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 35 | sequel listlengths 0 35 | during listlengths 0 35 | metadata dict | num_of_frames int64 16 16 | frame_captions listlengths 16 16 | video_id stringlengths 6 45 | frame2video_caption stringlengths 219 3.18k |
|---|---|---|---|---|---|---|---|---|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"\"2016 Gyeongju earthquake in Gyeongju, South Korea on September 12, 2016\"",
"people running out of buildings in Gyeongju South Korea on September 12 2016.",
"Rescue workers searching for survivors under debris in Gyeongju, South Korea on September 12, 2016 after the 2016 Gyeongju earthquake.",
"\"Damage to... | [
"rescue teams evacuating people from damaged buildings in Gyeongju, South Korea on September 12, 2016.",
"Emergency services treating injured people in Gyeongju, South Korea on September 12, 2016.",
"aerial footage of the 2016 Gyeongju earthquake damage in Gyeongju, South Korea on September 12, 2016\"",
"\"Ne... | [
"\"2016 Gyeongju earthquake South Korea\"",
"Gyeongju earthquake 2016 buildings shake and collapse aftermath.",
"\"Rescue teams search for people trapped under debris after the 2016 Gyeongju earthquake in Gyeongju, South Korea on September 12, 2016.\"",
"Gyeongju earthquake evacuation September 12 2016\"",
... | {
"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:\nTo extract events related to the 2016 Gyeongju earthquake, we should focus on describing the natural disaster itself and its aftermath. This includes events that are likely to be visualized in a video, such as damage, rescue operations, and reactions from the public.\n\nEVENTS:\n1. Earthquake hits Gyeongju, South Korea.\n2. Buildings shake and collapse in the aftermath of the earthquake.\n3. Rescue teams search for people trapped under debris.\n4. People evacuate the area, leaving their daily activities behind.\n5. News reports on the damage caused by the earthquake.",
"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:\nTo extract relevant events related to the 2016 Gyeongju earthquake, we need to consider geological events that could be visualized in a video and are likely to occur in South Korea. This might include footage of earthquakes, damage to buildings, rescue efforts, and news coverage.\n\nEVENTS:\n1. A magnitude 5.8 earthquake strikes near Gyeongju, South Korea.\n2. People running out of buildings due to the sudden earthquake.\n3. Rescue workers searching for survivors under debris in the aftermath.\n4. Damage to ancient buildings and monuments in Gyeongju, a city known for its historical sites.\n5. Emergency vehicles and helicopters arriving on the scene in response to the earthquake.",
"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: \nGiven the query is about a specific earthquake event, the extracted events should focus on the immediate aftermath and the response to the earthquake. These events should be visualizable in a video and are directly related to the earthquake. The context is a natural disaster in a specific location, so it's reasonable to expect events like rescue operations, damage assessment, and media coverage.\n\nEVENTS:\n1. Rescue teams evacuating people from damaged buildings\n2. Emergency services treating injured people\n3. Aerial footage of the earthquake damage in Gyeongju, South Korea\n4. News reporters interviewing residents about their experiences during the earthquake\n5. Aerial view of the aftermath, showing destruction and debris",
"video_URL": "http://youtube.com/watch?v=t8lY-rjy7-Y",
"video_description": "9월 12일, 경주에서는 역대 최대 규모인 5.8 지진이 일어났다. 지진으로 서울과 수도권까지 전국이 흔들렸고, 이로 인해 전화와 카카오톡도 모두 먹통이었다. 정부는 지진 발생 9분이 지나서야 긴급재난문자를 발송했고 이마저도 서울과 수도권 지역 국민들은 문자를 받지 못했다. #경주 #지진 #재난문자",
"video_id": "t8lY-rjy7-Y"
} | 16 | [
"The image shows a group of people, likely students, rushing down a hallway and up a staircase. They appear to be in a hurry, possibly evacuating the building. The timestamp on the image reads \"7시 44분,\" which indicates the time as 7:44 AM. The setting seems to be a school or similar institution.",
"The image sh... | t8lY-rjy7-Y | A group of students rushes down a hallway and up a staircase in a school or similar institution due to an urgent situation, likely an evacuation.
The students are in a hurry in a classroom, preparing to leave or responding to the situation.
An earthquake warning detected by the Korean Railway system prompts an evacuation or transition within the school.
An earthquake occurs in Gyeongju, causing the area to be secured and investigated, with debris scattered outside a building.
A bus drives through the affected area with debris scattered across the ground, possibly indicating the earthquake's impact.
A domestic reaction to the earthquake is shown, with a person playing with a dog in a room, indicating the widespread impact of the event.
The National Assembly requests immediate resolution of the issue, with the national security-related services being impacted.
A government official or representative addresses the media or public about the situation, likely related to the earthquake.
A discussion or update on the impact on national security-related services is shown through text messages on a mobile phone.
The government or institution provides an official statement, possibly focusing on lessons learned or improvements from the current events.
The speaker apologizes for a situation related to the Yoon Seok-yeol incident, indicating a significant event involving this person.
A chaotic scene in a school hallway is depicted, with students rushing down the stairs and along the corridor in a state of urgency and panic.
