Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual
Collection
Datasets used in the paper: Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video Retrieval
•
36 items
•
Updated
Dataset Viewer
query
stringclasses 259
values | prequel
listlengths 0
30
| sequel
listlengths 0
30
| during
listlengths 0
30
| metadata
dict | num_of_frames
int64 16
16
| frame_captions
listlengths 16
16
| video_id
stringlengths 6
45
| frame2video_caption
stringlengths 72
2.39k
|
|---|---|---|---|---|---|---|---|---|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=t8lY-rjy7-Y",
"video_description": "9월 12일, 경주에서는 역대 최대 규모인 5.8 지진이 일어났다. 지진으로 서울과 수도권까지 전국이 흔들렸고, 이로 인해 전화와 카카오톡도 모두 먹통이었다. 정부는 지진 발생 9분이 지나서야 긴급재난문자를 발송했고 이마저도 서울과 수도권 지역 국민들은 문자를 받지 못했다. #경주 #지진 #재난문자",
"video_id": "t8lY-rjy7-Y"
}
| 16
|
[
"A group of young women and children are seen running away from a staircase in a building. They appear to be in a state of panic, with some of them running down the stairs while others are on the floor, likely in a hurry to escape. The scene suggests a sense of urgency and distress.",
"A group of young men are engaged in a physical altercation in a classroom setting. The students are in motion, pushing and shoving each other, with some of them raising their arms or leaning against desks. The classroom has desks and chairs arranged in rows, with students wearing casual clothing such as t-shirts and jeans. A teacher, visible on one of the desks, appears to be intervening to separate the group. The classroom has a plain white wall and a yellow baseboard, with a window visible on the right side of the frame.",
"The current frame shows a train station platform during nighttime. A train is visible on one of the tracks, which is stationary. The platform appears clean and well-maintained with visible station signage and lighting. The train tracks have multiple tracks, and there are no people present on the platform. There is a clear view of the tracks and the surrounding infrastructure, including the station's roof and pillars.",
"The current frame shows an image from a surveillance camera within a warehouse. The warehouse is filled with large stacks of boxes and shelving units, indicating a storage area. The scene appears to be indoors, with fluorescent lighting. The timestamp on the image reads 2018-08-12 19:44:32, and there is text in Korean at the bottom of the frame, likely providing context or additional information about the event.",
"The current frame shows an image from a surveillance camera within a warehouse. The image captures large stacks of boxes and shelving units, indicating a storage area. There is a timestamp on the image that reads 2016-09-12 19:44:57. Visible text in Korean at the bottom of the frame is present, likely providing context or additional information about the event.",
"The current frame shows a single scene of debris and a plastic bag on the ground. The area appears to be an outdoor sidewalk or street, possibly at night. The ground is littered with red and blue bricks, and a yellow and blue caution tape is stretched across the scene, likely indicating a restricted area or warning for pedestrians. A large, tangled plastic bag lies on the ground, partially obscured by the debris. The scene suggests an incident involving the movement or disturbance of the bags on the street.",
"The current frame shows a street scene at night with a significant light source in the background. There is debris scattered across the ground, including what appears to be plastic bags and other indistinct objects. On the left side of the frame, there is a large, tangled plastic bag lying on the ground, partially obscured by the debris. A yellow and blue caution tape is stretched across the scene, indicating a restricted area or warning for pedestrians. The lighting in the scene suggests it is either dawn or dusk due to the low ambient light, and the overall scene suggests an incident involving the movement or disturbance of the bags on the street.",
"The current frame shows a person sitting on a bed, interacting with a small object on the bed. The individual appears to be engaged in some activity, possibly using the object for personal reasons or a hobby. The setting suggests a casual indoor environment, possibly a home or an apartment. There are pillows and other furnishings visible on the bed, indicating it is likely a bedroom. The lighting is dim, with a focus on the person and the object they are holding. There is no visible movement or action suggesting any specific event or incident.",
"The current frame shows a computer screen displaying a webpage with Korean text. The webpage header includes the URL \"https://www.mpis.go.kr/corp/population.html\" and the text reads: \"국민안전처 희망이지 계속 장에 안내.\" Below this, there is a section titled \"국민안전처 대표 희망이지가 이용 중... 서비스 제공이 원활하지 않은 것 같습니다.\" which translates to \"National Safety Commission Assistance Center is currently... the service is not functioning well.\" There are additional instructions below, stating \"앞으로 안정적인 서비스 제공을 위해 최선을 다하겠습니다.\" which means \"We will strive for stable service provision in the future.\" The bottom of the screen has the logo of the National Safety Commission. There is no visible movement or action in this frame.",
"The current frame shows a woman wearing a white outfit speaking into a microphone. She appears to be addressing an audience, likely at a formal event or press conference. There is a man in a dark suit standing behind her, and the background features a blue and red color scheme, suggesting a formal setting, possibly related to government or official duties.",
"The current frame shows a woman wearing a white outfit speaking into a microphone. Behind her, a man in a dark suit is standing, but no text is visible in the image. The background consists of a blue and red color scheme, which could indicate a formal setting, possibly related to government or official duties.",
"The current frame shows a woman wearing a white outfit sitting at a table with a microphone in front of her. Behind her, there is a blue and yellow flag with intricate patterns, suggesting an official or governmental context. The woman appears to be speaking, and there is a caption in Korean below her.",
"The current frame shows a woman wearing a white shirt sitting at a table with a microphone in front of her. She is speaking, and there is a caption in Korean below her that reads \"철저히 대비해 주기를 바랍니다.\"",
"The current frame shows a woman wearing a white shirt seated at a table, with a microphone placed in front of her. The setting appears to be a formal meeting or conference room, as indicated by the formal attire of the individuals and the presence of a table with multiple people seated at it, focused on the speaker. There is no microphone visible in this frame, suggesting she is speaking without a microphone attached. The environment suggests a serious and official discussion or announcement.",
"A group of individuals is seen running in a hallway with wooden walls and white tiled floors. The scene appears to be indoors, possibly in a school or institutional building, as suggested by the attire of the people and the presence of an escalator to the left. The people are dressed in casual clothing, and their movement indicates urgency or haste.",
"A group of individuals is gathered in a classroom setting, where several students are seen actively engaging with their desks, possibly participating in a group activity or rehearsal. Some students are standing near the front of the room, with a few individuals holding objects that could be props or tools for the group activity. The classroom is equipped with typical desks and chairs, along with various stationery items. The atmosphere seems lively and interactive, suggesting a focus on group dynamics and collaboration."
] |
t8lY-rjy7-Y
|
A series of unrelated events are depicted in the video. The scene begins with a group of young women and children fleeing a staircase in a building, suggesting an emergency or urgent situation. This is followed by a physical altercation between young men in a classroom, which is intervened by a teacher. The setting then shifts to a train station platform at night, where a stationary train is visible, and a warehouse with stacks of boxes and shelving units, captured by a surveillance camera.
The video then cuts to a street scene at night with debris and caution tape, indicating a restricted area or incident. A person is later seen sitting on a bed, interacting with a small object in a casual indoor environment. The scene then shifts to a computer screen displaying a webpage with Korean text from the National Safety Commission, discussing service provision issues.
