vehicle remains in park (P) mode, as indicated by the \"P\" on the dashboard. The text \"Speed available\" is still displayed, showing that the vehicle is ready to move. The speedometer continues to show 0 MPH, indicating the vehicle is still stationary. There is no visible indication of the child safety feature in this frame. The car seems to be in a stationary position, possibly still preparing for movement.",
"The man in the driver's seat is gesturing with his hands, possibly explaining or demonstrating something related to the vehicle. The car remains stationary, with the gear shift in park (P) mode, and the speedometer still shows 0 MPH.",
"The man in the driver's seat continues to gesture with his hands, further elaborating on his explanation or demonstration related to the vehicle. The car remains stationary, with the gear shift in park (P) mode, and the speedometer still shows 0 MPH.",
"The man in the driver's seat is engaged in conversation, gesturing with his left hand while his right hand remains on the steering wheel. The car is still stationary with the gear shift in park (P) mode, and the speedometer shows 0 MPH.",
"The man in the driver's seat continues his conversation, now gesturing with his right hand while his left hand is on the steering wheel. The car remains stationary with the gear shift in park (P) mode, and the speedometer still shows 0 MPH.",
"The man in the driver's seat is still engaged in his conversation, continuing to gesture with his right hand while keeping his left hand on the steering wheel. The car remains stationary with the gear shift in park (P) mode, and the speedometer still displays 0 MPH.",
"The man in the driver's seat continues his conversation, with his right hand gesturing and his left hand resting on the steering wheel. The car remains stationary, with the gear shift still in park (P) mode, and the speedometer displays 0 MPH.",
"The man in the driver's seat appears to be in the process of driving, as his right hand is now on the steering wheel and his left hand is on the gear shift. The car is moving, indicated by the speedometer showing a speed greater than 0 MPH. The car's interior and the man's focused expression suggest he is concentrating on driving.",
"The man in the driver's seat is still engaged in driving, maintaining his grip on the steering wheel with his right hand and his left hand on the gear shift. The interior of the car remains consistent with the previous frame, and his focused expression continues to reflect his concentration on driving."
] |
video7026
|
A vehicle, driven by a man, navigates through a rocky, natural landscape with large boulders and sparse vegetation. The driver prepares for a controlled descent, as indicated by the dashboard displays, and the vehicle momentarily remains stationary in park mode. During this time, the driver engages in conversation, gesturing with his hands while explaining or demonstrating something related to the vehicle. After the conversation, the driver proceeds to drive the vehicle, focusing on the road as the speedometer shows the car is moving. The video depicts the driver's actions and the vehicle's movement through the natural terrain, highlighting the preparation and execution of a controlled descent.
|
a man speaks to children in a classroom
|
[
"A man stands at the front of the classroom writing on a blackboard while speaking to the children",
"Children sit at their desks looking up at the man as he speaks to them",
"A man speaking to children while gesturing",
"A man speaking to children as they raise their hands to ask questions",
"The man walks around the classroom to assist individual students while speaking to them"
] |
[
"A man writes on a blackboard while speaking to children",
"Children take notes at their desks while a man speaks to them",
"A man gestures as he explains a concept to a group of children while speaking to them",
"Students ask questions and engage in discussion when a man speaks to them",
"A man speaking to children hands out worksheets or assignments to them"
] |
[
"A man stands at the front of the classroom writing on the blackboard while speaking to the children",
"Children sit at their desks listening to the man speak",
"A man speaking to children as he walks around the classroom to assist individual students",
"Students raise their hands to ask the man questions during a speech to children",
"A man uses visual aids such as a projector or diagrams to explain a concept to children during a presentation or lecture"
] |
{
"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 aspects of such a scene. The events should be specific and concrete enough to be captured in a video, focusing on the actions and activities that occur in a classroom.\n\nEVENTS:\n1. A man stands at the front of the classroom writing on the blackboard\n2. Children sit at their desks listening to the man speak\n3. The man walks around the classroom to assist individual students\n4. Students raise their hands to ask the man questions\n5. The man uses visual aids such as a projector or diagrams to explain a concept",
"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 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 be specific and relevant to the context of a man speaking to children in a classroom, avoiding generic or unrelated events.\n\nEVENTS:\n1. A man stands at the front of the classroom writing on a blackboard\n2. Children sit at their desks looking up at the man\n3. The man gestures as he speaks to the children\n4. Children raise their hands to ask questions\n5. The man walks around the classroom to assist individual students",
"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 of a classroom setting and involve interaction between a teacher and students, as the query suggests a educational or instructional context. 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 man writes on a blackboard\n2. Children take notes at their desks\n3. The man gestures as he explains a concept\n4. Students ask questions and engage in discussion\n5. The man hands out worksheets or assignments to the children",
"video_URL": "https://youtube.com/watch?v=video9775",
"video_description": null,
"video_id": "video9775"
}
| 16
|
[
"The current frame shows a group of children in a classroom setting, likely engaged in a learning or storytelling activity. They are seated and appear to be listening attentively, with some showing expressions of interest. The children are wearing name tags, indicating a structured educational or camp environment. There is educational material visible on the walls, such as charts and posters.",
"The current frame shows the same group of children in a classroom setting, likely continuing their learning or storytelling activity. They are still seated and appear to be actively listening or participating. The children are wearing name tags, indicating a structured educational or camp environment. The educational material on the walls, such as charts and posters, remains visible. The children seem more engaged, with some smiling or making eye contact, suggesting they are responding positively to the activity.",
"The image depicts a man sitting in a classroom environment, which appears to be part of an educational setting. He is holding a clipboard or a notepad, suggesting he might be conducting an observation or taking notes. The classroom is equipped with colorful storage bins and educational posters, reinforcing the learning environment. The overall context suggests he could be a teacher, educational administrator, or observer, engaged in an educational activity or assessment within the classroom.",
"The man continues to sit in the classroom, still holding his clipboard or notepad. He appears to be engaged in an ongoing activity, possibly taking notes or observing, as he remains focused on something or someone off-camera. The educational setting remains consistent, with colorful storage bins and posters visible in the background, indicating the continuity of the classroom environment.",
"The man is still seated in the classroom, maintaining his focus on something off-camera. The children around him appear engaged in a conversation, with some looking towards the man while others interact with each other. The classroom environment is consistent, with educational materials and colorful storage bins visible in the background.",
"The man remains seated in the classroom, continuing to focus on something off-camera. The children around him are still engaged in conversation, with some looking towards the man and others interacting with each other. The classroom environment remains consistent, featuring educational materials and colorful storage bins in the background.",
"The man remains seated in the classroom, continuing to focus on something off-camera. The children around him are still engaged in conversation, with some looking towards the man and others interacting with each other. The classroom environment remains consistent, featuring educational materials and colorful storage bins in the background.",
"The man is still seated in the classroom, appearing to be in conversation or giving instructions. The children are engaged, some facing him attentively. The classroom environment remains unchanged, with educational materials and storage bins visible in the background.",
"The boy is looking to his left, possibly responding to the man or participating in the conversation. The classroom environment remains consistent, with educational materials visible on the wall.",
"The boy appears to be speaking or listening attentively, with a focused expression on his face. The classroom setting is consistent with educational materials visible on the wall.",
"The boy is engaged in conversation, maintaining an attentive expression. The classroom environment, adorned with educational posters, suggests an ongoing discussion or learning activity.",
"The boy is still engaged in conversation, maintaining an attentive expression. The classroom environment, adorned with educational posters, suggests an ongoing discussion or learning activity.",
"The boy continues the conversation, still looking attentive and engaged in the ongoing discussion or learning activity in the classroom.",
"The boy remains engaged in the classroom activity, looking attentive. He is wearing a name tag, suggesting an interactive or educational setting.",
"The boy continues to participate in the classroom activity, maintaining his attentive expression. The colorful wall decorations in the background indicate an educational environment, reinforcing the setting of learning or discussion.",
"The man continues to participate in the classroom activity, maintaining his attentive expression. The colorful wall decorations in the background indicate an educational environment, reinforcing the setting of learning or discussion."