Students in a classroom appear confused and distressed, possibly reacting to an unusual and alarming situation within the school. |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"\"2016 Gyeongju earthquake in Gyeongju, South Korea on September 12, 2016\"",
"people running out of buildings in Gyeongju South Korea on September 12 2016.",
"Rescue workers searching for survivors under debris in Gyeongju, South Korea on September 12, 2016 after the 2016 Gyeongju earthquake.",
"\"Damage to... | [
"rescue teams evacuating people from damaged buildings in Gyeongju, South Korea on September 12, 2016.",
"Emergency services treating injured people in Gyeongju, South Korea on September 12, 2016.",
"aerial footage of the 2016 Gyeongju earthquake damage in Gyeongju, South Korea on September 12, 2016\"",
"\"Ne... | [
"\"2016 Gyeongju earthquake South Korea\"",
"Gyeongju earthquake 2016 buildings shake and collapse aftermath.",
"\"Rescue teams search for people trapped under debris after the 2016 Gyeongju earthquake in Gyeongju, South Korea on September 12, 2016.\"",
"Gyeongju earthquake evacuation September 12 2016\"",
... | {
"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:\nTo extract events related to the 2016 Gyeongju earthquake, we should focus on describing the natural disaster itself and its aftermath. This includes events that are likely to be visualized in a video, such as damage, rescue operations, and reactions from the public.\n\nEVENTS:\n1. Earthquake hits Gyeongju, South Korea.\n2. Buildings shake and collapse in the aftermath of the earthquake.\n3. Rescue teams search for people trapped under debris.\n4. People evacuate the area, leaving their daily activities behind.\n5. News reports on the damage caused by the earthquake.",
"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:\nTo extract relevant events related to the 2016 Gyeongju earthquake, we need to consider geological events that could be visualized in a video and are likely to occur in South Korea. This might include footage of earthquakes, damage to buildings, rescue efforts, and news coverage.\n\nEVENTS:\n1. A magnitude 5.8 earthquake strikes near Gyeongju, South Korea.\n2. People running out of buildings due to the sudden earthquake.\n3. Rescue workers searching for survivors under debris in the aftermath.\n4. Damage to ancient buildings and monuments in Gyeongju, a city known for its historical sites.\n5. Emergency vehicles and helicopters arriving on the scene in response to the earthquake.",
"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: \nGiven the query is about a specific earthquake event, the extracted events should focus on the immediate aftermath and the response to the earthquake. These events should be visualizable in a video and are directly related to the earthquake. The context is a natural disaster in a specific location, so it's reasonable to expect events like rescue operations, damage assessment, and media coverage.\n\nEVENTS:\n1. Rescue teams evacuating people from damaged buildings\n2. Emergency services treating injured people\n3. Aerial footage of the earthquake damage in Gyeongju, South Korea\n4. News reporters interviewing residents about their experiences during the earthquake\n5. Aerial view of the aftermath, showing destruction and debris",
"video_URL": "http://youtube.com/watch?v=CXe6_CDrdB8",
"video_description": "찐♡기상청사람들 예고 없이 찾아오는 지진! 한 번 발생하면 큰 피해를 주는 지진이기에 감시하는 일은 한시도 소홀히 할 수 없습니다. 그 최전방에서... 1년 365일 24시간 지진화산 감시 및 분석 업무에 최선을 다해 신속·정확하게 알리고자 노력하는 사람이 있습니다. 지진화산 감시 및 분석 업무 9년 차... 반복되는 주간 근무와 야간 근무가 힘들긴 하지만, 누구보다 묵묵하게 자리를 지키고 있는 진득한 뚝배기 같은 지진업무의 대들보!! 지진화산 감시 업무를 담당하는 기상청 사람을 만나고 왔습니다.(^_^)v 우리나라에서 가장 강력했던 규모 5.8의 경주 지진 때 지진감시 및 분석을 수행했던 기상청 사람은 누구? 지진감시 업무를 들어올 때마다 긴장되는 기상청 사람은 누구? 국민의 안전을 누구보다 걱정하는 기상청 사람은 누구? 지진 올바로 알고 지진 발생 시 빠르게 대처하길 바라는 기상청 사람은 누구? 최근 지진 안전을 홍보해 주시는 지진희 배우님을 그 누구보다 고마워하는 기상청 사람은 누구? 만나볼까요 :) #기상청사람들 #지진화산 #행동하는파수꾼",
"video_id": "CXe6_CDrdB8"
} | 16 | [
"In this frame, a man is standing in front of a wall of multiple monitors displaying various data and graphs. He is wearing a blue shirt and a white watch, and appears to be presenting or discussing the content on the screens. The text on the screen reads \"Q 엄무 소개?\" which translates to \"Q Introduction to work?\"... | CXe6_CDrdB8 | A professional or technical presentation about seismic activity, specifically an earthquake that occurred in Gyeongju, is being discussed. The video likely provides an in-depth analysis and interpretation of the event, focusing on its significance, magnitude, and the speed and accuracy of forecasts compared to actual occurrences. Key individuals, presumably experts in earthquake monitoring or analysis, are involved in the discussion and presentation, utilizing various data and graphs to convey their findings. The video may be part of a training, briefing, or educational session, emphasizing the importance of accurate seismic data interpretation for timely warnings and responses. |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"\"2016 Gyeongju earthquake in Gyeongju, South Korea on September 12, 2016\"",