The final scenes depict a woman in a white outfit speaking at a formal event or press conference, with a man in a dark suit standing behind her. She is shown speaking into a microphone, sitting at a table with a flag and caption in Korean, and seated at a table in a formal meeting or conference room. The video ends with a group of individuals running in a hallway and a group of students engaging in a lively and interactive group activity in a classroom. Overall, the video appears to be a collection of unrelated scenes, each with its own unique context and setting.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=CXe6_CDrdB8",
"video_description": "찐♡기상청사람들 예고 없이 찾아오는 지진! 한 번 발생하면 큰 피해를 주는 지진이기에 감시하는 일은 한시도 소홀히 할 수 없습니다. 그 최전방에서... 1년 365일 24시간 지진화산 감시 및 분석 업무에 최선을 다해 신속·정확하게 알리고자 노력하는 사람이 있습니다. 지진화산 감시 및 분석 업무 9년 차... 반복되는 주간 근무와 야간 근무가 힘들긴 하지만, 누구보다 묵묵하게 자리를 지키고 있는 진득한 뚝배기 같은 지진업무의 대들보!! 지진화산 감시 업무를 담당하는 기상청 사람을 만나고 왔습니다.(^_^)v 우리나라에서 가장 강력했던 규모 5.8의 경주 지진 때 지진감시 및 분석을 수행했던 기상청 사람은 누구? 지진감시 업무를 들어올 때마다 긴장되는 기상청 사람은 누구? 국민의 안전을 누구보다 걱정하는 기상청 사람은 누구? 지진 올바로 알고 지진 발생 시 빠르게 대처하길 바라는 기상청 사람은 누구? 최근 지진 안전을 홍보해 주시는 지진희 배우님을 그 누구보다 고마워하는 기상청 사람은 누구? 만나볼까요 :) #기상청사람들 #지진화산 #행동하는파수꾼",
"video_id": "CXe6_CDrdB8"
}
| 16
|
[
"The current frame shows a person standing in front of a large screen displaying various data and text in a digital interface. The individual is wearing a blue shirt with an ID badge and a smartwatch. There is Korean text overlaid on the image, indicating the nature of the content related to the data displayed. The setting appears to be a professional environment, possibly an office or a meeting room.",
"The current frame shows a person sitting at a desk, working on a computer. The individual is wearing a blue shirt and appears to be focused on their work. On the desk, there are multiple monitors displaying various graphs, charts, and data visualizations. One of the monitors is particularly large, with a lot of detail and a gradient of colors, suggesting it might be showing an interactive or high-resolution graphical representation. There are several maps spread out on the desk, with different regions marked and detailed. The person is interacting with the computer, possibly analyzing or managing the data displayed on the screens. The environment seems to be a professional office or a technical workspace. The text overlaid on the image in this frame is in Korean and reads, \"일정 제모 이상 되면 통보하고,\" which translates to \"If the schedule exceeds, a notification will be sent.\"",
"The current frame shows a person standing in front of a large display screen that appears to be a stock market dashboard. The person is wearing glasses, a blue shirt, and a watch on their left wrist, suggesting they might be involved in financial or analytical work. The person's hands are clasped together in front of them, and the individual's posture indicates they are engaged with the information being displayed on the screen. The backdrop features a blue and yellow background, common in stock market display formats, with various charts and text that could be market data, news, or reports. The overall setting suggests a professional environment, likely related to finance or stock trading.",
"The current frame shows a street scene with a yellow line on the road, a black car parked on the side of the street, and a person on the sidewalk. There are no significant actions or interactions taking place. The environment appears to be a residential area with buildings in the background and parked cars lining the street.",
"The current frame displays a close-up view of a computer screen showing a graph with yellow and blue waveforms, indicating some form of data analysis or medical monitoring. The graph seems to be part of a larger data visualization, possibly related to blood pressure readings, as it is common in medical contexts. The background of the screen has a blue and yellow gradient, and there are text boxes and other graphical elements that suggest this is a professional or analytical environment.",
"The current frame shows three individuals in a professional setting, likely a control room, with two of them standing and one seated at a computer monitor. They appear to be engaged in a discussion or explanation regarding a technical issue or data output. The person seated at the computer monitor is actively gesturing, indicating an active role in the discussion. In the background, there are additional screens and equipment, suggesting a highly technical environment. The atmosphere is one of collaboration and focused attention on the task at hand.",
"The current frame shows two individuals in a professional setting, likely a control room. One person is standing and pointing at a computer monitor displaying a map, while the other person is seated at a desk with papers, a mobile phone, and a laptop. The standing person appears to be explaining or pointing out specific areas on the map on the computer screen. The seated individual is attentively observing the standing person and appears to be listening or responding to what is being said. The environment suggests a collaborative work setting, possibly related to geographical data or operational information. The background includes additional monitors and equipment, indicating a technical or data-driven context.",
"The current frame depicts an individual in a blue shirt standing in front of a large screen displaying numerous data points and graphs. The person is wearing a lanyard with an ID badge and a smartwatch on their left wrist. In the foreground, text appears on the screen, likely indicating a discussion or presentation context. The background is filled with various charts and graphs, suggesting a focus on data analysis or reporting. The setting seems to be an office or control room, indicated by the presence of multiple screens and technical equipment.",
"The current frame shows an individual wearing a blue shirt in front of a large screen displaying various data points and graphs. The person is standing with their arms slightly raised and is positioned in front of a backdrop filled with a multitude of charts and graphs. The setting appears to be an office or control room, indicated by the presence of multiple screens and technical equipment in the background. The overall context suggests a discussion or presentation focused on data analysis or reporting.",
"The current frame shows an individual wearing a blue shirt working at a computer station in an office environment. The person is sitting at a desk with a large monitor displaying a data analysis interface. Surrounding the computer are several smaller monitors and office equipment, including a telephone, keyboard, and mouse. The person appears to be engaged in data processing or analysis, possibly reviewing or entering information. The environment suggests a professional setting, likely a data analysis or reporting session, with other employees working in the background. The overall context indicates a focus on analytical tasks within an office workspace.",
"The current frame shows an individual in a blue shirt sitting at a desk working with multiple computer monitors displaying various data analysis interfaces. The person appears to be engaged in data processing or analysis, possibly reviewing or entering information. The office environment includes several smaller monitors and office equipment, including a telephone, keyboard, and mouse. The individual is surrounded by a professional setting, likely a data analysis or reporting session.",
"The current frame shows an individual in a blue shirt standing in front of a large screen displaying numerous numerical and graph data figures. The person is wearing a lanyard with an ID badge. The background consists of multiple monitors, which are showing detailed charts, graphs, and numerical data. The text in the image is in Korean and reads: \"업무 내내 강장모드... 지진 업무 담당자의 숫자이죠!\" and \"지진을 말하고 있는.\" This translates to \"Beware of prolonged work mode... The work responsible person's number is...\". The setting suggests a professional environment focused on data monitoring or reporting.",
"The current frame shows a person in a blue shirt standing in front of a large screen that displays numerous numerical and graph data figures. The individual is wearing a lanyard with an ID badge, indicating they might be a key participant in a professional setting. The background features multiple monitors, suggesting that the person is likely engaged in data monitoring or reporting. The text in the image, in Korean, translates to \"Be careful of prolonged work mode... The work responsible person's number is...\" This implies that the individual is addressing an issue related to prolonged work hours or a specific work-related person within a workplace.",
"The current frame features a person wearing a blue shirt, standing in front of a large screen that displays numerous numerical and graph data figures. The individual is making a fist, possibly indicating a strong or assertive gesture. To the right of the person, there is a speech bubble with a red heart symbol, which may suggest affection, approval, or a positive sentiment. The background includes multiple monitors, which indicate that the person might be involved in monitoring or reporting on data. The text in the image, in Korean, translates to \"Be careful of prolonged work mode... The work responsible person's number is...\" This implies that the individual is addressing a potential issue related to prolonged work hours or a specific work-related person within a workplace.",
"The current frame shows a person wearing a blue shirt sitting at a desk, focused on working on a computer. The individual is using a keyboard and appears to be engaged in some form of data analysis or monitoring. Multiple computer screens are visible in the background, displaying various graphs, charts, and numerical data. There is a speech bubble with a red heart symbol to the right of the person, suggesting a sentiment or emotion. Text in Korean in the background translates to \"Be careful of prolonged work mode... The work responsible person's number is...\" This indicates the person is addressing a potential issue related to prolonged work hours or a specific work-related person within the workplace.",
"The current frame shows a person wearing a blue shirt standing in front of multiple computer screens displaying numerical data and graphs. The individual is holding a device with a circular button and a wristwatch, suggesting a work-related context. The person appears to be focused and possibly addressing a task or explanation involving the data displayed on the screens. The text in the background is in Korean, indicating a communication or presentation context. The overall scene suggests a professional environment, possibly a workplace or office setting."
