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 • 37 items • Updated
query stringclasses 259 values | prequel listlengths 0 30 | sequel listlengths 0 30 | during listlengths 0 30 | metadata dict | num_of_frames int64 4 4 | frame_captions listlengths 4 4 | video_id stringlengths 6 45 | frame2video_caption stringlengths 157 1.26k |
|---|---|---|---|---|---|---|---|---|
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... | [
"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 rubb... | [
"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 ea... | {
"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"
} | 4 | [
"The image shows a surveillance camera view of an aisle in a warehouse or storage area. The shelves on the right are stocked with numerous boxes, and the area appears organized. On the left, there is a wall with some equipment and boxes. The text at the bottom of the image indicates the time and location in Korean,... | t8lY-rjy7-Y | The video appears to depict a series of unrelated scenes. It begins with a surveillance view of a warehouse or storage area, showing an organized aisle with shelves and equipment. The scene then shifts to a domestic environment, possibly a bedroom, where a person is kneeling on a bed, interacting with a small object in a quiet and focused manner. The video then cuts to an official or professional setting, where a person is sitting at a desk, delivering a speech or making an official statement into a microphone. This person continues to address the audience in the final frame, maintaining a professional demeanor in front of a flag and laptop. The overall context suggests a narrative that jumps between different locations and activities, possibly indicating a search or investigation in progress, as hinted by the Korean text translations. |
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... | [
"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 rubb... | [
"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 ea... | {
"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"
} | 4 | [
"The image shows a scene of a busy street or market area, with several people walking. There is text in Korean that appears to discuss record times or distances. The text mentions \"5.8 km\" and \"5.8 hours,\" suggesting a comparison or achievement in a specific context, possibly related to travel or distance runni... | CXe6_CDrdB8 | A man discusses work-life balance and productivity in a series of scenes, starting with a busy street or market area displaying a record time or distance achievement. He then appears in a work environment, standing in front of a computer screen showing charts and graphs, initially smiling and later looking serious as he conveys a message about taking breaks from work. The video also includes a close-up of handwritten text on a notebook, where the concept of a "ginsang champion" is introduced, emphasizing the importance of efficiency, time management, and handling work demands effectively. The overall context suggests the man is sharing insights or advice on how to balance work and personal life, possibly in a social media or blog post. |
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... | [
"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 rubb... | [
"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 ea... | {
"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"
} | 4 | [
"The image shows a night vision scene depicting a small area with a structure that resembles a shrine or altar. There is a bright light or fire near the structure, possibly indicating activity or ritual. The image also includes text in Korean which translates to \"Jeongju crime scene, suspect arrived one to two day... | uF3x63vtddc | A crime investigation is underway in Jeongju, where a suspect arrived one to two days ago. The scene begins with a nighttime setting, showing a structure resembling a shrine or altar with a fire or bright light, indicating possible ritualistic activity. The investigation then shifts to an interior location, focusing on a decorative mirror and window, suggesting a search for evidence or clues. The scene moves to a street setting, where a white car is parked and several individuals, potentially investigators or witnesses, are gathered around the vehicle, engaged in conversation or inspection. The ongoing activity and presence of multiple individuals imply a thorough investigation into the crime, with the suspect's recent arrival in Jeongju being a key factor in the case. |
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... | [
"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 rubb... | [
"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 ea... | {
"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"
} | 4 | [