"people running out of buildings in Gyeongju South Korea on September 12 2016.",
"Rescue workers searching for survivors under debris in Gyeongju, South Korea on September 12, 2016 after the 2016 Gyeongju earthquake.",
"\"Damage to... | [
"rescue teams evacuating people from damaged buildings in Gyeongju, South Korea on September 12, 2016.",
"Emergency services treating injured people in Gyeongju, South Korea on September 12, 2016.",
"aerial footage of the 2016 Gyeongju earthquake damage in Gyeongju, South Korea on September 12, 2016\"",
"\"Ne... | [
"\"2016 Gyeongju earthquake South Korea\"",
"Gyeongju earthquake 2016 buildings shake and collapse aftermath.",
"\"Rescue teams search for people trapped under debris after the 2016 Gyeongju earthquake in Gyeongju, South Korea on September 12, 2016.\"",
"Gyeongju earthquake evacuation September 12 2016\"",
... | {
"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:\nTo extract events related to the 2016 Gyeongju earthquake, we should focus on describing the natural disaster itself and its aftermath. This includes events that are likely to be visualized in a video, such as damage, rescue operations, and reactions from the public.\n\nEVENTS:\n1. Earthquake hits Gyeongju, South Korea.\n2. Buildings shake and collapse in the aftermath of the earthquake.\n3. Rescue teams search for people trapped under debris.\n4. People evacuate the area, leaving their daily activities behind.\n5. News reports on the damage caused by the earthquake.",
"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:\nTo extract relevant events related to the 2016 Gyeongju earthquake, we need to consider geological events that could be visualized in a video and are likely to occur in South Korea. This might include footage of earthquakes, damage to buildings, rescue efforts, and news coverage.\n\nEVENTS:\n1. A magnitude 5.8 earthquake strikes near Gyeongju, South Korea.\n2. People running out of buildings due to the sudden earthquake.\n3. Rescue workers searching for survivors under debris in the aftermath.\n4. Damage to ancient buildings and monuments in Gyeongju, a city known for its historical sites.\n5. Emergency vehicles and helicopters arriving on the scene in response to the earthquake.",
"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: \nGiven the query is about a specific earthquake event, the extracted events should focus on the immediate aftermath and the response to the earthquake. These events should be visualizable in a video and are directly related to the earthquake. The context is a natural disaster in a specific location, so it's reasonable to expect events like rescue operations, damage assessment, and media coverage.\n\nEVENTS:\n1. Rescue teams evacuating people from damaged buildings\n2. Emergency services treating injured people\n3. Aerial footage of the earthquake damage in Gyeongju, South Korea\n4. News reporters interviewing residents about their experiences during the earthquake\n5. Aerial view of the aftermath, showing destruction and debris",
"video_URL": "http://youtube.com/watch?v=uF3x63vtddc",
"video_description": "\"경주 지진, 지하수는 1~2일 전에 미리 알았다\" 지난 12일과 19일 경주에서 규모 5.8을 비롯한 대형 지진이 잇따라 발생하기 하루 이틀 전 주변 지하수 수위가 크게 상승해, 향후 지진예측에 활용할 수 있다는 주장이 나왔습니다. 정상용 부경대 지구환경과학과 교수는 진앙에서 가장 가까운 경북 경주시 산내면에 있는 지하수 관측소 자료를 분석한 결과, 이 같이 밝혔습니다. 자료를 보면 지난 11일 암반 지하수 수위는 하루 사이에 무려 49㎝ 상승했고, 17일에도 39㎝나 올라갔습니다. 정 교수는 지진에 앞서 암석에 강한 압력이 가해져 지하수 수위가 많이 올라간 것으로 보인다며, 규모 4.5 이상의 지진에만 영향을 받았다고 설명했습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "uF3x63vtddc"
} | 16 | [
"In the image, two news anchors are standing in a news studio. The male anchor is on the left and the female anchor is on the right. They appear to be delivering a news report. The studio background shows multiple screens displaying various images, likely from other news stories or related footage. \n\nThe text on ... | uF3x63vtddc | The video appears to be a news broadcast covering an earthquake that occurred in Gyeongju. The report starts with two news anchors delivering a segment on the earthquake, highlighting how groundwater provided an early warning. The broadcast then cuts to various surveillance footage and news reports detailing the aftermath and consequences of the earthquake.
The footage shows scenes of damage and flooding in a residential area and industrial spaces, suggesting that the earthquake had a significant impact on the region. The news story emphasizes that a machine in Gyeongju was operational for 1-2 days before the earthquake occurred.
The footage then shifts to various locations in Gyeongju, including a commercial area and traditional buildings, showing scenes of normalcy and activity, possibly to contrast with the damage caused by the earthquake. The news report continues to reference the Gyeongju incident and the machine's operation for 1-2 days before the event, indicating that the story is still unfolding.