] |
CXe6_CDrdB8
|
The video appears to depict a professional setting, likely an office or control room, where individuals are engaged in data analysis, monitoring, and reporting. The main participant, a person wearing a blue shirt, is shown working at a computer, standing in front of large screens displaying various data and graphs, and interacting with colleagues in a collaborative environment. The context suggests a focus on technical or financial data, with screens showing stock market dashboards, maps, and numerical data. The individual is often seen wearing a lanyard with an ID badge and a smartwatch, indicating a professional or analytical role. Throughout the video, there are scenes of the person working alone, discussing issues with colleagues, and possibly addressing potential problems related to prolonged work hours or specific work-related tasks. The overall atmosphere is one of focus, collaboration, and attention to detail, with an emphasis on data-driven work and professional communication.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=uF3x63vtddc",
"video_description": "\"경주 지진, 지하수는 1~2일 전에 미리 알았다\" 지난 12일과 19일 경주에서 규모 5.8을 비롯한 대형 지진이 잇따라 발생하기 하루 이틀 전 주변 지하수 수위가 크게 상승해, 향후 지진예측에 활용할 수 있다는 주장이 나왔습니다. 정상용 부경대 지구환경과학과 교수는 진앙에서 가장 가까운 경북 경주시 산내면에 있는 지하수 관측소 자료를 분석한 결과, 이 같이 밝혔습니다. 자료를 보면 지난 11일 암반 지하수 수위는 하루 사이에 무려 49㎝ 상승했고, 17일에도 39㎝나 올라갔습니다. 정 교수는 지진에 앞서 암석에 강한 압력이 가해져 지하수 수위가 많이 올라간 것으로 보인다며, 규모 4.5 이상의 지진에만 영향을 받았다고 설명했습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "uF3x63vtddc"
}
| 16
|
[
"I'm sorry, but I cannot provide a description of the current frame as no frames were provided in the image you've sent. Please provide the image so I can assist you further.",
"I'm unable to provide a description of the current frame based on the image you've sent. Could you please provide the image or details about it?",
"I'm unable to provide a description of the current frame based on the image you've sent. Could you please provide the image or details about it?",
"The image shows a surveillance camera view of what appears to be a basement or a small enclosed area with walls and a floor. The room is filled with debris and rubble, indicating a recent collapse or an attempt at destruction. There is a large stone or concrete structure in the center, possibly a foundation or a part of the structure that was toppled. The surrounding area is littered with broken pieces, including a few scattered glass bottles and other debris. The lighting in the room is dim, and the overall scene suggests a chaotic and possibly dangerous situation.",
"The image depicts a nighttime street scene captured by a surveillance camera. The street is illuminated by streetlights and vehicle headlights, casting a yellowish glow on the road. There are several vehicles visible, including cars and possibly a van, moving or stationary. On the right side of the street, there are portable tents or structures with orange and white coloration, which are likely used for an event or gathering. The street appears to be closed off for a night event, as indicated by the absence of oncoming traffic and the lack of visible pedestrian activity. The surrounding environment is dark, with some faint lights from buildings or other sources in the background.",
"The current frame depicts a nighttime street scene. The street is illuminated by streetlights and vehicle headlights, casting a yellowish glow on the road. There are several vehicles visible, including cars and possibly a van, moving or stationary. On the right side of the street, there are portable tents or structures with orange and white coloration, which are likely used for an event or gathering. The street appears to be closed off for a night event, as indicated by the absence of oncoming traffic and the lack of visible pedestrian activity. The surrounding environment is dark, with some faint lights from buildings or other sources in the background.",
"The current frame shows an indoor scene captured by a security camera. The room appears to be a residential space, possibly a kitchen or dining area, with visible furniture such as a dining table and chairs. There are also some personal items on the table. The timestamp indicates it is around 09:35, and there is a visible news ticker at the bottom of the screen, displaying information in Korean.",
"The current frame shows an indoor setting with a focus on an air conditioning unit. The room appears to be a living or kitchen space, characterized by the presence of a dining table with some items on it, a mirror, and what seems to be a decorative wall piece or hanging ornament. There are no visible people or animals, and no significant movement is occurring in the frame. The timestamp at the bottom indicates it is around 09:35, and there is a visible news ticker at the bottom of the screen, also displaying information in Korean. The air conditioning unit is the central object in the frame, indicating a likely focus on climate control or energy efficiency, which are common topics in indoor air conditioning systems. There are no other notable objects or activities in the immediate vicinity.",
"The current frame shows an outdoor nighttime scene in a city street. There are no visible people or animals in the frame. On the right side of the image, there is a dark-colored car parked on the side of the street, facing the camera. In the background, there are a few additional vehicles, including one that is moving away from the camera. The street is lined with illuminated signs and shop fronts, typical of a commercial area. The atmosphere is dark, with artificial lighting from street lamps and vehicle headlights providing illumination. There are no signs of significant action or movement other than the presence of vehicles.",
"The current frame shows a nighttime scene on an urban street. There are no visible people or animals in the frame. On the right side of the image, there is a dark-colored car parked on the side of the street, facing the camera. In the background, there are a few additional vehicles, including one that is moving away from the camera. The street is lined with illuminated signs and shop fronts, typical of a commercial area. The atmosphere is dark, with artificial lighting from street lamps and vehicle headlights providing illumination. There is text on the screen indicating news commentary in Korean, which suggests that this footage is part of a news broadcast. The text overlay also provides additional context about the event being reported.",
"The current frame shows a white car parked on an urban street, viewed from an overhead perspective typical of CCTV footage. The car is facing the camera, and there are no visible people or animals in the frame. The street is illuminated by artificial lighting, and there are storefronts visible in the background, indicating a commercial area. The atmosphere appears to be dark due to the nighttime setting. There is no visible text overlay on this frame, which suggests that it is part of a news broadcast or related to a news story. The presence of text on the screen further implies that this footage is part of a news report.",
"The current frame shows a white car parked on an urban street viewed from an overhead perspective typical of CCTV footage. There are no visible people or animals in the frame. The street is illuminated by artificial lighting, and there are storefronts visible in the background, indicating a commercial area. The atmosphere appears to be dark due to the nighttime setting. There is no visible text overlay on this frame, which suggests that it is part of a news broadcast or related to a news story. The presence of text on the screen further implies that this footage is part of a news report.",
"The current frame depicts two individuals working on the roof of a traditional building. One person, wearing a pink top and dark pants, is standing on a roof rack, while the other, wearing a gray top and dark pants, is climbing the roof with an airbrush machine. The roof is made up of terracotta tiles and is part of a larger structure that appears to be part of a cultural or historical site. The scene suggests that the workers are engaged in maintenance or restoration work, possibly for the building's architectural or historical significance.",
"The current frame depicts two individuals working on the roof of a traditional building. One person, wearing a pink top and dark pants, is standing on a roof rack, while the other, wearing a gray top and dark pants, is climbing the roof with an airbrush machine. The roof is made up of terracotta tiles and is part of a larger structure that appears to be part of a cultural or historical site. The scene suggests that the workers are engaged in maintenance or restoration work, possibly for the building's architectural or historical significance.",
"The current frame shows two individuals engaged in roof maintenance work on a traditional building. One person is standing on a roof rack, wearing a pink top and dark pants, while the other person, wearing a gray top and dark pants, is climbing the roof with an airbrush machine. The roof is made up of terracotta tiles, and the overall scene suggests that the workers are involved in maintenance or restoration work, possibly for the building's architectural or historical significance.",
"The current frame shows two individuals engaged in roof maintenance work. One person, positioned on a roof rack, is wearing a pink top and dark pants. This person appears to be holding or adjusting some items on the roof rack. The other individual is wearing a light-colored top and dark pants, and is in the process of climbing the roof with an airbrush machine. The roof is composed of terracotta tiles, and the scene suggests that the workers are involved in maintenance or restoration work, possibly for the building's architectural or historical significance."
] |
uF3x63vtddc
|
The video appears to be a collection of unrelated scenes captured from various sources, including surveillance cameras and news broadcasts. The scenes depict different locations and activities, such as a damaged basement or enclosed area, a nighttime street scene with vehicles and portable tents, an indoor residential space, and an outdoor urban street with parked cars. Additionally, there are scenes of workers performing maintenance or restoration work on a traditional building's roof. The video also includes frames with text overlays in Korean, suggesting that it may be part of a news broadcast or report. Overall, the video seems to lack a coherent narrative, instead presenting a series of disparate scenes that may be related to news events, construction, or everyday activities.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=nln3QFJggKs",
"video_description": "106억 → 58억…경주 지진 피해금액 반토막 잇단 강진으로 100억원이 넘는 것으로 추정됐던 경주시의 공식 피해규모가 58억원 수준에 그치는 것으로 집계됐습니다. 경주시가 지진 발생 뒤 전수조사를 통해 발표한 잠정 추산 피해액은 약 107억원이었지만 사유재산 피해는 대부분 공식 피해액에서 빠졌습니다. 규정상 기와가 떨어지거나 벽체에 금이 가고 담장이 파손된 것은 재산피해 산정되지 않습니다. 이에 따라 사유재산 중에는 지진으로 주택이 완전히 부서지거나 반쯤 허물어진 것만 공식 피해액에 들어갔습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "nln3QFJggKs"
}
| 16
|
[
"The current frame shows two news anchors standing in front of a news studio backdrop. The backdrop features a map of South Korea, with one anchor on the left and the other on the right. Both anchors are wearing business attire; the anchor on the left has a dark suit and tie, while the anchor on the right is in a purple blazer and light pink blouse. On the left, there is a smaller text box with the number \"23\" and an orange logo with Korean characters. On the right, a graphic overlay of a map outline appears. The news ticker at the bottom includes some Korean text, with information about recent political developments in the country. The time displayed is \"17:02.\"",
"The current frame shows an aerial view of a sprawling urban area in South Korea, possibly a city. There are numerous buildings densely packed together, with green spaces interspersed among them. The landscape is expansive, indicating the city is not isolated. The weather appears cloudy, and the overall atmosphere suggests a busy, metropolitan environment. There are no visible people in the frame, focusing solely on the infrastructure and layout of the city. The location appears to be South Korea, as indicated by the text in the previous frame.",
"The current frame shows an aerial view of a sprawling urban area in South Korea, possibly a city. There are numerous buildings densely packed together, with green spaces interspersed among them. The landscape is expansive, indicating the city is not isolated. The weather appears cloudy, and the overall atmosphere suggests a busy, metropolitan environment. The text on the screen reads \"경주 4.5여진\" (경주 4.5 day) and \"106억 → 58억...경주 지진 공식 피해금액 반토포\". This suggests that the video is about the earthquake event in Gyeongju, South Korea, and the financial impact caused by the disaster.",
"The current frame shows a scene where a crane is lifting a large, rectangular object, which appears to be a building or structure. The crane is positioned above a grassy area with several vehicles, including a white truck and a black car, near a traditional-style building with a tiled roof. The sky is partly cloudy, and the overall setting suggests ongoing construction or demolition activities. There are no visible people or animals in the frame.",
"The current frame shows two individuals engaged in manual labor on a rooftop. One person, wearing a white hat, is handling what appears to be large, cylindrical objects, possibly containers or machinery, while the other person, wearing a red vest, is assisting in the process. The rooftop is covered with terracotta tiles and appears to be part of a traditional-style building. The scene suggests ongoing construction or maintenance activities.",