] |
video9775
|
A group of children, wearing name tags, are engaged in a learning or storytelling activity in a classroom setting. They appear to be listening attentively and participating in the discussion. A man, likely a teacher or educational administrator, is present in the classroom, observing and taking notes. He engages in conversation with the children, providing instructions or guidance. The children respond positively, showing interest and attentiveness. The classroom environment is filled with educational materials, posters, and colorful storage bins, reinforcing the learning setting. The video depicts an interactive and engaging educational activity, where the children are encouraged to participate and respond to the discussion, under the guidance of the man.
|
one micky mouse is talking to other
|
[
"Mickey Mouse standing in front of a group of characters during a conversation",
"Mickey Mouse shaking hands with another character during a conversation",
"Mickey Mouse having a conversation with Minnie Mouse",
"Mickey Mouse gesturing to a group of Disney characters during a conversation",
"Mickey Mouse pointing to a map or object while explaining to others during a conversation"
] |
[
"Mickey Mouse waving at other Disney characters during a conversation",
"Mickey Mouse having a conversation and shaking hands with other Disney characters",
"Mickey Mouse having a conversation with Minnie Mouse during their conversation scene",
"Mickey Mouse laughing with Goofy and Pluto during a conversation",
"Mickey Mouse giving a high-five to Donald Duck during a conversation"
] |
[
"Mickey Mouse standing in front of other characters during a conversation",
"Mickey Mouse waving at other characters during a conversation",
"Other characters gathering around Mickey Mouse during a conversation",
"Mickey Mouse pointing to something and talking during a conversation",
"other characters laughing and responding to Mickey Mouse during a conversation"
] |
{
"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: It makes sense to extract events that are typical of a scene where Mickey Mouse is interacting with other characters, likely in a cartoon or animated setting. The events should be simple, visual, and concrete, such as gestures, movements, or actions that can be easily depicted in a video frame.\n\nEVENTS:\n1. Mickey Mouse standing in front of other characters\n2. Mickey Mouse waving at other characters\n3. Other characters gathering around Mickey Mouse\n4. Mickey Mouse pointing to something and talking\n5. Other characters laughing and responding to Mickey Mouse",
"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: Given the query \"one Mickey Mouse is talking to other\", it makes sense to extract events that are related to Mickey Mouse interacting with other characters, likely in a cartoon or animated setting. The events should be concrete and visual, allowing for easy depiction in a video.\n\nEVENTS:\n1. Mickey Mouse standing in front of a group of characters\n2. Mickey Mouse shaking hands with another character\n3. Mickey Mouse having a conversation with Minnie Mouse\n4. Mickey Mouse gesturing to a group of Disney characters\n5. Mickey Mouse pointing to a map or object while explaining to others",
"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: 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 other characters, likely in a cartoon or theme park setting. The events should be concrete and visual, such as physical interactions or reactions between Mickey Mouse and the other characters.\n\nEVENTS:\n1. Mickey Mouse waving at other Disney characters\n2. Mickey Mouse shaking hands with other characters\n3. Mickey Mouse having a conversation with Minnie Mouse\n4. Mickey Mouse laughing with Goofy and Pluto\n5. Mickey Mouse giving a high-five to Donald Duck",
"video_URL": "https://youtube.com/watch?v=video9776",
"video_description": null,
"video_id": "video9776"
}
| 16
|
[
"The image shows a cartoon character that resembles a cow with a happy expression, wearing a large yellow hat and a yellow bow tie. The background features a pink and purple color scheme with some abstract shapes and a part of a clock visible on the left side.",
"The cartoon cow character, still donning its yellow hat and bow tie, maintains its cheerful demeanor. The background remains consistent with the previous frame, featuring a pink and purple color scheme with abstract shapes and a partial view of a clock. The cow appears animated and possibly engaged in a lively conversation or song, contributing to the overall cheerful atmosphere of the scene.",
"The cartoon cow character continues to wear its yellow hat and bow tie, maintaining a cheerful expression. The background still features a pink and purple color scheme with abstract shapes and a partial view of a clock. The cow seems to be animated, possibly continuing a lively conversation or song, which contributes to the overall cheerful atmosphere of the scene.",
"The cartoon cow character is animated, possibly continuing a lively conversation or song, maintaining its cheerful expression. The cow still wears its yellow hat and bow tie. The background remains a pink and purple color scheme with abstract shapes and a partial view of a clock, contributing to the overall cheerful atmosphere of the scene.",
"The cartoon cow character continues to be animated, likely still engaged in a lively conversation or song. The cow maintains its cheerful expression, still wearing its yellow hat and bow tie. The background persists with a pink and purple color scheme, abstract shapes, and a partial view of a clock, keeping the cheerful atmosphere intact.",
"The cartoon cow character is still animated, possibly continuing its lively conversation or song. The cow retains its cheerful expression and is still wearing its yellow hat and bow tie. The background remains with a pink and purple color scheme, abstract shapes, and a partial view of a clock, maintaining the cheerful atmosphere.",
"The cartoon cow character continues to engage in its lively conversation or song, maintaining its cheerful expression. The cow remains in its vibrant attire, including the yellow hat and bow tie. The background stays consistent with the pink and purple color scheme and abstract shapes, with the partial view of a clock still visible, reinforcing the cheerful and animated atmosphere of the scene.",
"The cartoon cow character continues its lively conversation or song, now facing slightly to the right. The cow maintains its cheerful expression and vibrant attire, including the yellow hat and bow tie. The background remains consistent with the pink and purple color scheme and abstract shapes, with the partial view of a clock still visible, reinforcing the cheerful and animated atmosphere of the scene.",
"The cartoon cow character remains in the midst of its lively conversation or song, now slightly turned to the left. The cow's cheerful expression and vibrant attire, featuring the yellow hat and bow tie, persist. The background continues with the pink and purple color scheme and abstract shapes, and the partial clock view is still present, maintaining the cheerful and animated scene atmosphere.",
"The cartoon cow character, still wearing the yellow hat and bow tie, is now looking directly forward. The cheerful expression and vibrant attire remain consistent. The background retains the pink and purple color scheme with abstract shapes, and the partial clock view is still visible, maintaining the cheerful and animated scene atmosphere.",
"The cartoon cow character, still wearing the yellow hat and bow tie, is now holding a wand with a star on top, appearing to be performing a magic trick or gesture. The cheerful expression and vibrant attire remain consistent. The background retains the pink and purple color scheme with abstract shapes, and the partial clock view is still visible, maintaining the cheerful and animated scene atmosphere.",
"The cartoon cow character continues to hold the wand with a star on top, reinforcing the theme of performing a magic trick or gesture. The character maintains a cheerful expression and vibrant attire, consistent with the previous frame. The background remains the same with the pink and purple color scheme and abstract shapes, and the partial clock view is still visible, continuing the cheerful and animated scene atmosphere.",
"The cartoon cow character is now seen smiling and waving its wand, continuing the theme of performing a magic trick. The character's cheerful expression and vibrant attire remain consistent. The background still features the pink and purple color scheme with abstract shapes, and the clock view is partially visible, maintaining the cheerful and animated scene atmosphere.",
"The cartoon cow character is holding a wand with a star on it, smiling and looking animated. The background features a pink and purple color scheme with abstract shapes, maintaining the cheerful and magical scene atmosphere.",
"The cartoon cow character continues to hold the wand with a star on it, now appearing surprised or curious, with wide eyes. The background remains consistent with the pink and purple color scheme and abstract shapes, keeping the magical scene atmosphere.",
"The cartoon cow character maintains its surprised or curious expression, still holding the wand with a star on it. The background continues to display the pink and purple color scheme and abstract shapes, preserving the magical scene atmosphere."