The video's context suggests that the earthquake had a notable impact on the region, with potential consequences for the local infrastructure and possibly the machine's operation. The ongoing news report seems to be investigating the incident, providing updates on the situation in Gyeongju. |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"\"2016 Gyeongju earthquake in Gyeongju, South Korea on September 12, 2016\"",
"people running out of buildings in Gyeongju South Korea on September 12 2016.",
"Rescue workers searching for survivors under debris in Gyeongju, South Korea on September 12, 2016 after the 2016 Gyeongju earthquake.",
"\"Damage to... | [
"rescue teams evacuating people from damaged buildings in Gyeongju, South Korea on September 12, 2016.",
"Emergency services treating injured people in Gyeongju, South Korea on September 12, 2016.",
"aerial footage of the 2016 Gyeongju earthquake damage in Gyeongju, South Korea on September 12, 2016\"",
"\"Ne... | [
"\"2016 Gyeongju earthquake South Korea\"",
"Gyeongju earthquake 2016 buildings shake and collapse aftermath.",
"\"Rescue teams search for people trapped under debris after the 2016 Gyeongju earthquake in Gyeongju, South Korea on September 12, 2016.\"",
"Gyeongju earthquake evacuation September 12 2016\"",
... | {
"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:\nTo extract events related to the 2016 Gyeongju earthquake, we should focus on describing the natural disaster itself and its aftermath. This includes events that are likely to be visualized in a video, such as damage, rescue operations, and reactions from the public.\n\nEVENTS:\n1. Earthquake hits Gyeongju, South Korea.\n2. Buildings shake and collapse in the aftermath of the earthquake.\n3. Rescue teams search for people trapped under debris.\n4. People evacuate the area, leaving their daily activities behind.\n5. News reports on the damage caused by the earthquake.",
"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:\nTo extract relevant events related to the 2016 Gyeongju earthquake, we need to consider geological events that could be visualized in a video and are likely to occur in South Korea. This might include footage of earthquakes, damage to buildings, rescue efforts, and news coverage.\n\nEVENTS:\n1. A magnitude 5.8 earthquake strikes near Gyeongju, South Korea.\n2. People running out of buildings due to the sudden earthquake.\n3. Rescue workers searching for survivors under debris in the aftermath.\n4. Damage to ancient buildings and monuments in Gyeongju, a city known for its historical sites.\n5. Emergency vehicles and helicopters arriving on the scene in response to the earthquake.",
"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: \nGiven the query is about a specific earthquake event, the extracted events should focus on the immediate aftermath and the response to the earthquake. These events should be visualizable in a video and are directly related to the earthquake. The context is a natural disaster in a specific location, so it's reasonable to expect events like rescue operations, damage assessment, and media coverage.\n\nEVENTS:\n1. Rescue teams evacuating people from damaged buildings\n2. Emergency services treating injured people\n3. Aerial footage of the earthquake damage in Gyeongju, South Korea\n4. News reporters interviewing residents about their experiences during the earthquake\n5. Aerial view of the aftermath, showing destruction and debris",
"video_URL": "http://youtube.com/watch?v=nln3QFJggKs",
"video_description": "106억 → 58억…경주 지진 피해금액 반토막 잇단 강진으로 100억원이 넘는 것으로 추정됐던 경주시의 공식 피해규모가 58억원 수준에 그치는 것으로 집계됐습니다. 경주시가 지진 발생 뒤 전수조사를 통해 발표한 잠정 추산 피해액은 약 107억원이었지만 사유재산 피해는 대부분 공식 피해액에서 빠졌습니다. 규정상 기와가 떨어지거나 벽체에 금이 가고 담장이 파손된 것은 재산피해 산정되지 않습니다. 이에 따라 사유재산 중에는 지진으로 주택이 완전히 부서지거나 반쯤 허물어진 것만 공식 피해액에 들어갔습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "nln3QFJggKs"
} | 16 | [
"The image shows a news broadcast from Yonhap News TV, featuring two news anchors. The male anchor on the left is dressed in a dark suit and red tie, while the female anchor on the right wears a blue blazer over a pink top. Both are standing in front of a backdrop depicting a nighttime street scene. There is a larg... | nln3QFJggKs | The video is a news report documenting the aftermath and recovery efforts following a significant earthquake in Gyeongju, South Korea, specifically a 4.5 magnitude aftershock. The report focuses on the reduced estimated damage costs from 106 billion to 58 billion won, indicating progress in assessing and addressing the impact of the earthquake.
Key participants involved in the report include the news anchors, construction workers, residents, and authorities conducting damage assessments and repair work. The video showcases the extensive structural damage to buildings, roads, and other infrastructure, as well as the ongoing cleanup and repair efforts.
The context of the event is set against the backdrop of Gyeongju, a historic city with significant cultural heritage sites, which are also affected by the earthquake. The video emphasizes the need for safety inspections and repair of these cultural heritage buildings to prevent further deterioration.
The report highlights the resilience of the community, with residents and workers engaged in recovery efforts, and the authorities working to assess and mitigate the damage caused by the earthquake. |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"\"2016 Gyeongju earthquake in Gyeongju, South Korea on September 12, 2016\"",
"people running out of buildings in Gyeongju South Korea on September 12 2016.",
"Rescue workers searching for survivors under debris in Gyeongju, South Korea on September 12, 2016 after the 2016 Gyeongju earthquake.",
"\"Damage to... | [
"rescue teams evacuating people from damaged buildings in Gyeongju, South Korea on September 12, 2016.",