"The current frame shows a scene on the ground where a large number of tattered, black objects are scattered haphazardly. These objects are lying amidst debris, with some surrounded by grass and vegetation. The ground is uneven and littered, with patches of dirt and small rocks. The environment appears to be a construction site or an area affected by a natural disaster, as indicated by the debris and tattered materials.",
"The current frame shows a scene where a large number of black objects, resembling broken glass or debris, are scattered on the ground. These objects are surrounded by grass and vegetation, suggesting the scene might be from a construction site or an area that has experienced a natural disaster. The ground appears to be uneven and littered with dirt and small rocks. The area seems to be devoid of any human presence or movement, indicating it might have been intentionally left in this state for a while.",
"The current frame shows a scene with multiple individuals standing and conversing near a small, traditional-style building. One person is dressed in a plaid shirt and appears to be addressing the group. Surrounding this group are piles of stones or debris, suggesting recent construction or activity. The setting appears to be rural or semi-urban, with a traditional building and a rustic background.",
"The current frame shows a damaged building's interior with exposed wooden beams and a collapsed roof. The wooden beams are broken, and the ceiling is partially collapsed. The damage appears severe, indicating a recent collapse. The text at the top of the frame reads \"경주 4.5천㎡ 높한 시민들 식량 온입\" which translates to \"Gyeongju 4.5 thousand square meters of high-rises of citizens receiving food.\" The bottom text reads \"106억 -> 58억...경주 지진 공식 피해금액 반토막,\" meaning \"10.6 billion -> 5.8 billion...Gyeongju earthquake official damage compensation fund bankruptcy.\" The scene suggests a severe natural disaster, with the potential for widespread destruction and loss of life.",
"The current frame shows a man in a red cap and jacket cleaning a wall that is visibly damaged and peeling, revealing the interior of the structure. The man appears to be in the process of removing the damaged material from the wall. The wall's paint is severely peeling, exposing the underlying material, and there are black marks on the surface that suggest it has been in contact with some substance. The overall context of the scene suggests that the man is performing maintenance or repair work on the damaged building.",
"The current frame shows a damaged wall with a large crack. The wall's surface is visibly peeling, exposing the underlying material, which has black marks that suggest it has been in contact with some substance. There is a noticeable difference in the color and texture between the damaged and intact sections of the wall.",
"The current frame shows a road with significant cracks and uneven surfaces, highlighting the condition of the pavement.",
"The current frame shows a large crack in the pavement, likely from a heavy traffic event, with an area of significant damage. The crack is deep and has a dark, uneven surface, suggesting it has absorbed substantial weight. There are visible signs of distress, such as crumbling or weakening around the crack, indicating potential structural damage. The environment appears to be a section of a road, and the crack is the central focus of the image.",
"The current frame shows a large, deep crack in the pavement of a road. The crack is prominent, with significant weight being absorbed, indicating structural damage. The surroundings suggest an urban environment at night, with lights illuminating the area. There is a vehicle in the distance, providing context to the possible cause of the damage.",
"The current frame shows a narrow, dimly lit hallway with pink tiled walls. The camera is positioned low, positioned between the walls, capturing a ceiling with a single light source casting a warm glow. There is no visible movement or people in the frame. The focus is on the immediate surroundings, and the scene does not provide any immediate context or narrative beyond the hallway and the ceiling light.",
"The current frame displays a close-up view of a partially damaged wall with exposed red and green tiles. The tiles are crumbling and discolored, indicating a significant deterioration. The angle of the camera is low, positioned between the wall and the ceiling, which is visible at the top of the frame. There is a noticeable contrast between the red and green tiles, which are the only visible ones, and the white tiles that form the wall's base. The ceiling light source provides a warm glow, highlighting the texture and wear on the tiles. The wall's corner appears to be a bit elevated, suggesting that the tiles are affixed to the wall with screws or nails. There are no visible people or objects in the frame, focusing the viewer's attention solely on the damaged wall."
] |
nln3QFJggKs
|
The video appears to be a news report about a significant earthquake that occurred in Gyeongju, South Korea. The report begins with two news anchors introducing the topic, followed by aerial views of the affected city, showcasing its urban landscape and infrastructure. The footage then cuts to scenes of destruction and damage caused by the earthquake, including buildings with collapsed roofs, debris-filled streets, and cracked pavements. The video also shows individuals engaged in manual labor, likely involved in reconstruction or cleanup efforts. Additionally, there are scenes of people discussing and assessing the damage, as well as individuals performing repair work on damaged buildings. The report highlights the financial impact of the disaster, with text overlays indicating a significant reduction in the official damage compensation fund. Throughout the video, the focus is on the aftermath of the earthquake, with an emphasis on the destruction, repair efforts, and the human impact of the disaster.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=n6UmQ9Kw2GQ",
"video_description": "경주 지진 이후 여진 307회 발생…\"강도 약해져\" 지난 12일 저녁 발생한 규모 5.8의 경주 지진 탓에 여진이 307차례 발생한 것으로 집계됐습니다. 기상청에 따르면 오늘 오후 4시까지 경주 지진 이후 여진은 규모 1.5∼3.0도 292회 등 모두 307차례 발생했습니다. 기상청 관계자는 \"경주 지진 탓에 여진이 계속 발생하고 있지만 강도가 약해지고 있다\"며 \"앞으로 일어날 여진 규모는 3.0 이하로 예상되기 때문에 그렇게 우려하지 않아도 될 것 같다\"고 말했습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "n6UmQ9Kw2GQ"
}
| 16
|
[
"The current frame shows a news broadcast with two news anchors, one male and one female. The male anchor is wearing a traditional Korean hanbok and the female anchor is dressed in a floral Korean hanbok. They are positioned in front of a backdrop that includes a weather map, which appears to depict heatwave or extreme weather conditions. The text on the screen indicates that the news is about an event after the Prime Minister's resignation and an explosion at a gas station. The current frame does not contain any action or participants beyond the anchors and their backdrop.",
"The current frame shows a news broadcast with two news anchors, one male and one female, positioned in front of a weather map. The map displays a heatwave or extreme weather condition, indicated by red areas. The male anchor is wearing a traditional Korean hanbok with white trim and a necklace, while the female anchor is dressed in a floral traditional Korean hanbok. The news ticker at the bottom of the screen indicates that there has been a \"Prime Minister's resignation\" and an \"explosions at gas stations\" after 307 incidents. The temperature in the broadcast is displayed as 23.6 degrees Celsius.",
"The current frame shows a timestamped video from a surveillance camera in a room. The video is black and white, and there are two news anchors in the foreground, one male and one female. The male anchor is wearing a traditional Korean hanbok with white trim and a necklace. The female anchor is dressed in a similar hanbok. In the background, there are two individuals, one standing near a window and the other partially obscured. The room appears to be a living space with visible furniture. There is a visible calendar on the wall, with the date partially visible. The video includes text overlays in the upper right corner, indicating a news channel name, and a ticker at the bottom, which is not fully legible due to the resolution. The temperature is displayed as 24.7°C.",
"The current frame shows a kitchen scene where various kitchen utensils and appliances are visible. On the counter, there are multiple pots, pans, and a cutting board, suggesting food preparation. Above the counter, there are hanging pots and pans, indicating that the kitchen is used for cooking and food storage. To the left, a woman is holding a kettle, which is a common appliance used for boiling water. The kitchen appears to be well-equipped and tidy, with no visible signs of disarray.",
"The current frame shows a kitchen counter with various utensils and appliances. There are multiple pots, pans, and a cutting board on the counter. Above the counter, there are hanging pots and pans, and a red kettle is visible, which is likely used for boiling water. To the left, a woman is holding a kettle, which is a common kitchen appliance used for boiling water. The kitchen appears to be well-equipped and tidy, with no visible signs of disarray. The setting suggests that the kitchen is used for food preparation and storage.",
"The current frame shows a kitchen environment where a woman is holding a red kettle. The kitchen counter has various utensils and appliances, including pots and pans. Hanging above the counter are white lamps with intricate patterns. The wall is adorned with hanging lights, creating a warm ambiance. There is no visible water, suggesting the kettle has been used for boiling water, as inferred from the kettle being held and the absence of other boiling water sources. The setting is tidy and orderly, with no visible signs of disarray.",
"The current frame shows a kitchen environment where a woman is holding a red kettle. There is no visible water, suggesting that the kettle has been used for boiling water. The kettle is placed on the counter, and the kitchen counter appears to be cluttered with various utensils and appliances. The walls are decorated with hanging lights, and the setting is tidy and organized.",
"The current frame shows a kitchen environment where a woman is holding a red kettle. The kettle is placed on the counter, and there appears to be water inside, which is not visible due to the woman's gesture. The woman is standing in front of a wall adorned with hanging lights. The kitchen counter is cluttered with various utensils and appliances, but there is no visible water in the kettle.",
"The current frame shows a woman standing next to a baby crib. The crib is white with patterned bedding inside and appears to be in a storage area, possibly a laundry room or a baby changing station. The crib is situated next to a shelf with various items, including what seems to be baby supplies or clothing.",
"The current frame shows a baby in a crib, appearing to be in distress or discomfort. The crib has patterned bedding and is positioned next to a shelf with various items. There is no visible text in the current frame.",
"The current frame shows a plastic water bottle on a surface with a label indicating it is for a baby. There is a large container or jar with a reddish tint in the background. No text is visible in the current frame.",
"The current frame shows a scene from a television broadcast, where a potted palm plant is illuminated by a bright light source, creating a stark contrast with the surrounding darkness. The potted plant is centrally located in the frame. In the background, partially obscured, there appears to be a wall with some electronic equipment or machinery visible. The overall scene is dimly lit, with the potted plant being the primary source of illumination.",
"The current frame shows a television broadcast scene where a potted plant is being illuminated by a bright light source, creating a stark contrast with the surrounding darkness. The potted plant is centrally located in the frame, and the electronic equipment or machinery is partially obscured in the background. The overall scene is dimly lit, with the potted plant being the primary source of illumination.",
"The current frame shows a television broadcast scene where a potted plant is being illuminated by a bright light source, creating a stark contrast with the surrounding darkness. The potted plant is centrally located in the frame, and the electronic equipment or machinery is partially obscured in the background. The overall scene is dimly lit, with the potted plant being the primary source of illumination.",
"The current frame shows a television broadcast scene where a potted plant is being illuminated by a bright light source, creating a stark contrast with the surrounding darkness. The potted plant is centrally located in the frame, and the electronic equipment or machinery is partially obscured in the background. The overall scene is dimly lit, with the potted plant being the primary source of illumination.",
"The current frame shows a television broadcast scene with a potted plant centrally located in the frame. The potted plant is illuminated by a bright light source, creating a stark contrast with the surrounding darkness. The electronic equipment or machinery is partially obscured in the background, adding to the dimly lit environment. The overall scene is focused on the potted plant, with no other discernible activity or participants in the frame."