] |
video9776
|
A cartoon cow character, wearing a yellow hat and bow tie, is the main participant in the video. The character maintains a cheerful expression throughout, engaging in what appears to be a lively conversation or song. The setting features a consistent pink and purple color scheme with abstract shapes and a partial view of a clock in the background. As the video progresses, the cow character introduces a wand with a star on top, using it to perform a magic trick or gesture, which adds a magical theme to the scene. The character's expressions vary from cheerful to surprised or curious, but the overall atmosphere remains cheerful and animated. The video depicts the cow character's enthusiastic and magical performance, with no other participants or significant changes in the setting.
|
a naked child runs through a field
|
[
"A child taking off their clothes to run through a field and play in a sprinkler or water hose on a hot day.",
"A family having a picnic in a field with a child running freely after removing their clothes",
"A child playing a game of tag or hide-and-seek while running through a field and shedding clothes.",
"A child swimming in a nearby pond or lake and then running through the field to get back to their towel or clothes",
"A family participating in a music festival or a nudist event in a field where a child is running around and naturally without clothes."
] |
[
"A child running through a field of tall grass",
"A child laughs and spins around while running through a field",
"A child running through a field chasing after a butterfly or insect",
"child falls and gets up while running through a field",
"A child running through a field reaches the edge and climbs over a fence"
] |
[
"A child runs through a field",
"A child running through a field while laughing and spinning around",
"A child running through a field, picking wildflowers or touching the grass",
"A child running through a field trips and falls, then gets back up",
"A child running through a field, smiling and unselfconscious as they approach the camera"
] |
{
"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: This query describes a simple and vivid scene that can be easily visualized in a video, and it makes sense to extract events that focus on the child's actions and the setting. The events should capture the carefree and natural atmosphere of a child playing in a field, and can be reasonably captioned as individual frames in a video.\n\nEVENTS:\n1. A child runs through a field\n2. The child laughs and spins around in the field\n3. The child picks wildflowers or touches the grass in the field\n4. The child trips and falls in the field, then gets back up\n5. The child runs towards the camera, smiling and unselfconscious",
"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 a child being in a state of undress and in a natural setting, considering typical scenarios where a child might be without clothes and in a field. These events should be concrete and visualizable in a video, taking into account common activities or situations involving children in outdoor settings.\n\nEVENTS:\n1. A child taking off their clothes to play in a sprinkler or water hose on a hot day.\n2. A family having a picnic in a field, with the child removing their clothes to run around freely.\n3. A child playing a game of tag or hide-and-seek in a field, shedding clothes in the process of playing.\n4. A child swimming in a nearby pond or lake and then running through the field to get back to their towel or clothes.\n5. A family participating in a music festival or a nudist event in a field, where the child is naturally 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 related to the child's actions and interactions with the field environment, considering typical scenarios that could be visually depicted in a video. The events should be concrete and plausible, taking into account common activities and settings associated with a child running in a field.\n\nEVENTS:\n1. The child runs through tall grass\n2. The child laughs and spins around in the field\n3. The child chases after a butterfly or insect\n4. The child falls and gets up, continuing to run\n5. The child reaches the edge of the field and climbs over a fence",
"video_URL": "https://youtube.com/watch?v=video7025",
"video_description": null,
"video_id": "video7025"
}
| 16
|
[
"A young child is running on a grassy field near a body of water, with other people visible in the background.",
"A woman is running on a grassy field near a body of water, with other people visible in the background.",
"A woman is walking on a grassy field near a body of water, with people lounging and enjoying the sunny day under colorful umbrellas in the background.",
"A woman in a swimsuit walks on a grassy field near a body of water, with people lounging and enjoying the sunny day under colorful umbrellas in the background.",
"A group of people are enjoying a sunny day at a sandy beach near a body of water. Some individuals are lounging and sunbathing on the beach, while others are sitting or lying near the water's edge. Trees and foliage provide a natural backdrop to the scene, adding a serene atmosphere to the leisurely activities taking place.",
"A group of people are enjoying a sunny day at a sandy beach near a body of water. Some individuals are lounging and sunbathing on the beach, while others are sitting or lying near the water's edge. Trees and foliage provide a natural backdrop to the scene, adding a serene atmosphere to the leisurely activities taking place. In the foreground, a person in a white swimsuit sits on the sand, while another person in black shorts is reclining nearby. In the background, more individuals are engaged in various beach activities, with some standing near the water and others relaxing under the shade.",
"A group of people are enjoying a sunny day at a sandy beach near a body of water. Some individuals are lounging and sunbathing on the beach, while others are sitting or lying near the water's edge. Trees and foliage provide a natural backdrop to the scene, adding a serene atmosphere to the leisurely activities taking place. In the foreground, a person in a white swimsuit sits on the sand, while another person in black shorts is reclining nearby. In the background, more individuals are engaged in various beach activities, with some standing near the water and others relaxing under the shade.",
"The scene continues at the sandy beach near the body of water, with people still enjoying their day. The individual in the white swimsuit remains seated on the sand, and the person in black shorts stays reclined. In the background, there are still people near the water and others relaxing under the shade, maintaining the leisurely atmosphere.",
"The scene remains at the sandy beach near the body of water, with people still enjoying their day. The individual in the white swimsuit is now standing, and the person in black shorts stays reclined. In the background, there are still people near the water and others relaxing under the shade, maintaining the leisurely atmosphere.",
"The scene remains focused on the person in the white swimsuit standing on the sandy beach near the body of water, with the individual in black shorts still reclined. The background continues to show people near the water and others relaxing under the shade, preserving the leisurely atmosphere.",
"The current frame shows a black and white photograph of a person who appears to be in a uniform, suggesting a formal or professional setting. The focus is solely on this individual, with no additional context or background details visible.",
"The current frame features a black and white photograph of a person in a uniform, indicating a formal or professional environment. The focus remains solely on this individual, with no additional context or background details visible.",
"The current frame features a black and white photograph of a young man in a uniform. He has a serious expression and is looking directly at the camera, suggesting a formal portrait. The uniform includes a collared shirt with a striped neckband, indicating a possible military or official capacity. There is no additional context or background details visible, maintaining a focus on the individual.",
"The current frame continues to feature a black and white photograph of the same young man in a uniform. He maintains a serious expression and continues to look directly at the camera, reinforcing the formal portrait context. The uniform, with its collared shirt and striped neckband, suggests a military or official role. The absence of additional background details keeps the focus squarely on the individual, consistent with the previous frame's portrayal.",
"The current frame continues to feature a black and white photograph of the same young man in a uniform. He maintains a serious expression and continues to look directly at the camera, reinforcing the formal portrait context. The uniform, with its collared shirt and striped neckband, suggests a military or official role. The absence of additional background details keeps the focus squarely on the individual, consistent with the previous frame's portrayal.",
"The current frame shows a close-up black and white photograph of the young man in a uniform. He has a serious expression and is looking directly at the camera. The uniform, with its collared shirt and striped neckband, indicates a military or official role. The background remains plain, keeping the focus on the individual."
] |
video7025
|
The video depicts two distinct scenes. The first part shows a leisurely day at a beach near a body of water, where people are lounging, sunbathing, and enjoying the sunny day. The scene transitions through various individuals, including a young child and a woman, before focusing on a group of people relaxing on the beach. The atmosphere is serene, with trees and foliage providing a natural backdrop.