"Emergency services treating injured people in Gyeongju, South Korea on September 12, 2016.",
"aerial footage of the 2016 Gyeongju earthquake damage in Gyeongju, South Korea on September 12, 2016\"",
"\"Ne... | [
"\"2016 Gyeongju earthquake South Korea\"",
"Gyeongju earthquake 2016 buildings shake and collapse aftermath.",
"\"Rescue teams search for people trapped under debris after the 2016 Gyeongju earthquake in Gyeongju, South Korea on September 12, 2016.\"",
"Gyeongju earthquake evacuation September 12 2016\"",
... | {
"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:\nTo extract events related to the 2016 Gyeongju earthquake, we should focus on describing the natural disaster itself and its aftermath. This includes events that are likely to be visualized in a video, such as damage, rescue operations, and reactions from the public.\n\nEVENTS:\n1. Earthquake hits Gyeongju, South Korea.\n2. Buildings shake and collapse in the aftermath of the earthquake.\n3. Rescue teams search for people trapped under debris.\n4. People evacuate the area, leaving their daily activities behind.\n5. News reports on the damage caused by the earthquake.",
"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:\nTo extract relevant events related to the 2016 Gyeongju earthquake, we need to consider geological events that could be visualized in a video and are likely to occur in South Korea. This might include footage of earthquakes, damage to buildings, rescue efforts, and news coverage.\n\nEVENTS:\n1. A magnitude 5.8 earthquake strikes near Gyeongju, South Korea.\n2. People running out of buildings due to the sudden earthquake.\n3. Rescue workers searching for survivors under debris in the aftermath.\n4. Damage to ancient buildings and monuments in Gyeongju, a city known for its historical sites.\n5. Emergency vehicles and helicopters arriving on the scene in response to the earthquake.",
"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: \nGiven the query is about a specific earthquake event, the extracted events should focus on the immediate aftermath and the response to the earthquake. These events should be visualizable in a video and are directly related to the earthquake. The context is a natural disaster in a specific location, so it's reasonable to expect events like rescue operations, damage assessment, and media coverage.\n\nEVENTS:\n1. Rescue teams evacuating people from damaged buildings\n2. Emergency services treating injured people\n3. Aerial footage of the earthquake damage in Gyeongju, South Korea\n4. News reporters interviewing residents about their experiences during the earthquake\n5. Aerial view of the aftermath, showing destruction and debris",
"video_URL": "http://youtube.com/watch?v=n6UmQ9Kw2GQ",
"video_description": "경주 지진 이후 여진 307회 발생…\"강도 약해져\" 지난 12일 저녁 발생한 규모 5.8의 경주 지진 탓에 여진이 307차례 발생한 것으로 집계됐습니다. 기상청에 따르면 오늘 오후 4시까지 경주 지진 이후 여진은 규모 1.5∼3.0도 292회 등 모두 307차례 발생했습니다. 기상청 관계자는 \"경주 지진 탓에 여진이 계속 발생하고 있지만 강도가 약해지고 있다\"며 \"앞으로 일어날 여진 규모는 3.0 이하로 예상되기 때문에 그렇게 우려하지 않아도 될 것 같다\"고 말했습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "n6UmQ9Kw2GQ"
} | 16 | [
"The image shows a news broadcast with two news anchors wearing traditional Korean clothing. The screen behind them displays a weather map highlighting a region in South Korea, indicating a severe weather event. The text on the screen reads, \"경주 지진 이후 여진 307회 발생... '강도 약해져'\" which translates to \"Following the Gy... | n6UmQ9Kw2GQ | The video is a news broadcast discussing the aftermath of the Gyeongju earthquake, focusing on the experiences and perceptions of women in the affected areas. The broadcast initially highlights the 307 aftershocks that occurred following the earthquake and notes a decrease in intensity over time. The narrative shifts to explore the daily lives of women in the affected area, showcasing various settings such as a kitchen, a baby's room, and a personal living space, which emphasizes the long-term impacts of the earthquake on women and their resilience. The video also touches on logistics and delivery times, suggesting a broader discussion of the earthquake's effects on the community's daily life. The broadcast continues to report on the weather and other news, including a North Korean missile launch and a severe weather event in South Korea. |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"\"2016 Gyeongju earthquake in Gyeongju, South Korea on September 12, 2016\"",
"people running out of buildings in Gyeongju South Korea on September 12 2016.",
"Rescue workers searching for survivors under debris in Gyeongju, South Korea on September 12, 2016 after the 2016 Gyeongju earthquake.",
"\"Damage to... | [
"rescue teams evacuating people from damaged buildings in Gyeongju, South Korea on September 12, 2016.",
"Emergency services treating injured people in Gyeongju, South Korea on September 12, 2016.",
"aerial footage of the 2016 Gyeongju earthquake damage in Gyeongju, South Korea on September 12, 2016\"",
"\"Ne... | [
"\"2016 Gyeongju earthquake South Korea\"",
"Gyeongju earthquake 2016 buildings shake and collapse aftermath.",
"\"Rescue teams search for people trapped under debris after the 2016 Gyeongju earthquake in Gyeongju, South Korea on September 12, 2016.\"",
"Gyeongju earthquake evacuation September 12 2016\"",
... | {
"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:\nTo extract events related to the 2016 Gyeongju earthquake, we should focus on describing the natural disaster itself and its aftermath. This includes events that are likely to be visualized in a video, such as damage, rescue operations, and reactions from the public.\n\nEVENTS:\n1. Earthquake hits Gyeongju, South Korea.\n2. Buildings shake and collapse in the aftermath of the earthquake.\n3. Rescue teams search for people trapped under debris.\n4. People evacuate the area, leaving their daily activities behind.\n5. News reports on the damage caused by the earthquake.",