"The image shows a construction scene where a crane is lifting a large object over a building with a traditional Korean-style roof. Several vehicles, including trucks, are parked in the foreground, and some people are visible in the vicinity. The text in the top left corner reads \"경주 4.5여진 안전처 홈피 또 먹통\" indicating... | nln3QFJggKs | The video depicts the aftermath of a 4.5 magnitude earthquake in Gyeongju, showcasing the damage to infrastructure and cultural assets. The scene shifts between a construction site where a crane is lifting debris, a rural area with traditional Korean houses, and close-up views of cracked roads and damaged walls. The earthquake has caused significant destruction, with an initial damage cost estimate of 106 billion won being revised to 58 billion won due to a lack of public bidding. The video highlights the need for rebuilding and public safety measures, emphasizing the impact of the earthquake on the community and the importance of addressing the damage to ensure public safety. |
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... | [
"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 rubb... | [
"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 ea... | {
"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"
} | 4 | [
"The image shows a kitchen setting with various kitchen utensils and appliances visible. There is a cutting board, utensils hanging on the wall, and pots and pans on the counter. A news ticker is present at the bottom of the image with Korean text. The top right corner has additional text in Korean, likely indicati... | n6UmQ9Kw2GQ | A news broadcast on Yonhap News TV reports on a disturbing incident involving a woman who gave birth to 307 children after a sexual assault, with the news studio setup showing an indoor environment with various props and a screen displaying relevant information in Korean. |
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... | [
"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 rubb... | [
"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 ea... | {
"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"
} | 4 | [
"The frame shows a grainy black and white image of a chaotic scene, likely a news report or footage from a disaster area. The text in Korean at the bottom of the screen reads \"경주 지진으로 8명 부상...재산피해 253건\", which translates to \"8 people injured due to Gyeongju earthquake...253 property damage cases\". The image app... | uoagwCVoHGM | The video depicts the aftermath of an earthquake in Gyeongju, showing the damage and cleanup efforts. The footage includes a chaotic scene with debris, a person sweeping up debris, and a close-up of a cracked wall, highlighting the extent of the destruction. The earthquake resulted in 8 people injured and 253 property damage cases. The video also shows individuals walking together in a hallway, suggesting a sense of normalcy and support amidst the disaster. Overall, the video appears to be a news report or documentary about the Gyeongju earthquake, showcasing the impact on the community and the ongoing recovery efforts. |
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... | [
"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 rubb... | [
"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 ea... | {
"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"
} | 4 | [
"The image shows a news broadcast screen displaying a radar map and seismic activity data. On the left, there's a map with a network of lines and data points indicating a seismic event. The right side features a detailed radar map with concentric circles and indicators, suggesting tracking of an object or phenomeno... | 5p1N4MtudiI | A news broadcast reports on an ongoing series of earthquakes in Zhongju, noting that the seismic activity has continued for the 316th time with a current period of relative quiet. The video displays seismic activity data, including radar maps and seismographs, to provide visual context to the event. Maps of the affected geographical area are shown, marked with numerous yellow and orange circles representing earthquake epicenters, to illustrate the widespread nature of the seismic activity. |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12... | [
"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 rubb... | [
"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 ea... | {
"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"
} | 4 | [
"An aerial view of a traditional tiled roof with some sections covered by blue tarpaulin, indicating possible repairs or maintenance. A white car is parked on the street adjacent to the building.",
"The current frame shows several workers on a traditional tiled roof covered with blue tarpaulin, engaged in repair ... | roaxxb8zRLU | The video depicts a rural area, specifically Kangju Jinamji, where disaster prevention and infrastructure improvement efforts are underway. The scene opens with a close-up view of a traditional tiled roof undergoing repairs or maintenance, with workers prioritizing safety. The camera then pans out to reveal the broader context: a rural landscape with a road, fields, and notable buildings such as a school. The focus is on preparations for or recovery from disasters, particularly flooding, as indicated by the text and the presence of buses and infrastructure near the school. The video highlights the importance of disaster prevention measures and infrastructure enhancements in the area, showcasing the community's efforts to mitigate the impact of natural disasters. |
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... | [