The second part of the video abruptly shifts to a series of black and white photographs of a young man in a uniform, suggesting a formal or professional setting, possibly military or official. The photographs are formal portraits, with the individual maintaining a serious expression and looking directly at the camera. The focus remains solely on the individual, with no additional context or background details visible. The video ends with a close-up of the young man's face, still in the formal portrait context.
|
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 during a talent show or audition",
"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 audition",
"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 audition",
"The little boy taking a deep breath before starting to sing at his singing performance",
"little boy takes a deep breath before singing at a talent show or audition",
"Confetti and balloons falling from the ceiling after a singing performance",
"Confetti and balloons falling from the ceiling after a talent show or audition performance"
] |
[
"The little boy stepping up to the microphone during a singing performance",
"The little boy stepping up to the microphone at a talent show or audition",
"The crowd applauding as the little boy begins to sing at his singing performance",
"The crowd applauding as the little boy begins to sing at a talent show or audition",
"Judges taking notes and looking impressed during a singing performance",
"Judges taking notes and looking impressed at a talent show or audition",
"little boy performing an emotional or powerful part of a song during a singing performance",
"little boy performing emotional or powerful song part in talent show or audition",
"The crowd giving a standing ovation after the little boy finishes his singing performance",
"The crowd giving a standing ovation after the little boy finishes singing at a talent show or audition"
] |
[
"A little boy standing on a stage with a microphone during a singing performance",
"A little boy standing on a stage with a microphone during a talent show or audition",
"boy giving an emotional singing performance",
"boy singing with emotional expression on a talent show or audition",
"Judges looking at the boy with focused attention during his singing performance",
"Judges looking at the boy with focused attention during a talent show audition",
"the crowd applauding and cheering during a singing performance",
"The crowd applauding and cheering at a talent show or audition",
"boy taking a bow after finishing his song at a singing performance",
"The boy taking a bow after finishing his song at a talent show or audition"
] |
{
"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: Given the query \"a little boy singing in front of judges and crowd\", it makes sense to extract events that are typical of a singing competition or audition setting, where a young performer is showcasing their talent to a panel of judges and an audience. The extracted events should be concrete and visual, allowing for easy depiction in a video.\n\nEVENTS:\n1. A little boy standing on a stage with a microphone\n2. The boy singing with emotional expression\n3. Judges looking at the boy with focused attention\n4. The crowd applauding and cheering\n5. The boy taking a bow after finishing his song",
"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 that are typical of a talent show or competition setting, as the query suggests a performance in front of an audience and judges. 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: Given the query \"a little boy singing in front of judges and crowd\", it makes sense to extract events that are typical of a singing competition or audition setting, as the presence of judges and a crowd suggests a performance-based scenario. The extracted events should be concrete and visual, focusing on the actions of the little boy and the reactions of the judges and crowd.\n\nEVENTS:\n1. The little boy stepping up to the microphone\n2. The crowd applauding as the little boy begins to sing\n3. Judges taking notes and looking impressed\n4. The little boy performing an emotional or powerful part of the song\n5. The crowd giving a standing ovation after the little boy finishes singing",
"video_URL": "https://youtube.com/watch?v=video9778",
"video_description": null,
"video_id": "video9778"
}
| 16
|
[
"A woman with curly hair is sitting on a red chair, smiling and looking down, possibly at notes or a script on a desk in front of her.",
"The woman with curly hair is now standing, appearing to adjust her jacket or blouse, possibly preparing to speak or move. The audience in the background remains attentive.",
"The woman with curly hair is still standing, leaning slightly forward, possibly engaging in conversation or reacting to something. The audience continues to watch attentively.",
"The woman with curly hair is now standing upright, adjusting her jacket, possibly indicating the conclusion of a segment or her preparation to move to another activity. The audience remains engaged, observing her actions.",
"The woman with curly hair is standing beside a chair on a stage, still adjusting her jacket. The audience continues to watch attentively.",
"The woman with curly hair is now seated in a chair on a stage, adjusting her jacket. The audience continues to watch attentively.",
"A young boy with curly hair is standing on stage holding a microphone, addressing the audience.",
"The young boy with curly hair continues to stand on stage, holding a microphone and speaking to the audience.",
"The young boy with curly hair continues to stand on stage, holding a microphone and speaking to the audience.",
"The young boy with curly hair is still on stage, holding a microphone and speaking to the audience.",
"The young boy with curly hair remains on stage, still holding the microphone and continuing to speak to the audience.",
"The young boy with curly hair is now clapping his hands, likely acknowledging the audience or other participants.",
"A man is seated in a red chair, clapping his hands while wearing sunglasses and a black t-shirt with the word \"GUILTY\" on it.",
"The man in the red chair is still clapping his hands, maintaining his engagement and enthusiasm. He is wearing sunglasses and a black t-shirt with the word \"GUILTY\" on it.",
"The man in the red chair continues to clap his hands, showing sustained enthusiasm and engagement. He remains wearing sunglasses and a black t-shirt with the word \"GUILTY\" on it.",
"Three individuals stand on stage in front of the \"The Voice\" logo. The person on the left appears to be singing into a microphone, the person in the center is clapping and smiling, and the person on the right is also clapping, smiling, and reaching towards the person in the center."
] |
video9778
|
A woman with curly hair is initially preparing to speak on a stage, adjusting her attire and engaging with the audience. She then transitions, allowing a young boy with curly hair to take the stage, where he addresses the audience using a microphone. The boy's segment appears to conclude with him clapping, acknowledging the audience. The scene then shifts to a man in a red chair, wearing a "GUILTY" t-shirt and sunglasses, who is clapping enthusiastically. The video culminates with three individuals on stage in front of "The Voice" logo, where one is singing, and the others are clapping and showing appreciation, suggesting a musical performance or competition setting.
|
fireworks are being lit and exploding in a night sky
|
[
"People setting up fireworks on the ground at night that lead to a fireworks explosion",
"People setting up fireworks on the ground at night for a fireworks display",
"A person lighting a firework fuse at night leading to a fireworks explosion",
"A person lighting a firework fuse during a nighttime fireworks display",
"Fireworks explosion shooting up into the night sky",
"Fireworks display with fireworks shooting up into the night sky",
"Fireworks exploding into colorful patterns at night",
"Fireworks exploding into colorful patterns during a nighttime fireworks display",
"Sparks and debris falling back down to the ground after a fireworks explosion at night",
"Sparks and debris falling back down to the ground during a nighttime fireworks display"
] |
[
"Fireworks shooting up into the air during a fireworks explosion at night",
"Fireworks shooting up into the air during a nighttime fireworks display",
"Explosions of colorful lights in the night sky from fireworks explosion",
"Fireworks display explosions of colorful lights in the night sky",
"sparks and embers falling back down to the ground after a fireworks explosion at night",
"Sparks and embers falling back down to the ground during a nighttime fireworks display",
"People watching and reacting to the fireworks explosion during the fireworks display at night",
"People watching and reacting to the fireworks display at night",
"Fireworks exploding in synchronized patterns and designs at night during a fireworks explosion",
"Fireworks exploding in synchronized patterns and designs during a nighttime fireworks display"
] |
[
"Fireworks explosion at night with fireworks shooting up into the night sky",
"Fireworks display at night with fireworks shooting up into the night sky",
"Explosions of colorful lights and patterns in the sky at night from fireworks displays",
"Explosions of colorful lights and patterns in the sky during a nighttime fireworks display",
"Sparks and embers falling back down to the ground after a fireworks explosion at night",
"Sparks and embers falling back down to the ground during a nighttime fireworks display",
"People watching and reacting to the fireworks explosion display at night",
"People watching and reacting to the fireworks display at night",
"Silhouettes of buildings or trees against the bright night sky during a fireworks explosion at night",
"Silhouettes of buildings or trees against the bright night sky during 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: It makes sense to extract events that describe the visual and auditory aspects of fireworks being lit and exploding in a night sky, as these events can be easily visualized in a video. The extracted events should focus on the fireworks themselves, as well as the surrounding environment and potential reactions from people watching.\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. Silhouettes of buildings or trees against the bright night sky",
"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 setup and execution of fireworks, as these events are likely to be visualized in a video associated with the query. Events such as preparation, ignition, and explosion of fireworks are concrete and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. People setting up fireworks on the ground\n2. A person lighting a firework fuse\n3. Fireworks shooting up into the night sky\n4. Fireworks exploding into colorful patterns\n5. Sparks and debris falling back down to the ground",
"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: It makes sense to extract events that are visually related to fireworks and their explosion in a night sky, considering the typical setting and characteristics of such an event. The extracted events should be concrete and likely to be seen in a video capturing fireworks explosions.\n\nEVENTS:\n1. Fireworks shooting up into the air\n2. Explosions of colorful lights in the night sky\n3. Sparks and embers falling back down to the ground\n4. People watching and reacting to the fireworks display\n5. Fireworks exploding in synchronized patterns and designs",