"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:\nTo extract relevant events related to the 2016 Gyeongju earthquake, we need to consider geological events that could be visualized in a video and are likely to occur in South Korea. This might include footage of earthquakes, damage to buildings, rescue efforts, and news coverage.\n\nEVENTS:\n1. A magnitude 5.8 earthquake strikes near Gyeongju, South Korea.\n2. People running out of buildings due to the sudden earthquake.\n3. Rescue workers searching for survivors under debris in the aftermath.\n4. Damage to ancient buildings and monuments in Gyeongju, a city known for its historical sites.\n5. Emergency vehicles and helicopters arriving on the scene in response to the earthquake.",
"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: \nGiven the query is about a specific earthquake event, the extracted events should focus on the immediate aftermath and the response to the earthquake. These events should be visualizable in a video and are directly related to the earthquake. The context is a natural disaster in a specific location, so it's reasonable to expect events like rescue operations, damage assessment, and media coverage.\n\nEVENTS:\n1. Rescue teams evacuating people from damaged buildings\n2. Emergency services treating injured people\n3. Aerial footage of the earthquake damage in Gyeongju, South Korea\n4. News reporters interviewing residents about their experiences during the earthquake\n5. Aerial view of the aftermath, showing destruction and debris",
"video_URL": "http://youtube.com/watch?v=uoagwCVoHGM",
"video_description": "경주 지진으로 8명 부상…재산피해 253건 어제 저녁 경주 일대에서 발생한 지진으로 인해 8명이 다치고 카카오톡과 국민안전처 홈페이지 등 통신망이 일시적으로 마비되는 등의 장애가 있었습니다. 국민안전처는 경주 일대에서 오늘과 어제에 걸쳐 일어난 지진으로 인해 80살 여성 황 모 씨 등 8명이 경상을 입고 253건의 재산피해가 신고됐다고 밝혔습니다. 이번 지진으로 인해 KTX 대전~부산 구간이 5분가량 정차하기도 했습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "uoagwCVoHGM"
} | 16 | [
"A news anchor in a purple blazer and light pink top is presenting a story. Behind her is a black-and-white surveillance image showing a scene with water, possibly from a flood, as it flows over a barrier. The image features several potted plants and a railing on the left side. The text on the screen, in Korean, me... | uoagwCVoHGM | A devastating earthquake, specifically the Gyeongju earthquake, has caused significant damage and injuries in the affected area. The incident resulted in 8 people being injured and 253 properties suffering damage. The video presents a comprehensive overview of the aftermath of the disaster, showcasing the extensive cleanup efforts, damage to buildings, and the ongoing recovery process. Scenes depict people sweeping debris, assessing structural damage, and navigating through the airport, highlighting the disruption to daily life and travel. The news anchor continues to provide updates on the situation, reinforcing the severity of the earthquake's impact on both individuals and property. The video emphasizes the need for continued recovery and restoration efforts to address the damage caused by the earthquake. |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"\"2016 Gyeongju earthquake in Gyeongju, South Korea on September 12, 2016\"",
"people running out of buildings in Gyeongju South Korea on September 12 2016.",
"Rescue workers searching for survivors under debris in Gyeongju, South Korea on September 12, 2016 after the 2016 Gyeongju earthquake.",
"\"Damage to... | [
"rescue teams evacuating people from damaged buildings in Gyeongju, South Korea on September 12, 2016.",
"Emergency services treating injured people in Gyeongju, South Korea on September 12, 2016.",
"aerial footage of the 2016 Gyeongju earthquake damage in Gyeongju, South Korea on September 12, 2016\"",
"\"Ne... | [
"\"2016 Gyeongju earthquake South Korea\"",
"Gyeongju earthquake 2016 buildings shake and collapse aftermath.",
"\"Rescue teams search for people trapped under debris after the 2016 Gyeongju earthquake in Gyeongju, South Korea on September 12, 2016.\"",
"Gyeongju earthquake evacuation September 12 2016\"",
... | {
"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:\nTo extract events related to the 2016 Gyeongju earthquake, we should focus on describing the natural disaster itself and its aftermath. This includes events that are likely to be visualized in a video, such as damage, rescue operations, and reactions from the public.\n\nEVENTS:\n1. Earthquake hits Gyeongju, South Korea.\n2. Buildings shake and collapse in the aftermath of the earthquake.\n3. Rescue teams search for people trapped under debris.\n4. People evacuate the area, leaving their daily activities behind.\n5. News reports on the damage caused by the earthquake.",
"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:\nTo extract relevant events related to the 2016 Gyeongju earthquake, we need to consider geological events that could be visualized in a video and are likely to occur in South Korea. This might include footage of earthquakes, damage to buildings, rescue efforts, and news coverage.\n\nEVENTS:\n1. A magnitude 5.8 earthquake strikes near Gyeongju, South Korea.\n2. People running out of buildings due to the sudden earthquake.\n3. Rescue workers searching for survivors under debris in the aftermath.\n4. Damage to ancient buildings and monuments in Gyeongju, a city known for its historical sites.\n5. Emergency vehicles and helicopters arriving on the scene in response to the earthquake.",
"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: \nGiven the query is about a specific earthquake event, the extracted events should focus on the immediate aftermath and the response to the earthquake. These events should be visualizable in a video and are directly related to the earthquake. The context is a natural disaster in a specific location, so it's reasonable to expect events like rescue operations, damage assessment, and media coverage.\n\nEVENTS:\n1. Rescue teams evacuating people from damaged buildings\n2. Emergency services treating injured people\n3. Aerial footage of the earthquake damage in Gyeongju, South Korea\n4. News reporters interviewing residents about their experiences during the earthquake\n5. Aerial view of the aftermath, showing destruction and debris",