"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 rubb... | [
"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 ea... | {
"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"
} | 4 | [
"The image shows a group of people walking together outdoors. They are all wearing yellow jackets. The scene appears to be a public or official event, possibly a visit or inspection. A banner and some text in Korean at the bottom of the image suggest a formal context, mentioning \"President Park Geun-hye, Gyeongju ... | 3ojHTwrvx90 | The video depicts a formal event where President Park Geun-hye visits Gyeongju City Hall to declare a special zone for the world. A group of people, mostly wearing yellow jackets, gather to participate in or witness the event. The scene involves a series of addresses or speeches, first by a woman and then by a man, both using microphones to convey their messages to the audience. The event appears to be a significant public or governmental ceremony, with participants showing keen interest and attention to the declarations being made. The overall context suggests an official visit and announcement related to designating a special zone, with the involvement of high-ranking officials and a formal 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... | [
"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 rubb... | [
"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 ea... | {
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=w6jdwGYcKZU",
"video_description": "안전처 \"경주지진 부상자 23명ㆍ재산피해 1,118건\" 국민안전처는 경주에서 발생한 규모 5.8의 지진으로 부상자 23명이 발생하고, 재산상 피해는 1천118건으로 집계됐다고 밝혔습니다. 안전처와 보건복지부에 따르면 부상자 23명 가운데 7명은 병원에서 치료를 받고 귀가했으며, 16명은 입원 중입니다. 지역별 부상자는 경북이 12명으로 가장 많고, 울산 4명, 대구 2명, 부산·인천·충북·전남·경남 각 1명입니다. 안전처는 균열이 발생한 주택을 대상으로 구조기술사 등과 함께 안전점검을 하고 귀가 여부와 추가 안전조치 등을 검토할 예정입니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "w6jdwGYcKZU"
} | 4 | [
"The image appears to show a scene with debris and rubble, indicating possible destruction or a disaster aftermath. There are fragments of structures and scattered objects on the ground. The text at the bottom of the image, written in Korean, states \"경주 지진 부상자 23명 · 재산피해 1,118건\" which translates to \"Gyeongju ear... | w6jdwGYcKZU | The video depicts the aftermath of an earthquake in Gyeongju, showing widespread destruction and damage to structures. The earthquake resulted in 23 injuries and 1,118 instances of property damage. The footage includes scenes of debris-filled environments, cracked walls, and damaged traditional Korean houses, highlighting the extent of the disaster. The video appears to be part of a news segment, providing visual evidence of the earthquake's impact on the community. |
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017. | [
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching... | [
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders ... | [
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responder... | {
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=oK2O8Xtkrvs",
"video_description": "15일 오후 2시 29분쯤 경북 포항시 북구 북쪽 9㎞ 지역에서 규모 5.4의 지진이 발생했다. 오마이TV는 지진 발생 당시 포항시 북구 한살림협동조합 매장을 촬영한 CCTV영상을 제보받아 공개한다. 이 영상에는 갑자기 진열대 물건들이 쏟아져내리는 장면이 들어있다. 한살림협동조합에 근무하는 박혜령(경북 영덕군)씨는 영상을 제보하면서 \"당시 사무실에 있었는데 벽지와 창문이 20초 이상 심하게 흔들렸다\"며 \"아직도 가슴이 진정되지 않는다\"고 말했다. 그는 \"바닥이 계속 흔들려 모두 밖으로 나왔고 안으로 들어갈 엄두를 내지 못했다\"며 \"이후 여진을 알리는 재난문자가 세 차례 왔다\"고 당시 상황을 설명했다. (영상제보 : 박혜령 씨/ 영상편집 : 황지희 기자)",
"video_id": "oK2O8Xtkrvs"
} | 4 | [
"In the current frame, a person is crouching near a shelf inside a store. The store has various shelves stocked with products. The text on the screen reads: \"[시민 제보] 포항 지진 순간, 쏟아진 진열대,\" which translates to \"[Citizen Report] Moment of the Pohang earthquake, toppled display.\" This suggests the image captures a mo... | oK2O8Xtkrvs | A video captures the moment of and immediate aftermath of the Pohang earthquake inside a store. The footage, sourced from OhmyTV, shows a person crouching near a shelf amidst a disarrayed store with various products scattered on the floor due to the earthquake. As the video progresses, it becomes clear that the store suffered significant damage, with shelves toppled and items displaced. A person in the background is seen assessing the situation, indicating efforts to understand the extent of the damage. The video concludes with a screen displaying the OhmyTV logo, URL, and additional information, serving as a credit or informational segment about the footage. |
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017. | [
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching... | [
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders ... | [
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responder... | {
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=6HhGFKbHFbs",
"video_description": "경북 포항에서 규모 5.4의 지진과 여진이 발생, 전국이 지진파에 흔들거리면서 주민들이 불안에 떨고 있다. 15일 기상청에 따르면 이날 오후 2시29분쯤 포항시 북구 흥해 6㎞ 지점에서 지진이 발생했다. http://www.hankookilbo.com/v/38f7f1c1597443e5ac55aca087a5dae2",
"video_id": "6HhGFKbHFbs"
} | 4 | [
"The frame shows a street scene with pedestrians walking and a white car parked in the center of the road. Various shops line the street, and a sign with Korean text is visible. The date on the sign indicates November 15.",