] |
n6UmQ9Kw2GQ
|
The video appears to be a news broadcast with two anchors, a male and a female, both wearing traditional Korean hanbok, discussing significant events including the Prime Minister's resignation and explosions at gas stations. The broadcast cuts to various scenes, including a kitchen where a woman is preparing food, a baby in a crib, and a television broadcast scene with a potted plant being illuminated. The video jumps between these different settings, with the news anchors providing context and information about the events unfolding. The kitchen scenes suggest a domestic setting, while the baby and potted plant scenes seem unrelated to the news broadcast. The overall context of the video is a news program covering current events, interspersed with unrelated domestic and television broadcast scenes.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=uoagwCVoHGM",
"video_description": "경주 지진으로 8명 부상…재산피해 253건 어제 저녁 경주 일대에서 발생한 지진으로 인해 8명이 다치고 카카오톡과 국민안전처 홈페이지 등 통신망이 일시적으로 마비되는 등의 장애가 있었습니다. 국민안전처는 경주 일대에서 오늘과 어제에 걸쳐 일어난 지진으로 인해 80살 여성 황 모 씨 등 8명이 경상을 입고 253건의 재산피해가 신고됐다고 밝혔습니다. 이번 지진으로 인해 KTX 대전~부산 구간이 5분가량 정차하기도 했습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "uoagwCVoHGM"
}
| 16
|
[
"The image depicts a news broadcast with a female news anchor standing in front of a large screen displaying a surveillance video of an area. The footage shows a flooded scene with water reaching up to the ground level. There are buildings visible in the background, indicating an urban setting. The anchor is holding a piece of paper and appears to be providing information or reporting on the scene shown on the screen. The news ticker at the bottom of the screen includes various Korean texts and information, likely related to the flood incident.",
"The current frame shows a news broadcast with a female news anchor standing in front of a large screen. The screen is displaying an image of a flooded area with water rising above the ground level. The flood appears to be covering a significant portion of the ground, indicating a substantial event. The background of the news broadcast includes a cityscape, suggesting the location of the flood incident is an urban area. The news ticker at the bottom of the screen contains various Korean texts and information, likely providing context or updates on the flood incident. The anchor is holding a piece of paper, which is likely used to refer to the footage displayed on the screen during the broadcast.",
"The current frame shows a news broadcast with a female news anchor standing in front of a large screen. The screen is displaying an image of a flooded area with water rising above the ground level, indicating a substantial flood. The flood appears to be covering a significant portion of the ground, and the camera angle suggests it is being monitored from a building. The background of the news broadcast includes a cityscape, reinforcing the urban location of the flood incident. The news ticker at the bottom of the screen contains various Korean texts and information, likely providing context or updates on the flood incident.",
"The current frame depicts a surveillance camera view of an underground tunnel or passageway. There are no visible human subjects or animals, and the environment appears to be an abandoned or possibly historical underground setting. The tunnel has a rough, concrete appearance with some debris and debris on the floor. The lighting suggests either early morning or late afternoon, with the sky appearing overcast. The timestamp on the camera reads \"14:57\", and the text at the bottom of the screen is in Korean, indicating that the footage is from a news broadcast.",
"The current frame shows a close-up view of a white surface with some reflection and slight dirt marks. The camera angle is low, providing a perspective of the surface without revealing much detail about the surroundings or objects on or around it. There are no visible human subjects or animals, and no text or additional context is present in the frame. The background is indistinct due to the close-up perspective and lighting conditions.",
"The current frame shows a close-up view of a large, rectangular structure with a metallic appearance. The surface of the structure is smooth and reflective, with some light reflecting off its surface. There are no visible people, vehicles, or other objects in the frame. The background is dark, making it difficult to discern any additional details about the surroundings.",
"The current frame shows a man wearing gloves and holding a small object, possibly a tool or a device, in his hands. He appears to be interacting with something off-frame to his right. The man is standing in front of a display table filled with various items, including what looks like clothing and other accessories. The table is situated in what appears to be a retail store, as suggested by the presence of clothing racks and products. The overall scene suggests that the man might be performing some kind of maintenance or inspection task, possibly related to the items on the display table.",
"The current frame shows a person wearing colorful shoes and gloves, holding a broom-like tool with a green handle and an orange head. The person is standing on a tiled floor, seemingly sweeping or cleaning. In the background, a wooden table is partially visible, indicating that the setting might be indoors, possibly in a kitchen or dining area. There is no visible text or additional context in the image to provide further details.",
"The current frame shows a person wearing a yellow jacket and black pants, standing in an indoor setting with a tiled floor. The individual is holding a broom-like tool with a green handle and an orange head. In the background, there are several pieces of furniture, including a black chair and a brown sofa. The person appears to be engaged in some activity related to sweeping or cleaning, although the exact nature of their task is not clear from the image. The setting is likely a living room or dining area, given the presence of the furniture.",
"The current frame shows a person wearing a yellow jacket and black pants standing in an indoor setting with a tiled floor. The individual is holding a green-handled broom-like tool. In the background, there are several pieces of furniture, including a black chair and a brown sofa. The setting appears to be a living room or dining area. The video likely depicts a cleaning or maintenance task being performed, focusing on the interaction between the person and the broom.",
"The current frame shows a person wearing a striped sweater and a collared shirt, standing in front of a beige curtain. The individual appears to be reaching towards the curtain with one hand. The focus of this scene is on the curtain, suggesting that the person is either adjusting it or interacting with it. There are no visible people, objects, or text in the current frame, and no background details are provided.",
"The current frame shows a close-up of a person's chest, revealing a visible crack or tear in the skin. The background is blurred and predominantly light-colored, making the detailed texture and the crack stand out clearly. There is no visible human figure, objects, or text in this frame.",
"The current frame shows a close-up of a person's chest, revealing a visible crack or tear in the skin. The background is blurred and predominantly light-colored, making the detailed texture and the crack stand out clearly. There is no visible human figure, objects, or text in this frame.",
"The current frame shows a person walking on a corridor with a blurred background. The person appears to be wearing a dark-colored jacket, with their face partially obscured by shadow. The corridor is dimly lit, and the overall atmosphere is somewhat mysterious due to the blurred background. The focus is primarily on the person's movement and attire.",
"The current frame shows an indoor setting that appears to be a train station. The scene is bustling with activity as people move through the area, some walking towards the camera and others moving away. A glass entrance door is prominent in the center, suggesting it leads to a boarding or waiting area. The lighting is bright and artificial, illuminating the entire scene. There are several people visible, including a couple who seem to be in conversation, and others walking briskly. The background includes signage and advertisements, indicating commercial establishments within the station. There is no significant change in the environment or actions, maintaining a continuous flow of movement.",
"The current frame shows a man walking towards a woman in a hallway. The man is wearing a dark t-shirt and dark pants, and the woman is dressed in a black jacket and a white top. They are walking past an elevator. The hallway appears to be indoors, and there are doors and walls visible. The text overlay at the bottom of the image indicates a news segment from \"KBS 23\" with a timestamp of 14:58."