"video_URL": "https://youtube.com/watch?v=video9779",
"video_description": null,
"video_id": "video9779"
}
| 16
|
[
"Fireworks exploding in the night sky, with colorful flags visible on a ship's mast.",
"Fireworks continue to light up the night sky, with a prominent burst of golden sparks near the top of the frame. A ship's mast with colorful flags remains visible, adding to the festive atmosphere.",
"Fireworks illuminate the night sky, continuing from the previous frame. Another burst of golden sparks is prominent, accompanied by a ship's mast adorned with colorful flags. The festive atmosphere persists with fireworks, adding to the celebratory mood.",
"A large golden firework bursts in the night sky, accompanied by a ship's mast decorated with colorful flags. The festive atmosphere continues with the ongoing fireworks display, enhancing the celebratory mood.",
"The large golden firework continues its display in the night sky, with the ship's mast decorated with colorful flags still visible. The celebratory atmosphere persists, marked by the ongoing fireworks and vibrant colors.",
"The large golden firework in the night sky has continued its dazzling display, with the ship's mast still prominently decorated with colorful flags. The vibrant and celebratory atmosphere is maintained, highlighted by the ongoing fireworks.",
"The large golden firework continues to illuminate the night sky, with additional fireworks now visible, adding to the festive atmosphere. The ship's mast remains adorned with colorful flags, maintaining the celebratory context.",
"The golden firework explodes into a vibrant display, with numerous white and gold sparks radiating outward. The ship's mast with colorful flags is still visible, enhancing the celebratory mood of the scene.",
"The golden firework continues to burst into a dazzling array of white and gold sparks, illuminating the night sky. The ship's mast with colorful flags remains in view, maintaining the festive atmosphere.",
"The golden firework has transitioned into a brownish hue, continuing to explode in the night sky. The ship's mast with colorful flags is still visible, reinforcing the festive ambiance.",
"The firework continues to expand in the sky, now forming a large, intricate pattern with sparkling lights. The ship's mast with colorful flags remains prominently visible, contributing to the festive atmosphere of the scene.",
"The firework is still prominently visible in the sky, continuing to expand and form a large, intricate pattern with sparkling lights. The ship's mast with colorful flags remains prominently visible, contributing to the festive atmosphere of the scene. The surrounding area appears dark, emphasizing the brightness of the firework.",
"The firework has reached its peak in the sky, displaying a large, bright, and colorful burst with numerous sparkling lights. The ship's mast with colorful flags is still visible, enhancing the festive atmosphere. The surrounding area remains dark, highlighting the firework's brilliance.",
"The firework continues to display its radiant burst in the sky, with the ship's mast and colorful flags still visible, maintaining the festive atmosphere. The dark surroundings emphasize the firework's bright and vibrant display.",
"The firework continues to light up the night sky with its bright and radiant burst, with the ship's mast and colorful flags still prominently displayed, enhancing the festive and celebratory atmosphere. The dark surroundings continue to emphasize the firework's vibrant display.",
"The fireworks display continues to light up the night sky with an explosion of bright, golden sparks. The ship's mast and colorful flags remain prominently displayed, maintaining the festive and celebratory atmosphere. The dark surroundings continue to highlight the vibrant fireworks."
] |
video9779
|
A fireworks display is taking place at night, near a ship with a mast adorned with colorful flags. The fireworks explode in the sky, creating a festive and celebratory atmosphere, with bursts of golden sparks and vibrant colors illuminating the dark surroundings. The ship's mast with colorful flags remains visible throughout the display, contributing to the overall festive mood. The fireworks continue to explode and expand in the sky, forming intricate patterns with sparkling lights, and eventually reaching a peak with a large, bright, and colorful burst. The display maintains its vibrancy and celebratory atmosphere until the end, with the ship's presence and the fireworks combining to create a joyful and festive event.
|
a man is singing and standing in the road
|
[
"A man picks up a guitar case and walks out of a building to go singing",
"A man picks up a guitar case and walks out of a building while standing",
"A man walks down the street looking for a spot to perform his singing",
"A man walks down the street, looking for a spot to stand and perform",
"A man stands at the side of the road, takes a deep breath, and begins to sing",
"A man stands at the side of the road, takes a deep breath, and begins to sing",
"A man sets up a microphone stand in the middle of the road to start singing",
"A man sets up a microphone stand in the middle of the road",
"A man attracts a crowd of people who stop to listen to him sing in an impromptu performance of his music",
"a man stands and sings attracting a crowd of people who stop to listen to him"
] |
[
"The man sings to a crowd of people gathered around him",
"The man stands and sings to a crowd of people gathered around him",
"Cars drive by the man while he is singing in the road",
"Cars drive by the man while he is standing and singing in the road",
"people stopping to listen to a man singing in the street or public place",
"people stop to listen to the man singing",
"The man plays a musical instrument while singing in the road",
"The man stands in the road playing a musical instrument while singing",
"Bystanders throw money into a tip jar or hat in front of the man singing",
"Bystanders throw money into a tip jar or hat in front of the standing man"
] |
[
"A man stands in the middle of the road singing",
"A man stands in the middle of the road",
"The man sings with his mouth open",
"The man sings with his mouth open while standing",
"people passing by look at the man singing",
"people passing by look at the man standing and singing",
"Cars drive around the man standing in the road while he is singing",
"Cars drive around the man standing in the road",
"The man gestures with his hands while singing",
"The man gestures with his hands while singing and standing"
] |
{
"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 singing and standing in the road<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the actions of the man, such as his singing and standing in the road, as these are concrete and visual events that could be captured in a video. The events should focus on the specific actions and setting described in the query, without adding extraneous details.\n\nEVENTS:\n1. A man stands in the middle of the road\n2. The man sings with his mouth open\n3. People passing by look at the man singing\n4. Cars drive around the man standing in the road\n5. The man gestures with his hands while singing",
"en_article_excerpt": "a man is singing and standing in the road",
"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 singing and standing in the road<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query \"a man is singing and standing in the road\", it makes sense to extract events that could lead up to this scene, such as the man's preparation or actions before standing in the road to sing. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. A man picks up a guitar case and walks out of a building\n2. A man walks down the street, looking for a spot to perform\n3. A man stands at the side of the road, takes a deep breath, and begins to sing\n4. A man sets up a microphone stand in the middle of the road\n5. A man attracts a crowd of people who stop to listen to him sing",
"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 singing and standing in the road<|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 actions of the man singing and standing in the road, considering the context of a video that could visually capture these moments. The events should be concrete and plausible, such as interactions with passersby, reactions from the audience, or the man's performance itself.\n\nEVENTS:\n1. The man sings to a crowd of people gathered around him\n2. Cars drive by the man while he is singing in the road\n3. People stop to listen to the man singing\n4. The man plays a musical instrument while singing in the road\n5. Bystanders throw money into a tip jar or hat in front of the man",
"video_URL": "https://youtube.com/watch?v=video7028",
"video_description": null,
"video_id": "video7028"
}
| 16
|
[
"A person is skateboarding in front of a traditional Japanese gate, with several people standing and watching in the background.",
"A person is walking past a traditional Japanese gate, wearing sunglasses and a beanie. The background shows a crowd of people and a large red lantern hanging in front of the gate.",
"A person stands outside near a traditional Japanese gate, wearing a jacket and a red scarf, seemingly engaged in conversation or speaking. The background shows a crowd of people and some structures that resemble a festival or cultural setting.",
"The person, still near the traditional Japanese gate, is now smiling and looking directly at the camera. The background remains consistent with the crowd and cultural setting.",
"The scene shifts to a group of people gathered around a table in what appears to be a traditional Japanese bar or restaurant. They are engaged in a lively activity, clinking glasses together, likely celebrating or toasting. The atmosphere is convivial, with several individuals raising their drinks in unison. There is a sense of camaraderie and enjoyment among the group, as they interact with each other in a warm and informal setting. The bar counter and traditional decor in the background suggest a casual and culturally rich environment.",
"The group of four people stands together in an open area with traditional architectural elements, such as large doors and red walls, which suggests a historical or cultural setting. One individual raises their hand in a gesture, possibly greeting or signaling, while the others stand close together, indicating a sense of unity and possibly the continuation of their social interaction from the previous scene. The environment is bright and spacious, emphasizing a shift from the indoor setting of the bar to an outdoor or semi-outdoor area, possibly continuing their celebration in a different venue.",
"The group of four people remains together in the same open area with traditional architectural elements. One individual continues to raise their hand in a gesture, likely still greeting or signaling, while the others remain close together, maintaining a sense of unity. The environment remains bright and spacious, suggesting the continuation of their social interaction in the same venue.",