"video_URL": "http://youtube.com/watch?v=5p1N4MtudiI",
"video_description": "경주 지진 316회 이어가다 현재는 '잠잠' 지난 12일 발생한 규모 5.8의 경주 지진의 여진이 316회 발생한 것으로 집계됐습니다. 기상청은 오늘 오전 11시 기준 여진 횟수가 316회라고 발표했습니다. 규모별 횟수는 1.5에서 3.0이 301차례, 3.0에서 4.0은 14차례, 4.0에서 5.0은 1차례 감지됐습니다. 사흘째 계속된 여진은 일단 멈추는 징후를 보이고 있는 것으로 기상청은 파악하고 있습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "5p1N4MtudiI"
} | 16 | [
"The image is a still from a news broadcast on EBS TV. Two presenters are standing in front of a cityscape backdrop, featuring a bridge over a river with buildings in the background. The presenters are dressed in traditional Korean hanbok attire. The text at the bottom of the screen in Korean mentions \"The 316th I... | 5p1N4MtudiI | A news broadcast on EBS TV, initially focusing on the 316th Invention Exhibition, which has not been held for 31 years, transitions into a report on severe weather and seismic activity. The video shows ongoing weather updates, including weather radar images, and eventually shifts to seismic activity analysis, displaying maps of the Korean Peninsula with data points indicating significant seismic activity. The text overlay throughout the video continues to mention "The 316th Invention Exhibition is now 'Deadlock'". |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"\"2016 Gyeongju earthquake in Gyeongju, South Korea on September 12, 2016\"",
"people running out of buildings in Gyeongju South Korea on September 12 2016.",
"Rescue workers searching for survivors under debris in Gyeongju, South Korea on September 12, 2016 after the 2016 Gyeongju earthquake.",
"\"Damage to... | [
"rescue teams evacuating people from damaged buildings in Gyeongju, South Korea on September 12, 2016.",
"Emergency services treating injured people in Gyeongju, South Korea on September 12, 2016.",
"aerial footage of the 2016 Gyeongju earthquake damage in Gyeongju, South Korea on September 12, 2016\"",
"\"Ne... | [
"\"2016 Gyeongju earthquake South Korea\"",
"Gyeongju earthquake 2016 buildings shake and collapse aftermath.",
"\"Rescue teams search for people trapped under debris after the 2016 Gyeongju earthquake in Gyeongju, South Korea on September 12, 2016.\"",
"Gyeongju earthquake evacuation September 12 2016\"",
... | {
"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:\nTo extract events related to the 2016 Gyeongju earthquake, we should focus on describing the natural disaster itself and its aftermath. This includes events that are likely to be visualized in a video, such as damage, rescue operations, and reactions from the public.\n\nEVENTS:\n1. Earthquake hits Gyeongju, South Korea.\n2. Buildings shake and collapse in the aftermath of the earthquake.\n3. Rescue teams search for people trapped under debris.\n4. People evacuate the area, leaving their daily activities behind.\n5. News reports on the damage caused by the earthquake.",
"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:\nTo extract relevant events related to the 2016 Gyeongju earthquake, we need to consider geological events that could be visualized in a video and are likely to occur in South Korea. This might include footage of earthquakes, damage to buildings, rescue efforts, and news coverage.\n\nEVENTS:\n1. A magnitude 5.8 earthquake strikes near Gyeongju, South Korea.\n2. People running out of buildings due to the sudden earthquake.\n3. Rescue workers searching for survivors under debris in the aftermath.\n4. Damage to ancient buildings and monuments in Gyeongju, a city known for its historical sites.\n5. Emergency vehicles and helicopters arriving on the scene in response to the earthquake.",
"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: \nGiven the query is about a specific earthquake event, the extracted events should focus on the immediate aftermath and the response to the earthquake. These events should be visualizable in a video and are directly related to the earthquake. The context is a natural disaster in a specific location, so it's reasonable to expect events like rescue operations, damage assessment, and media coverage.\n\nEVENTS:\n1. Rescue teams evacuating people from damaged buildings\n2. Emergency services treating injured people\n3. Aerial footage of the earthquake damage in Gyeongju, South Korea\n4. News reporters interviewing residents about their experiences during the earthquake\n5. Aerial view of the aftermath, showing destruction and debris",
"video_URL": "http://youtube.com/watch?v=roaxxb8zRLU",
"video_description": "국제신문 뉴스&이슈 구독하기 http://goo.gl/FFQL4 국제신문 근교산&기획특집 구독하기 http://goo.gl/SM0fM 국제신문 기사보기 http://iii.im/pk3Z 국제신문 영상팀이 경주 지진피해 복구 현장을 드론으로 담았다.",
"video_id": "roaxxb8zRLU"
} | 16 | [
"The image shows an aerial view of a traditional Korean village with numerous houses featuring black-tiled roofs. The text on the image is in Korean and reads \"하늘에서 본 경주\" (Jeju seen from the sky) and \"9.24일 도요미 경주시 황남동 일대\" (On September 24, Toyomi, Hwangnam-dong area of Gyeongju City). The view captures the den... | roaxxb8zRLU | The video is an aerial tour of the traditional Korean village of Gyeongju, showcasing its architecture and layout. The village is known for its black-tiled roofs and organized layout, with the surrounding mountains providing a picturesque backdrop. The video highlights several ongoing restoration efforts in the village, with workers actively engaged in repairing damaged buildings and roofs, using cranes and other equipment. The restoration work emphasizes the importance of preserving the village's historical structures.