] |
uoagwCVoHGM
|
A news broadcast is reporting on a significant flood incident in an urban area, displaying surveillance footage of the flooded scene. The news anchor provides information and context, with a news ticker at the bottom of the screen offering updates in Korean. The footage then cuts to various unrelated scenes, including an abandoned underground tunnel, a close-up of a white surface, a metallic structure, and a person performing maintenance or inspection tasks in a retail store. The video also shows individuals engaged in cleaning activities, such as sweeping, in different indoor settings, including a living room or dining area. Additionally, there are scenes of people interacting with their environment, like adjusting a curtain, and close-ups of a person's chest with a visible crack or tear in the skin. The video then shifts to show a person walking in a corridor, followed by a bustling train station scene with people moving through the area. Finally, it depicts a man and a woman walking towards each other in a hallway, with the scene being part of a news segment from "KBS 23". Overall, the video appears to be a collection of disparate scenes, with the initial focus on a flood incident, followed by a series of unrelated events and settings.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=5p1N4MtudiI",
"video_description": "경주 지진 316회 이어가다 현재는 '잠잠' 지난 12일 발생한 규모 5.8의 경주 지진의 여진이 316회 발생한 것으로 집계됐습니다. 기상청은 오늘 오전 11시 기준 여진 횟수가 316회라고 발표했습니다. 규모별 횟수는 1.5에서 3.0이 301차례, 3.0에서 4.0은 14차례, 4.0에서 5.0은 1차례 감지됐습니다. 사흘째 계속된 여진은 일단 멈추는 징후를 보이고 있는 것으로 기상청은 파악하고 있습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "5p1N4MtudiI"
}
| 16
|
[
"The image shows a news broadcast with two presenters, one male and one female, sitting in front of a cityscape backdrop. Both presenters are dressed in traditional Korean hanbok. The background features a bridge, a river, and urban buildings. The weather is indicated as 26.7°C. The news ticker at the bottom of the screen reads \"경주 지진 316회 이어가다 현재는 잠점\" which translates to \"The 316th earthquake in Gyeongsang Province is ongoing, Ko Jae is a restaurant.\"",
"The current frame depicts two presenters, one male and one female, dressed in traditional Korean hanbok, sitting in front of a backdrop of a cityscape featuring a bridge over a river, urban buildings, and a cloudy sky. The weather is shown as 26.7°C. A news ticker at the bottom of the screen reads, \"경주 지진 316회 이어가다 현재는 잠점.\"",
"The current frame depicts a news broadcast featuring a split-screen display. On the left side of the screen is a map, and on the right side, there are detailed weather radar overlays showing multiple weather phenomena. The map indicates the geographical extent of a coastal area with marked locations and routes. The weather radar on the right side displays various weather patterns, including storms and severe weather conditions, indicated by concentric circular patterns and other weather indicators. The overall context suggests a news report about a significant weather event, with mentions of earthquake 316 and references to Japan.",
"The current frame shows a split-screen display of a news broadcast. On the left side, there is a map indicating the geographical extent of a coastal area, marked with various locations and routes. On the right side, there are detailed weather radar overlays showing multiple weather phenomena, including storms and severe weather conditions, indicated by concentric circular patterns and other weather indicators. The text overlay on the right side of the screen provides additional context, mentioning the event number 316, the location of the event, and possibly some geographical or procedural details about the broadcast. The overall scene suggests a news report about a significant weather event, focusing on the geographical and temporal specifics of the incident.",
"The current frame shows a static image with a close-up view of a map. The map displays a detailed and colorful representation of a coastal area, with various geographical features marked on it. The colors used in the map include red, blue, green, and yellow, likely to represent different types of geographical locations or boundaries. The image also features satellite or aerial views of the map, indicating the scale and spatial arrangement of the areas shown. The background behind the map is a darker shade, likely to provide contrast and emphasize the map itself. The text overlay at the bottom right corner of the screen appears to be a news ticker or title, providing additional context about the event, possibly related to weather or environmental conditions in the coastal area.",
"The current frame displays a highly pixelated and blurry image, making it difficult to discern specific details. The image appears to be either a digital glitch or a corrupted visual representation, as it lacks clarity and context. There are no discernible geographical features, people, or actions identifiable from the current frame alone. The primary elements include the image itself and the noise or distortion, which suggests it has not been processed or displayed correctly. The lack of clarity prevents accurate interpretation of the scene.",
"The current frame shows an individual working at a computer desk. The person is focused on a computer screen, using a keyboard and mouse. The screen displays multiple windows, with text and graphics visible. The surrounding environment includes additional computer monitors and what appears to be a cluttered workspace. The overall setting suggests a professional or work-related environment, with a focus on digital or technical work. There are no visible signs of distress or urgency, indicating a calm or routine work scenario.",
"The current frame shows an individual at a computer desk, working on a computer. The person is focused on a screen displaying multiple waveforms, which could be related to audio or medical data. The environment appears to be a typical work or study setting, with a neat workspace. There are no visible signs of distress or urgency, indicating a calm or routine work scenario.",
"The current frame shows a person seated at a computer desk, working on a computer. The individual appears to be focused on a screen displaying multiple waveforms, which could be related to audio or medical data. The environment seems calm and routine, with a typical work or study setting, and there are no visible signs of distress or urgency.",
"The current frame shows a monitor displaying a map with weather-related information. The map is divided into two segments, each containing different types of weather patterns. The top segment shows a region with green weather markers, which may indicate high precipitation or clear weather, while the bottom segment displays yellow weather markers, suggesting a change in weather conditions, such as moving storms or heavy precipitation. The text overlay on the screen reads \"경주 지진 316회 이야기가다 현재는 '잠참'',\" which translates to \"The 316th earthquake in Jeju is about to stop.\" This suggests that the focus of the video is on the Earthquake 316th and its impact on Jeju Island.",
"The current frame shows a computer monitor displaying a map, specifically focusing on the geographical area around Jeju Island. The map is divided into two sections, with the top section displaying green weather markers indicating areas of high precipitation or clear weather, and the bottom section showing yellow weather markers suggesting a change in weather conditions, such as moving storms or heavy precipitation. The bottom text overlay reads \"경주 지진 316회 이야기가다 현재는 '잠참',\" which translates to \"The 316th earthquake in Jeju is about to stop.\" This suggests that the monitor is showing the situation after a significant earthquake, and the focus is on the effects and progression of the quake on Jeju Island.",
"The current frame shows a map with multiple circular markers, each colored yellow and orange, indicating various levels of severity or impact. The yellow markers are densely packed in several areas, suggesting a high level of concern or impact, while the orange markers are spread out, indicating a more spread-out issue. The map is divided into two sections: a green area with green weather markers, and a blue area with blue weather markers. The blue section has text overlay that reads \"연합뉴스TV 고속도로에 사상자 사망 1인,\" which translates to \"Excessive casualties reported on the highway, 1 person deceased.\" This suggests a news story about a high number of casualties due to an incident on a highway. The overall context of the current frame seems to be about the aftermath of an earthquake, as indicated by the yellow and orange markers on the map.",
"The current frame shows a map with multiple circular markers, each colored yellow and orange. The yellow markers are densely packed in several areas, suggesting a high level of concern or impact. In contrast, the orange markers are spread out, indicating a more spread-out issue. The map is divided into two sections: a green area with green weather markers, and a blue area with blue weather markers. The green section has text overlay that reads, \"연합뉴스TV 고속도로에 사상자 사망 1인,\" which translates to \"Excessive casualties reported on the highway, 1 person deceased.\" This suggests a news story about an incident on a highway involving high numbers of casualties.",
"The current frame shows a map with multiple circular markers, some colored yellow and some colored orange. The yellow markers are densely packed in several areas, suggesting a high level of concern or impact. The orange markers are spread out, indicating a more spread-out issue. The map is divided into two sections: a green area with green weather markers, and a blue area with blue weather markers. The green section has text overlay that reads, \"연합뉴스TV 고속도로에 사상자 사망 1인,\" which translates to \"Excessive casualties reported on the highway, 1 person deceased.\" This suggests a news story about an incident on a highway involving high numbers of casualties.",
"The current frame displays a digital screen showing a temperature reading of 89 degrees, indicated by the large number on the screen. This temperature is part of a larger context provided in the lower part of the image, which mentions \"경주 지진 316회 이어가다 현재는 '잠참'\" (This is the 316th earthquake since the 316th episode, currently in a 'pause'). The text includes \"경주 지진 316회 이어가다 현재는 '잠참'\" (This is the 316th earthquake since the 316th episode, currently in a 'pause') and mentions a temperature of \"27.2°C\". The image also includes a news ticker with additional information about the weather and time. The top right corner of the image displays a logo and text that reads \"연합뉴스TV\" and \"국회법안 발의 2천 건 돌파 동원\", indicating the news source and a related news event.",
"The current frame displays a digital screen showing a temperature reading of 27.2°C. This temperature is part of a larger context provided in the lower part of the image, which mentions \"경주 지진 316회 이어가다 현재는 '잠참'\" (This is the 316th earthquake since the 316th episode, currently in a 'pause'). The text includes \"경주 지진 316회 이어가다 현재는 '잠참'\" (This is the 316th earthquake since the 316th episode, currently in a 'pause') and mentions a temperature of \"27.2°C\". The image also includes a news ticker with additional information about the weather and time. The top right corner of the image displays a logo and text that reads \"연합뉴스TV\" and \"국회법안 발의 2천 건 돌파 동원\", indicating the news source and a related news event."