"A man is seen looking intently at a red sign with Japanese text and the number \"2,\" positioned in an urban setting with surrounding buildings.",
"In the current frame, a group of people is gathered in a room, seemingly engaged in a lively activity. There are several individuals standing and clapping, while others are seated at tables with plates and cups, indicating a social or dining event. The atmosphere appears festive, and the participants seem to be enjoying themselves. The background includes framed pictures and a large screen displaying an animated character, adding to the convivial ambiance of the setting.",
"The group of people is now more actively engaged in the activity, with several individuals raising their hands enthusiastically. The atmosphere remains festive as everyone appears to be enjoying the lively interaction. The seated participants continue to clap and participate, maintaining the convivial ambiance of the social or dining event. The background still features framed pictures and a large screen displaying an animated character, reinforcing the celebratory setting.",
"The current frame shows a bustling urban street scene at night, with numerous cars and taxis moving along a busy road. The traffic is heavy, suggesting a peak hour in a metropolitan area. The backdrop is filled with illuminated signs and storefronts, creating a vibrant cityscape. The atmosphere is dynamic, with the continuous flow of vehicles and the bright lights of the city adding to the sense of activity.",
"In this frame, a person is walking along a sidewalk next to the busy street, moving away from the camera. The city's night lights and signs continue to illuminate the area, maintaining the dynamic and vibrant atmosphere. Traffic remains heavy, with vehicles still moving along the road. The person appears to be crossing a pedestrian bridge or overpass, indicated by the railings and elevated walkway.",
"The current frame shows the same person, now in a more open area, possibly in the middle of the street, engaging with the camera. The individual is wearing a beanie and a necklace, and they seem to be smiling or talking. The backdrop remains consistent with the vibrant city lights and illuminated signs, continuing to create a lively atmosphere. The traffic in the background is still visible, suggesting the person is near a busy intersection or pedestrian area.",
"The current frame shows a person standing in front of a traditional building, likely a temple, engaging with the camera. The individual is wearing a beanie, sunglasses, and a necklace. The background includes the temple's architecture, suggesting a cultural or historical setting. Other people are visible in the background, possibly exploring or walking around the area.",
"The person in the current frame is still standing in front of the traditional building, likely a temple, engaging with the camera. They are now holding up two fingers, possibly in a gesture of peace or victory. The individual continues to wear a beanie, sunglasses, and a necklace. The background remains consistent with the temple's architecture, suggesting a cultural or historical setting. Other people are still visible in the background, possibly exploring or walking around the area.",
"In the current frame, the person is now walking on a busy city street at night. They are wearing a jacket and jeans, and appear to be holding something in their hands. The background shows multiple vehicles, including cars and a bus, indicating a bustling urban environment. The area is brightly lit with neon signs, suggesting a lively nightlife scene."
] |
video7028
|
The video depicts a series of scenes showcasing a person's experiences in a Japanese cultural setting, interspersed with urban landscapes. The video begins with the person skateboarding in front of a traditional Japanese gate, followed by scenes of them walking and interacting with others near the gate. They are then shown participating in a lively celebration at a traditional Japanese bar or restaurant, toasting with a group of friends. The group continues their social interaction in an open area with traditional architectural elements, before the scene shifts to an urban setting where the person is seen looking at a sign and later attending a festive event with others. The video also features scenes of the person walking in busy city streets at night, interacting with the camera, and visiting a traditional temple. Throughout the video, the person is often shown wearing casual, eclectic clothing, including a beanie, sunglasses, and a necklace. The overall context suggests a cultural exchange or travel experience, with the person exploring and engaging with Japanese culture and urban environments.
|
cartoon show for kids
|
[
"Colorful characters singing and dancing together in a cartoon show",
"a group of friends playing a game or sport in a fantastical environment in a cartoon show",
"A young hero character learning a valuable lesson from a wise mentor in a cartoon show",
"A comedic villain getting outsmarted by the main characters in a cartoon show",
"A fun and imaginative adventure sequence with characters exploring a new world in a cartoon show"
] |
[
"colorful characters dancing and singing together in a cartoon show",
"A group of animal friends playing in a magical forest in a cartoon show",
"A superhero cartoon character saving the day in a cartoon show",
"A cartoon teacher explaining a fun science experiment on a cartoon show",
"A group of kids on a cartoon adventure, exploring a new planet in a cartoon show"
] |
[
"Colorful characters singing and dancing together in a cartoon show",
"a group of cartoon friends playing a game or sport in a cartoon show",
"A cartoon character learning a new skill or lesson from a teacher in a cartoon show",
"Cartoon animals going on a fun adventure or exploration in a cartoon show",
"A birthday party or celebration with cartoon characters and kids during a cartoon show"
] |
{
"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: cartoon show for kids<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query \"cartoon show for kids\", it makes sense to extract events that are commonly found in children's cartoons, such as characters interacting with each other, engaging in fun activities, or learning valuable lessons. These events should be concrete and visually engaging, making them suitable for a video caption.\n\nEVENTS:\n1. Colorful characters singing and dancing together\n2. A group of cartoon friends playing a game or sport\n3. A cartoon character learning a new skill or lesson from a teacher\n4. Cartoon animals going on a fun adventure or exploration\n5. A birthday party or celebration with cartoon characters and kids",
"en_article_excerpt": "cartoon show for kids",
"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: cartoon show for kids<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query \"cartoon show for kids\", it makes sense to extract events that are commonly found in children's cartoons, such as characters interacting with each other, engaging in fun activities, or learning valuable lessons. These events should be colorful, lively, and easy to visualize in a video format.\n\nEVENTS:\n1. Colorful characters singing and dancing together\n2. A group of friends playing a game or sport in a fantastical environment\n3. A young hero character learning a valuable lesson from a wise mentor\n4. A comedic villain getting outsmarted by the main characters\n5. A fun and imaginative adventure sequence with characters exploring a new world",
"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: cartoon show for kids<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query \"cartoon show for kids\", it makes sense to extract events that are typical scenes or plot elements commonly found in children's cartoons, such as character interactions, action sequences, or educational moments. These events should be visually engaging and easy to imagine as a video clip.\n\nEVENTS:\n1. Colorful characters dancing and singing together\n2. A group of animal friends playing in a magical forest\n3. A superhero cartoon character saving the day\n4. A cartoon teacher explaining a fun science experiment\n5. A group of kids on a cartoon adventure, exploring a new planet",
"video_URL": "https://youtube.com/watch?v=video7029",
"video_description": null,
"video_id": "video7029"
}
| 16
|
[
"A cartoon character resembling a blue octopus with a pink hat and an orange shirt is standing next to a wall-mounted telephone. The character appears to be reaching out to answer the phone.",
"The blue octopus character is now holding the phone's receiver, seemingly engaged in a conversation, as indicated by its attentive posture and facial expression.",
"The blue octopus character remains engaged in the conversation, with one hand holding the phone receiver to its ear and the other resting on the wall. Its focused expression suggests it is actively listening or speaking on the phone.",
"The yellow sponge character with a surprised expression is holding a broom, seemingly reacting to the ongoing situation.",
"The yellow sponge character is now holding a telephone receiver, smiling, and appearing to be engaged in a conversation, while the previous broom is no longer visible.",
"The yellow sponge character is still holding the telephone receiver and talking on the phone, with a smile on his face, indicating he is having a pleasant conversation.",
"The yellow sponge character continues his pleasant conversation on the telephone, now looking slightly surprised or amused, possibly reacting to something unexpected in the call.",
"The blue octopus-like character is engaged in a conversation on the telephone, holding the receiver close to his ear. He appears focused and attentive, suggesting he is listening intently to the person on the other end of the line. The scene continues to depict the character's interaction, maintaining the continuity of the dialogue established in the previous frame.",
"The blue octopus-like character continues his conversation on the telephone, now holding the receiver away from his ear. He displays a broad smile and seems to be responding enthusiastically to the person on the other end of the line.",
"The yellow sponge character appears visibly angry, standing with his fists on his hips and an open mouth, as if shouting or expressing frustration.",
"The yellow sponge character is now pulling on his hair with both hands, showing heightened frustration or distress, as his open mouth reveals his teeth.",
"The yellow sponge character continues to display extreme distress, pulling on his hair with both hands, his mouth wide open in an exaggerated expression of frustration.",
"The yellow sponge character is now holding a corded telephone receiver to his ear, smiling and looking relaxed, indicating a significant shift in mood from the previous frame.",
"The yellow sponge character continues to hold the corded telephone receiver to his ear, still smiling and looking relaxed, maintaining the same cheerful demeanor as in the previous frame.",
"The yellow sponge character continues to hold the corded telephone receiver to his ear, still smiling and looking relaxed, maintaining the same cheerful demeanor as in the previous frame.",
"The yellow sponge character is smiling and looking relaxed while holding the corded telephone receiver to his ear."