"The scene continues on the same street, now with a white arrow painted on the road and a ... | 6HhGFKbHFbs | A video depicts a scene on a street in a Korean town, showing pedestrians walking along the road lined with various shops. The date November 15 is visible on a sign. A white car is initially parked in the center of the road but disappears in subsequent frames. A person is seen walking down the middle of the road, looking at their phone, before moving to the right side towards a crowd of pedestrians. The video then cuts to a screen displaying the logo and web address of a Korean news or media publication, HANKOOKILBO.COM, suggesting the footage may be part of a news report or related content. |
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017. | [
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching... | [
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders ... | [
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responder... | {
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=1sXMvTYhnn0",
"video_description": "+--------------------------------------------------------------------------------+ ◈ 중앙일보 공식 SNS 채널 ◈ - 페이스북 : https://www.facebook.com/joongang/ - 인스타그램 : https://www.instagram.com/joongangilbo - 트위터 : http://www.twitter.com/joongangilbo - 유튜브 : https://goo.gl/DyGoPC - 네이버 TV : http://tvcast.naver.com/joongangsisa - 네이버포스트 : https://goo.gl/eeYh4k 당신이 원하는 뉴스, 중앙일보 SNS 채널과 함께하세요. +--------------------------------------------------------------------------------+",
"video_id": "1sXMvTYhnn0"
} | 4 | [
"The image shows a room with a large grandfather clock on the wall. The clock displays the time as approximately 10:10. Next to it is a smaller wall clock. The background includes bookshelves and various items, including a white helmet. The text on the image is in Korean and discusses an apartment collapse and the ... | 1sXMvTYhnn0 | The video depicts a series of unrelated scenes, but the overarching context appears to be news or reportage about various incidents and accidents in an urban setting, likely in Korea given the text in Korean. The video begins in a room with clocks, setting a time context, and transitions to a street scene in front of a commercial building, mentioning a vehicle-related issue. It then shifts to a busy airport terminal, where the focus turns to an accident involving a taxi at Daegeu Station, with a driver under investigation for negligent homicide. Throughout the airport scenes, people are engaged in typical travel activities, oblivious to the news being reported. The key actions involve reporting on accidents, the participants include unnamed individuals in the background of the scenes, and the context is one of urban life interrupted by incidents of negligence or disaster. |
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017. | [
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching... | [
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders ... | [
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responder... | {
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=MH6_TeWDitQ",
"video_description": "포항 북구 북쪽 9Km 지역서 5.4 지진 이어 여진…전국서 감지 2.2, 2.6 전진 이어 3.6 여진도 발생 기상청은 15일 오후 2시 29분 쯤 경북 포항시 북구 북쪽 9㎞ 지역에서 규모 5.4의 지진이 발생했다고 밝혔습니다. 진앙은 북위 36.10도, 동경 129.37도입니다. 기상청은 이 지진의 깊이를 9㎞로 파악했습니다. 기상청은 당초 지진 발생지역과 규모를 포항시 북구 북쪽 6㎞ 지점, 규모 5.5로 발표했으나 잠시 후 수정하는 등 혼선이 이어지고 있습니다. 이날 오후 2시49분에는 포항시 북구 북쪽 7km에서 규모 3.6의 여진도 발생했습니다. 기상청은 \"이동속도가 빠른 지진파(P파)만을 이용해 자동 추정한 정보\"라며 \"여진 등 안전에 주의해야 한다\"고 당부했습니다. 이날 지진으로 경북과 경남은 물론 서울 지역에서도 건물 흔들림이 느껴지는 등 전국 곳곳에서 진동이 감지됐습니다. 이보다 앞서 이 인근에서는 두 차례 지진이 있었다고 기상청은 발표했습니다. 오후 2시 22분 32초 포항시 북구 북쪽 7km 지역(북위 36.11도, 동경 129.36도)에서 규모 2.2의 지진이 난 후 2시 22분 44초에는 비슷한 지점(북위 36.08도, 동경 129.31도)에서 규모 2.6의 지진이 발생했습니다. (끝)",
"video_id": "MH6_TeWDitQ"
} | 4 | [
"The image shows a map with various regions labeled in Korean. The central focus is a red target-like symbol, indicating a specific location of interest or an event. The surrounding regions include labels such as \"포항시북구\" (Pohang-si Buk-gu), \"포항시남구\" (Pohang-si Nam-gu), \"경주시\" (Gyeongju-si), and \"영천시\" (Yeongch... | MH6_TeWDitQ | The video depicts an event occurring in an urban area of South Korea, specifically around Pohang and neighboring cities. It begins with a map highlighting a location of interest, then transitions to a bustling street scene with people and cars, suggesting a significant event or gathering. However, the scene quickly changes to one of disorder, with debris scattered across the road, indicating some form of incident or disturbance. The video concludes with the aftermath of this event, showing the same area with debris still present and a few individuals in the vicinity, suggesting that the impact of the incident is ongoing. The overall context implies that the video is capturing the lead-up, occurrence, and immediate aftermath of an event that disrupts normal urban activity in the region. |
End of preview. Expand
in Data Studio
README.md exists but content is empty.
- Downloads last month
- 7
Size of downloaded dataset files:
4.38 MB
Size of the auto-converted Parquet files:
4.38 MB
Number of rows:
2,394