] |
5p1N4MtudiI
|
The video appears to be a news broadcast focusing on a significant earthquake event, specifically the 316th earthquake in Gyeongsang Province, with some frames mentioning Jeju Island. The broadcast features two presenters dressed in traditional Korean hanbok, presenting in front of a cityscape backdrop. The news ticker and text overlays provide updates on the earthquake's status, mentioning it is ongoing or about to stop, and report on related incidents such as casualties on a highway. The video also includes maps, weather radar, and satellite imagery to provide geographical and weather context. Additionally, there are frames showing individuals working on computers, possibly monitoring the situation or analyzing data related to the earthquake. The overall context suggests a breaking news report on the earthquake and its aftermath, with a focus on providing updates and information to the public.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=roaxxb8zRLU",
"video_description": "국제신문 뉴스&이슈 구독하기 http://goo.gl/FFQL4 국제신문 근교산&기획특집 구독하기 http://goo.gl/SM0fM 국제신문 기사보기 http://iii.im/pk3Z 국제신문 영상팀이 경주 지진피해 복구 현장을 드론으로 담았다.",
"video_id": "roaxxb8zRLU"
}
| 16
|
[
"The current frame shows a traditional Korean village with numerous black-tiled roofs. In the foreground, there is a large red object, which appears to be a balloon or a piece of fabric. The background reveals a wide array of traditional Korean houses with sloping roofs, set against a backdrop of mountains and a partly cloudy sky. The text \"하늘에서 본 경주\" (Heul-eomseye) is visible at the top, while \"9.24일 토요일 경주시 황남동 일대\" (9.24th, Wednesday, Chuseok, Haeam-nam-dong, Il-dae) is displayed at the bottom.",
"The current frame shows a traditional Korean village with numerous black-tiled roofs. The focus is on the architectural elements, which include sloping roofs and the layout of the homes. In the foreground, there is a large red object, which appears to be a piece of fabric or a balloon. The background reveals a wide array of traditional Korean houses with similar sloping roofs, set against a backdrop of mountains and a partly cloudy sky. The text \"하늘에서 본 경주\" (Heul-eomseye) is visible at the top, and \"9.24일 토요일 경주시 황남동 일대\" (9.24th, Wednesday, Chuseok, Haeam-nam-dong, Il-dae) is displayed at the bottom.",
"The current frame shows a traditional Korean village with numerous black-tiled roofs. The focus is on the architectural elements, particularly the sloping roofs, which are a hallmark of traditional Korean architecture. In the foreground, there is a large red object, which appears to be a piece of fabric or a balloon. The background reveals a wide array of traditional Korean houses with similar sloping roofs, set against a backdrop of mountains and a partly cloudy sky. The text \"하늘에서 본 경주\" (Heul-eomseye) is visible at the top, and \"9.24일 토요일 경주시 황남동 일대\" (9.24th, Wednesday, Chuseok, Haeam-nam-dong, Il-dae) is displayed at the bottom.",
"The current frame shows a traditional Korean village with multiple black-tiled roofs, highlighting the characteristic sloping roofs of Korean architecture. In the foreground, a large piece of blue fabric or plastic is prominently displayed on the roof, contrasting with the gray tiles. The background reveals a dense collection of these traditional houses, each with their own distinctive sloping roofs. The setting appears to be a well-organized urban area, possibly a residential or commercial district. The text \"하늘에서 본 경주\" (Heul-eomseye) is visible at the top of the frame, suggesting the title or theme of the video, while \"9.24일 토요일 경주시 황남동 일대\" (9.24th, Wednesday, Chuseok, Haeam-nam-dong, Il-dae) at the bottom indicates the location and date of the event, which is likely related to the Korean traditional festival or celebration.",
"The current frame shows an aerial view of a traditional Korean village with multiple black-tiled roofs. The roofs are sloping, and the structure appears to be part of a larger community area. A crane is lifting a large piece of blue fabric or plastic from the roof, indicating construction or maintenance work. The background reveals more traditional houses with similar sloping roofs, suggesting a well-organized urban area. The text \"하늘에서 본 경주\" (Heul-eomseye) is visible at the top of the frame, likely serving as the title or theme of the video. At the bottom, \"9.24일 토요일 경주시 황남동 일대\" (9.24th, Wednesday, Chuseok, Haeam-nam-dong, Il-dae) is displayed, providing the location and date of the event.",
"The current frame shows a construction scene with multiple workers on a rooftop, actively engaged in building or maintenance activities. The sky is clear, and no specific time of day is evident. The surrounding area includes other buildings, tents, and green areas, indicating a communal or urban setting. The text \"하늘에서 본 경주\" (Heul-eomseye) is visible at the top of the frame, suggesting that the video might be about a local event or construction in the village.",
"The current frame shows two workers on a rooftop, working together to construct or secure a green mesh netting. One worker, dressed in black, is on a red lift, while the other, wearing a yellow jumpsuit and a cap, is assisting from below. They are handling the green netting, which is spread out on the rooftop. The background includes a clear sky and some buildings, indicating an outdoor construction or maintenance activity in a town or village setting.",
"The current frame shows a group of workers on a rooftop, working together. One worker, wearing a yellow vest, is handling a blue tarp, which is spread out on the roof. Another worker, also in a yellow vest and wearing a hard hat, is assisting from below, possibly securing or adjusting the tarp. The worker in the yellow vest is standing near the roof tiles, and the worker in the hard hat is holding a tool or device above the tarp. The background includes more rooftop tiles and a cloudy sky, indicating an outdoor activity, likely related to construction or maintenance work. There are no other significant visual elements present.",
"The current frame shows a group of workers on a rooftop, engaged in some form of maintenance or construction activity. One worker, wearing a white hard hat and a dark vest, is seated on the roof, appearing to focus on the task at hand. Another worker, also in a white hard hat and dark clothing, is standing near the roof tiles, possibly assisting or observing. The background features a dense arrangement of green bamboo, suggesting a garden or natural setting. The roof itself is partially covered with tiles, and there is a colorful, intricate wooden structure visible in the upper part of the frame, hinting at traditional or culturally significant elements. The overall scene suggests an ongoing effort to maintain or restore the roofed area.",
"The current frame shows a group of people on a grassy field, possibly a park, engaging in an activity. A couple of individuals appear to be walking or moving around. There is no visible activity or interaction between the people. The setting is an open space with open grassy areas and walking paths, and there are no structures or objects in the immediate vicinity.",
"The current frame shows a tall, cylindrical stone tower situated within a circular grassy area, surrounded by a paved walkway. There are a few people walking around the tower and on the path. The setting appears to be a public park or a similar recreational area. The tower is the central focus of the image, with the circular grassy area enclosing it. The individuals are scattered around the tower and pathway, indicating some level of activity or visitation. The environment is well-maintained and green, with a clear delineation between the grassy area and the paved walkway. No significant changes in the environment or the tower's position can be observed from this point in the image.",
"The current frame shows an aerial view of a rural area with a building adjacent to a road. The building has a blue roof and appears to be a school or community center. The surrounding landscape consists of green fields and patches of trees, indicating a countryside setting. The road is well-maintained and curves around the area, suggesting accessibility and connectivity. There is no visible activity or movement, and the overall scene is static.",
"The current frame shows an aerial view of a rural area with a prominent red circular marker in the center. Surrounding the red marker, there are smaller red markers scattered across the landscape, suggesting a network of target locations. A well-maintained road is visible in the foreground, curving around the area, and extends into the background. The surrounding landscape includes green fields and patches of trees, indicating a countryside setting. There are no visible people or moving vehicles, and the overall scene remains static.",
"The current frame shows a rural area with a red, looping object that resembles a speedboat or a hyperloop-like structure in motion. This red object is situated above the ground, curving through the landscape. Surrounding the red object are green fields and patches of trees, indicating agricultural or natural land use. A body of water or large pond can be seen on the right side of the frame. The background is slightly cloudy, suggesting variable weather conditions. The image does not include any people or moving vehicles.",
"The current frame shows a red, looping object, which appears to be a hyperloop or a similar type of transportation vehicle, traveling through the air over a rural landscape. The object is curving over the ground, suggesting it is in motion. Surrounding the red object are fields, patches of trees, and a body of water or large pond on the right side. The background is slightly cloudy, indicating variable weather conditions. No people or moving vehicles are visible in this frame.",
"The current frame shows a logo with a prominent \"K\" inside a blue square with rounded corners, against a black background. Below the logo, the Korean text \"국제신문\" is displayed, followed by \"KOOKJE SHINMUN\" in smaller white text."