] |
video7029
|
A video depicts a conversation between a blue octopus character and a yellow sponge character over the telephone. The blue octopus answers the phone and engages in a conversation, displaying focused and attentive expressions. Meanwhile, the yellow sponge character initially reacts with surprise, then joins the conversation, smiling and appearing to have a pleasant exchange. However, the yellow sponge's mood shifts, and he becomes frustrated and distressed, displaying anger and pulling his hair. The situation resolves as the yellow sponge character returns to speaking on the phone, this time showing a significant improvement in mood, smiling, and looking relaxed throughout the remainder of the conversation. The context suggests a lighthearted and comedic exchange between the two characters, with the yellow sponge experiencing a range of emotions before ultimately returning to a positive state.
|
some cartoon characters are moving around an area
|
[
"Cartoon characters walking in different directions",
"Characters running into each other and reacting during the movement of cartoon characters",
"Characters interacting with objects in the area, such as picking up items or climbing structures during the movement of cartoon characters",
"Cartoon characters entering and exiting buildings or other enclosed spaces in animated scenes or shows",
"cartoon characters using bicycles or skateboards to move around in their daily activities or adventures"
] |
[
"cartoon characters running around in circles",
"Characters jumping over obstacles in the movement of cartoon characters",
"Characters interacting with each other through conversation or gestures in the movement of cartoon characters",
"cartoon characters chasing one another in animated movement sequences",
"Characters playing with objects or toys in the area during the movement of cartoon characters"
] |
[
"cartoon characters walking around a park in motion or movement scenes",
"cartoon characters running through a city street",
"cartoon characters jumping over obstacles in a forest during movement sequences",
"Characters interacting with each other through movement in a town square",
"Cartoon characters dancing in a colorful meadow during movement scenes"
] |
{
"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: some cartoon characters are moving around an area<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are visually concrete and related to the movement of cartoon characters in a given area, considering typical scenarios often depicted in cartoons. This could involve various actions and interactions between characters, as well as movements within their environment.\n\nEVENTS:\n1. Cartoon characters walking around a park\n2. Characters running through a city street\n3. Characters jumping over obstacles in a forest\n4. Characters interacting with each other in a town square\n5. Characters dancing in a colorful meadow",
"en_article_excerpt": "some cartoon characters are moving around an area",
"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: some cartoon characters are moving around an area<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of cartoon characters and their interactions with their environment, considering common cartoon scenarios and settings. The extracted events should be visually engaging and plausible in a cartoon context, such as characters walking, running, or interacting with objects.\n\nEVENTS:\n1. Cartoon characters walking in different directions\n2. Characters running into each other and reacting\n3. Characters interacting with objects in the area, such as picking up items or climbing structures\n4. Characters entering and exiting buildings or other enclosed spaces\n5. Characters using transportation like bicycles or skateboards to move around",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: some cartoon characters are moving around an area<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical actions or behaviors associated with cartoon characters in a dynamic setting, such as interacting with each other or their environment. Given the vague nature of the query, the extracted events should be general and common in cartoon scenarios.\n\nEVENTS:\n1. Cartoon characters running around in circles\n2. Characters jumping over obstacles\n3. Characters interacting with each other through conversation or gestures\n4. Characters chasing one another\n5. Characters playing with objects or toys in the area",
"video_URL": "https://youtube.com/watch?v=video9772",
"video_description": null,
"video_id": "video9772"
}
| 16
|
[
"A character with wings is flying above a rocky landscape.",
"A character with wings is continuing to fly over the rocky landscape, maintaining their forward momentum.",
"The character with wings continues to soar over the rocky terrain, maintaining their forward momentum, and appears to be getting closer to their destination.",
"The character with wings is navigating through a narrow canyon, skillfully maneuvering between the rocky cliffs while continuing their flight towards their destination.",
"The character with wings is flying over a vast expanse of rugged, reddish-brown rock formations under a cloudy sky.",
"The character with wings is flying over a coastal area with clear blue water and sandy cliffs. The character is approaching the shoreline, where two individuals are visible on the beach. The scene features trees and a castle-like structure in the background, suggesting a journey towards a significant destination.",
"The character with wings is now perched on a rocky outcrop, overlooking the beach. Two individuals are seen standing on the shoreline, engaged in conversation or observation. The serene coastal setting, with sandy cliffs and distant greenery, provides a tranquil backdrop to their interaction.",
"The character with wings is now closer to the camera, revealing more intricate details of its features and attire. Its wings are slightly spread, indicating a readiness to take flight. The two individuals on the shore continue their engagement, their attention still directed towards the character. The coastal backdrop remains consistent, emphasizing the contrast between the mythical element and the natural scenery.",
"The character with wings is now in an elevated position, closer to the camera, revealing more intricate details of its features and attire. Its wings are spread wide, indicating readiness to take flight. The two individuals on the shore continue their engagement, their attention still directed towards the character. The coastal backdrop remains consistent, emphasizing the contrast between the mythical element and the natural scenery.",
"The character with wings is now even closer to the camera, showcasing its detailed features and attire. Its wings remain spread wide, preparing for flight. The two individuals on the shore are still engaged, their attention focused on the character. The coastal backdrop continues to emphasize the contrast between the mythical element and the natural scenery.",
"The character with wings, now fully airborne, is seen taking flight. The wings are fully extended, propelling the character upward. The two individuals on the shore continue to watch, their gaze following the character's ascent. The coastal backdrop remains a prominent feature, highlighting the contrast between the mythical character and the serene natural scenery.",
"The character with wings, now fully airborne, is seen taking flight. The wings are fully extended, propelling the character upward. The two individuals on the shore continue to watch, their gaze following the character's ascent. The coastal backdrop remains a prominent feature, highlighting the contrast between the mythical character and the serene natural scenery.",
"The character with wings continues to soar higher into the sky, wings fully extended, as the two individuals on the shore persist in observing the character's ascent. The background features a serene coastal landscape, emphasizing the contrast between the mythical character and the natural scenery.",
"The character with wings continues to soar higher into the sky, wings fully extended, as the two individuals on the shore persist in observing the character's ascent. The background features a serene coastal landscape, emphasizing the contrast between the mythical character and the natural scenery.",
"The character with wings ascends higher into the sky, now against a backdrop of clouds, indicating further elevation. The two individuals on the shore continue to watch the character's ascent, maintaining their position. The natural scenery of the coastal landscape remains consistent, highlighting the character's fantastical flight against the serene environment.",
"The video continues to depict a fantastical landscape, now focusing on an architectural view of a city with a prominent building resembling the Sydney Opera House. The scene includes a blend of buildings and greenery, suggesting an urban environment. No characters or actions are depicted in this frame, maintaining a static and serene atmosphere."