The video also takes a break from the village to show the Gimseongdae park area, which is less crowded than usual, and Naemul Elementary School, which is historically significant due to its location near the epicenter of the Gyeongju earthquake. The video then shifts its focus to a rural area, highlighting the region's geographical context, including a winding road and the Wungsan Fault passing by the epicenter. The video ends with a logo for the South Korean newspaper "국제신문" (Kookje Shinmun), suggesting a transition to an informational segment about the newspaper. |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"\"2016 Gyeongju earthquake in Gyeongju, South Korea on September 12, 2016\"",
"people running out of buildings in Gyeongju South Korea on September 12 2016.",
"Rescue workers searching for survivors under debris in Gyeongju, South Korea on September 12, 2016 after the 2016 Gyeongju earthquake.",
"\"Damage to... | [
"rescue teams evacuating people from damaged buildings in Gyeongju, South Korea on September 12, 2016.",
"Emergency services treating injured people in Gyeongju, South Korea on September 12, 2016.",
"aerial footage of the 2016 Gyeongju earthquake damage in Gyeongju, South Korea on September 12, 2016\"",
"\"Ne... | [
"\"2016 Gyeongju earthquake South Korea\"",
"Gyeongju earthquake 2016 buildings shake and collapse aftermath.",
"\"Rescue teams search for people trapped under debris after the 2016 Gyeongju earthquake in Gyeongju, South Korea on September 12, 2016.\"",
"Gyeongju earthquake evacuation September 12 2016\"",
... | {
"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:\nTo extract events related to the 2016 Gyeongju earthquake, we should focus on describing the natural disaster itself and its aftermath. This includes events that are likely to be visualized in a video, such as damage, rescue operations, and reactions from the public.\n\nEVENTS:\n1. Earthquake hits Gyeongju, South Korea.\n2. Buildings shake and collapse in the aftermath of the earthquake.\n3. Rescue teams search for people trapped under debris.\n4. People evacuate the area, leaving their daily activities behind.\n5. News reports on the damage caused by the earthquake.",
"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:\nTo extract relevant events related to the 2016 Gyeongju earthquake, we need to consider geological events that could be visualized in a video and are likely to occur in South Korea. This might include footage of earthquakes, damage to buildings, rescue efforts, and news coverage.\n\nEVENTS:\n1. A magnitude 5.8 earthquake strikes near Gyeongju, South Korea.\n2. People running out of buildings due to the sudden earthquake.\n3. Rescue workers searching for survivors under debris in the aftermath.\n4. Damage to ancient buildings and monuments in Gyeongju, a city known for its historical sites.\n5. Emergency vehicles and helicopters arriving on the scene in response to the earthquake.",
"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: \nGiven the query is about a specific earthquake event, the extracted events should focus on the immediate aftermath and the response to the earthquake. These events should be visualizable in a video and are directly related to the earthquake. The context is a natural disaster in a specific location, so it's reasonable to expect events like rescue operations, damage assessment, and media coverage.\n\nEVENTS:\n1. Rescue teams evacuating people from damaged buildings\n2. Emergency services treating injured people\n3. Aerial footage of the earthquake damage in Gyeongju, South Korea\n4. News reporters interviewing residents about their experiences during the earthquake\n5. Aerial view of the aftermath, showing destruction and debris",
"video_URL": "http://youtube.com/watch?v=3ojHTwrvx90",
"video_description": "박 대통령, 경주 지진현장 방문 \"특별재난지역 선포\" 박근혜 대통령은 최근 강진이 잇따라 발생한 경북 경주 지역을 찾아 특별재난지역 선포를 적극 검토하라고 지시했습니다. 이어 지진 등 재난 안전 시스템을 원점에서 재점검할 것도 주문했습니다. 박 대통령은 아울러 인근 월성 원자력발전소를 찾아 \"원전은 단 한치의 실수도 용납되지 않는다\"며 지진 방재대책을 철저히 재점검해달라고 당부했습니다. 박 대통령의 지시에 국민안전처 또한 경주시를 특별재난지역으로 선포할 예정입니다. 특별재난지역으로 지정되면 지자체의 피해 복구비 부담이 완화되고, 피해 주민들은 공공요금 감면혜택을 받게됩니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "3ojHTwrvx90"
} | 16 | [
"The current frame features two news anchors presenting a news story. In the background, a group of people is gathered, with one woman in a yellow jacket speaking to the crowd. The text on the screen indicates the news is about President Park visiting a local community, mentioning a special voting area.",
"In the... | 3ojHTwrvx90 | President Park's delegation, recognizable by their yellow jackets, is actively engaged in overseeing a special voting area election event. They visit a community, specifically Jeonju Jihyun Hall, where a building with a damaged roof is covered by a blue tarp. The delegation appears to be discussing and coordinating efforts to ensure the smooth operation of the voting process in this area despite the challenges posed by the damaged building. The president's special deployment is likely aimed at addressing these challenges and ensuring that the election runs smoothly. Throughout the event, the delegation remains focused and engaged, possibly reviewing plans and strategies to resolve the issues at the damaged building and ensure a successful election process. |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | ["\"2016 Gyeongju earthquake in Gyeongju, South Korea on September 12, 2016\"","people running out o(...TRUNCATED) | ["rescue teams evacuating people from damaged buildings in Gyeongju, South Korea on September 12, 20(...TRUNCATED) | ["\"2016 Gyeongju earthquake South Korea\"","Gyeongju earthquake 2016 buildings shake and collapse a(...TRUNCATED) | {"article_url":"https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84","(...TRUNCATED) | 16 | ["A news anchor is delivering a report in front of a cityscape background. The text on the screen in(...TRUNCATED) | w6jdwGYcKZU | "The video begins with a news anchor delivering a report about a collision involving a government of(...TRUNCATED) |
End of preview. Expand
in Data Studio
README.md exists but content is empty.
- Downloads last month
- 12
Size of downloaded dataset files:
8.84 MB
Size of the auto-converted Parquet files:
8.84 MB
Number of rows:
2,394