] |
roaxxb8zRLU
|
The video appears to depict a traditional Korean village with numerous black-tiled roofs, set against a backdrop of mountains and a partly cloudy sky. The scene shows various stages of construction or maintenance work, with workers on rooftops, handling fabrics, netting, and tarps. The video also features aerial views of the village and surrounding countryside, showcasing the architecture, roads, and natural landscapes. Additionally, there are scenes of people walking in a park, visiting a stone tower, and a rural area with a building and a road. The video also includes unusual elements, such as a red, looping object resembling a hyperloop, traveling through the air over a rural landscape. The text overlays provide context, including the title "하늘에서 본 경주" (Heul-eomseye), and the location and date "9.24일 토요일 경주시 황남동 일대" (9.24th, Wednesday, Chuseok, Haeam-nam-dong, Il-dae), suggesting a connection to a Korean traditional festival or celebration. The video concludes with a logo, "국제신문" (KOOKJE SHINMUN), which may indicate the video's source or affiliation. Overall, the video presents a mix of traditional Korean culture, construction, and innovative technology, set against the backdrop of a rural Korean landscape.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=3ojHTwrvx90",
"video_description": "박 대통령, 경주 지진현장 방문 \"특별재난지역 선포\" 박근혜 대통령은 최근 강진이 잇따라 발생한 경북 경주 지역을 찾아 특별재난지역 선포를 적극 검토하라고 지시했습니다. 이어 지진 등 재난 안전 시스템을 원점에서 재점검할 것도 주문했습니다. 박 대통령은 아울러 인근 월성 원자력발전소를 찾아 \"원전은 단 한치의 실수도 용납되지 않는다\"며 지진 방재대책을 철저히 재점검해달라고 당부했습니다. 박 대통령의 지시에 국민안전처 또한 경주시를 특별재난지역으로 선포할 예정입니다. 특별재난지역으로 지정되면 지자체의 피해 복구비 부담이 완화되고, 피해 주민들은 공공요금 감면혜택을 받게됩니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "3ojHTwrvx90"
}
| 16
|
[
"The current frame features a news broadcast on Alibek TV. It shows a studio setting with two news anchors, a male and a female, seated in front of a background displaying a crowd of people. The male anchor is dressed in a suit with a red tie, while the female anchor wears a gray blazer. Both are facing the camera. Behind them, a diverse group of people is gathered, some of whom are taking photos or recording the event. The studio background includes a logo at the top left corner and a news ticker at the bottom right corner. The ticker includes text in Korean and mentions a news story about \"Park Dae-myung, Geum du-hye-han's address to the National Assembly\" on December 12. The overall atmosphere is that of a live broadcast with a focus on community engagement and political discourse.",
"The current frame shows a group of people outdoors, dressed in yellow jackets, walking together. They appear to be part of a coordinated event or group movement. In the background, there is a white van and various other people, possibly organizers or participants. The setting seems to be a street or a public area with buildings in the distance. The atmosphere is casual, and the participants seem focused on their movement.",
"The current frame shows a group of people dressed in yellow jackets walking together. They appear to be in a coordinated group, possibly a team or a campaign, given their matching attire. The background features a white van and several other individuals who seem to be participants or organizers. The setting appears to be outdoors, on a street or in a public area, with buildings in the distant background. The atmosphere is casual, and the individuals seem focused on their movement.",
"The current frame shows a group of people dressed in yellow jackets standing in a line. The individuals appear to be part of a coordinated group or movement, possibly during a public event or gathering. The background includes a white van and other people, suggesting they might be part of an organized event or protest. The setting appears to be outdoors, and the atmosphere is one of unity and purpose. The image does not contain any visible text.",
"The current frame shows a group of people dressed in yellow jackets standing in a line. They are positioned in front of a building covered with a blue tarp, suggesting some form of construction or renovation work. The individuals appear to be part of a coordinated group or movement, possibly during a public event or gathering. The background includes other people, suggesting a larger group is present. The scene suggests an organized activity, such as a protest or community event. There are no visible texts or banners in the image, and the overall atmosphere is one of unity and purpose.",
"The current frame shows a group of people dressed in yellow jackets standing together in a line, facing a camera. They are positioned in front of a white fence and a building with a blue tarp covering its roof. There are no visible texts or banners in the image. The overall atmosphere suggests a coordinated group or movement, possibly during a public event or gathering.",
"The current frame shows a group of people dressed in yellow jackets standing together in a line, facing a camera. They are positioned in front of a white fence and a building with a blue tarp covering its roof. The overall atmosphere suggests a coordinated group or movement, possibly during a public event or gathering.",
"The current frame depicts a group of individuals dressed in yellow jackets standing in a line outdoors. They appear to be engaged in a group activity or gathering, possibly during a formal event or ceremony. The setting includes a white fence in the background, and the group is positioned in front of a building with a blue tarp on its roof. The attire of the individuals suggests they are part of an organized group or institution. The overall mood of the image is one of unity and purpose, with no visible signs of dynamic movement or interaction with other participants.",
"The current frame shows a group of individuals, mostly dressed in yellow jackets, standing in a line outdoors. They appear to be engaged in a formal or ceremonial activity, possibly related to a political or governmental event. The setting includes a white fence in the background and a blue tarp on the roof of a building. The individuals are likely part of an organized group or institution, as indicated by their uniform attire. The overall mood suggests a sense of unity and purpose, with no visible dynamic movement or interaction with other participants in the frame.",
"The current frame depicts a man dressed in a yellow jacket standing next to another individual holding a piece of paper or a poster. They are positioned outdoors, with a building and a door visible in the background. The man in the yellow jacket appears to be speaking or interacting with the person holding the paper. The setting suggests a formal or official event, with the attire of the individuals indicating a professional or governmental context. The overall mood is one of engagement or communication.",
"The current frame shows a group of people wearing yellow jackets standing outdoors. They appear to be engaged in a discussion or presentation, as one person is gesturing with their hands while another is holding a piece of paper or a poster. The group is composed of both men and women, and they are gathered in what looks like a formal setting, possibly a meeting or a conference. The background includes a building and a door, indicating an institutional or governmental location. The individuals' attire, with their yellow jackets, suggests a uniform or organizational group, which is consistent with the context of the event.",
"The current frame shows a group of people wearing yellow jackets standing outdoors. They appear to be engaged in a formal or semi-formal gathering. One person is gesturing with their hands while another is holding a piece of paper or a poster. The group consists of both men and women, and they are gathered in what looks like a formal setting, possibly a meeting or a conference. The background includes a building and a door, indicating an institutional or governmental location. The individuals' attire, with their yellow jackets, suggests a uniform or organizational group, which is consistent with the context of the event. The overall atmosphere appears to be one of focused discussion or presentation.",
"The current frame shows a group of individuals, all dressed in yellow jackets, standing closely together outdoors. The focus is on the central figure who is slightly out of focus and appears to be in mid-speech or discussion. The expressions and body language suggest a serious and composed demeanor. In the background, there are additional people, but their faces are not visible. The setting appears to be a formal or semi-formal gathering, possibly a press conference or a meeting, indicated by the uniforms and the presence of a microphone. The overall atmosphere is one of unity and attentiveness.",
"The current frame shows a group of individuals, all dressed in yellow jackets, standing closely together outdoors. The focus is on a central figure who appears to be speaking or addressing the group. The expressions and body language suggest a serious and composed demeanor. The setting is an outdoor event, likely a press conference or a meeting, as indicated by the formal attire of the individuals and the presence of a microphone. The overall atmosphere is one of unity and attentiveness. The timestamp in the bottom left corner indicates the time as 08:50, and there is a news ticker at the bottom of the screen providing additional context.",
"The current frame shows a group of people, all wearing yellow jackets, walking along a street. They are gathered in a line formation, walking away from the camera. The scene suggests a coordinated group activity or a group walking for a purpose. There is no central figure or focal point within the group, indicating that they are all part of the same group. The attire of the individuals is consistent with a uniform, and the setting appears to be outdoors during daytime. The group is walking towards the left side of the frame.",
"The current frame depicts a group of people, all wearing yellow jackets, walking along a street. They appear to be part of a coordinated group activity, as they are walking in a line formation. The setting is outdoors during daytime, and the group is moving away from the camera. No central figure or focal point is evident within the group, suggesting unity and focus on the collective activity. The attire of the individuals is consistent with a uniform, and the overall scene suggests a planned movement, possibly for a public or organizational event."
] |
3ojHTwrvx90
|
The video appears to depict a coordinated group event or movement involving individuals dressed in yellow jackets. The event seems to be related to a political or community gathering, with the group walking together in a line, standing in formation, and engaging in discussions or presentations. The setting is outdoors, with various backgrounds including streets, buildings, and a white van. The atmosphere is generally one of unity, purpose, and seriousness, with the individuals appearing focused on their activities. The event may be connected to a news story or political address, as hinted at in the initial frame featuring a news broadcast on Alibek TV discussing an address to the National Assembly. Overall, the video suggests a planned and organized activity, possibly a protest, community event, or press conference, with the yellow jackets indicating a uniform or organizational affiliation.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
| ["People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",(...TRUNCATED)
| ["Buildings collapsing or showing significant structural damage during the 12 September 2016 earthqu(...TRUNCATED)
| ["People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 20(...TRUNCATED)
| {"article_url":"https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84","(...TRUNCATED)
| 16
| ["The current frame shows a news broadcast from Yonhap News TV, featuring a female news presenter. T(...TRUNCATED)
|
w6jdwGYcKZU
| "The video appears to be a news report about an earthquake that occurred in Korea, resulting in 23 d(...TRUNCATED)
|
End of preview. Expand
in Data Studio
README.md exists but content is empty.
- Downloads last month
- 5
Size of downloaded dataset files:
9.17 MB
Size of the auto-converted Parquet files:
9.17 MB
Number of rows:
2,394