] |
video9772
|
A winged character flies over a rocky landscape, navigating through a narrow canyon and eventually reaching a coastal area with a castle-like structure. The character lands on a rocky outcrop and interacts with two individuals on the beach, before taking flight again. As the character soars higher into the sky, the two individuals watch from the shore, set against a serene coastal backdrop. The character continues to ascend, eventually disappearing into the clouds. The video then shifts to depict a fantastical urban landscape, featuring a city with a prominent building, suggesting a new setting or destination, possibly related to the character's journey.
|
baseball player hits ball
|
[
"Pitcher throwing the ball to hit it",
"batter swinging the bat while hitting a ball",
"Ball flying through the air after being hit during a hit",
"runner rounding the bases after hitting a ball",
"Fielder attempting to catch the hit ball during a baseball game after a batter is hitting a ball"
] |
[
"Baseball player swinging bat while hitting a ball",
"ball flying through the air when hitting a ball",
"Ball landing in the outfield after hitting a ball",
"Runner rounding bases after hitting a ball",
"Fielder catching the ball after hitting it"
] |
[
"Baseball player swings bat while hitting a ball",
"ball leaves pitcher's hand when hitting a ball",
"Bat makes contact with ball when hitting a ball",
"Ball soars through the air when hitting a ball",
"Player runs to first base after hitting a ball"
] |
{
"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: baseball player hits ball<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the action of hitting a ball in a baseball game, as these events are likely to be visualized in a video of the query. The extracted events should focus on the physical actions involved in hitting a ball, such as the player's swing and the ball's movement.\n\nEVENTS:\n1. Baseball player swings bat\n2. Ball leaves pitcher's hand\n3. Bat makes contact with ball\n4. Ball soars through the air\n5. Player runs to first base",
"en_article_excerpt": "baseball player hits ball",
"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: baseball player hits ball<|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 hitting a ball in a baseball game, as these events are likely to be visualized in a video of the query. The extracted events should be specific to the sport of baseball and the action of hitting, taking into account common scenarios that occur during a game.\n\nEVENTS:\n1. Pitcher throwing the ball\n2. Batter swinging the bat\n3. Ball flying through the air after being hit\n4. Runner rounding the bases\n5. Fielder attempting to catch the hit ball",
"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: baseball player hits ball<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are direct consequences or actions related to a baseball player hitting a ball, as these events are likely to be visualized in a video of the query. The extracted events should be specific and relevant to the sport of baseball, considering the typical actions and outcomes that occur when a player hits a ball.\n\nEVENTS:\n1. Baseball player swinging bat\n2. Ball flying through the air\n3. Ball landing in the outfield\n4. Runner rounding bases\n5. Fielder catching the ball",
"video_URL": "https://youtube.com/watch?v=video7021",
"video_description": null,
"video_id": "video7021"
}
| 16
|
[
"A baseball player in a white uniform with the number 20 is at bat, preparing to swing. A catcher in red gear and an umpire are positioned behind the batter. In the background, players in red uniforms are seated in the dugout.",
"The baseball player in the white uniform with the number 20 has just completed his swing, following through with the motion. The catcher in red gear is crouched, ready to catch the ball, while the umpire stands closely behind. The players in red uniforms remain seated in the dugout, watching the action.",
"The baseball player in the white uniform with the number 20 is now completing his follow-through motion after swinging. The catcher in red gear is crouched, ready to catch the ball, while the umpire stands closely behind. The players in red uniforms remain seated in the dugout, watching the action.",
"The baseball player in the white uniform with the number 20 has finished his swing and is moving forward. The catcher in red gear is now standing up, possibly after catching the ball, while the umpire remains in position. The players in red uniforms are still seated in the dugout, observing the ongoing play.",
"The baseball player in the white uniform with the number 20 continues to move forward after finishing his swing. The catcher in red gear remains upright, suggesting he has successfully caught the ball. The umpire is still in his position, closely observing the play. The players in red uniforms are still seated in the dugout, attentively watching the game.",
"The player in the white uniform with the number 20 is now further away from the batter's box, having completed his swing and movement. The catcher, dressed in red gear, maintains his upright position, indicating the ball has been securely caught. The umpire continues to observe the ongoing action closely. The players in red uniforms remain seated in the dugout, intently observing the game.",
"A player in a red uniform with the number 3 is running across the outfield, possibly trying to retrieve a ball. The setting appears to be a baseball field, with trees and parked cars visible in the background.",
"The player in a red uniform with the number 3 continues running across the outfield, still focused on retrieving the ball. The outfield setting remains consistent, with trees and a white vehicle visible in the background.",
"The player in a red uniform with the number 3 is still running across the outfield, maintaining his focus on retrieving the ball. The outfield setting remains consistent, with trees and a white vehicle visible in the background.",
"The player in a red uniform with the number 3 continues to run across the outfield, actively moving towards the ball. The background still shows the trees and a white vehicle, indicating the scene remains consistent with the previous frame.",
"The player in a red uniform with the number 3 is now approaching the outfield fence, preparing to catch the ball near the ground. The background remains consistent with the previous frames, showing the trees and white vehicle.",
"The player in a red uniform is now crouched near the outfield fence, attempting to catch the ball just before it reaches the ground. The background remains consistent with trees and parked vehicles visible.",
"A baseball player wearing a black and white uniform with the number 14 is walking towards the dugout, passing by teammates who are also in uniform.",
"The baseball player wearing a black and white uniform with the number 14 continues towards the dugout, accompanied by teammates who are walking alongside. One teammate, number 75, is visible, engaging in conversation with the player. The group approaches the dugout, with one teammate walking in the opposite direction.",
"The baseball player wearing a black and white uniform with the number 14 continues towards the dugout, still accompanied by teammates. The player is now joined by a teammate wearing the number 23. Another teammate, number 11, is visible, engaging in conversation with the player. The group approaches the dugout, with one teammate walking in the opposite direction.",
"The baseball player wearing a black and white uniform with the number 14 continues walking towards the dugout, still accompanied by teammates. The player is now joined by a teammate wearing the number 23. Another teammate, number 11, is visible, engaging in conversation with the player. The group approaches the dugout, with one teammate walking in the opposite direction."
] |
video7021
|
A baseball game is taking place between two teams, one wearing white uniforms and the other wearing red uniforms. The video begins with a player from the white team, number 20, at bat, swinging and following through with the motion. The catcher from the red team is crouched and ready to catch the ball, while the umpire observes the play. After the swing, the catcher stands up, suggesting he has caught the ball, and the player from the white team moves forward.
The scene then shifts to the outfield, where a player from the red team, number 3, is running to retrieve a ball. He continues to run across the outfield, eventually approaching the fence and attempting to catch the ball near the ground.
The video then cuts to a different scene, showing a player from a team wearing black and white uniforms, number 14, walking towards the dugout with teammates. They engage in conversation and approach the dugout, joined by other teammates. The scene suggests a break in the game or a transition between innings, with the players interacting and moving towards the dugout. The overall context is a baseball game with multiple teams and players involved in different aspects of the game.
|
End of preview. Expand
in Data Studio
README.md exists but content is empty.
- Downloads last month
- 7
Size of downloaded dataset files:
4.08 MB
Size of the auto-converted Parquet files:
4.08 MB
Number of rows:
1,000