Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual
Collection
Datasets used in the paper: Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video Retrieval • 37 items • Updated
query stringclasses 259 values | prequel listlengths 0 30 | sequel listlengths 0 30 | during listlengths 0 30 | metadata dict | num_of_frames int64 32 32 | frame_captions listlengths 32 32 | video_id stringlengths 6 45 | frame2video_caption stringlengths 287 3.07k | asr dict |
|---|---|---|---|---|---|---|---|---|---|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12... | [
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubb... | [
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 ea... | {
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=t8lY-rjy7-Y",
"video_description": "9월 12일, 경주에서는 역대 최대 규모인 5.8 지진이 일어났다. 지진으로 서울과 수도권까지 전국이 흔들렸고, 이로 인해 전화와 카카오톡도 모두 먹통이었다. 정부는 지진 발생 9분이 지나서야 긴급재난문자를 발송했고 이마저도 서울과 수도권 지역 국민들은 문자를 받지 못했다. #경주 #지진 #재난문자",
"video_id": "t8lY-rjy7-Y"
} | 32 | [
"The image shows a bustling street market in an urban setting at night, with people gathered around various stalls. The text on the image reads \"어제 저녁 7시 44분,\" which translates to \"yesterday evening at 7:44 PM.\" The scene depicts individuals walking, standing, and engaging in activities typical of a market, suc... | t8lY-rjy7-Y | The video depicts a series of scenes related to earthquake preparedness and response in South Korea. It begins with a bustling street market at night, followed by scenes of students participating in an earthquake drill in a classroom and a hallway. The drill appears to be part of a larger emergency preparedness exercise, as indicated by the involvement of various settings, including a train station and a storage room.
As the video progresses, it shifts to show the aftermath of an earthquake in Gyeongju, South Korea, with scenes of debris, destruction, and emergency responders. The footage includes news reports and official announcements, highlighting the severity of the earthquake and the government's response.
The latter part of the video focuses on governmental meetings and discussions, where officials address the earthquake situation, emphasizing the need for preparedness and learning from past experiences to better respond to future seismic events. The discussions also touch on criticism of the government's response to the earthquake, with calls for improved preparedness and emergency measures.
Throughout the video, the emphasis is on earthquake preparedness, response, and the importance of learning from past experiences to enhance safety measures for the future. The various scenes, from drills to governmental discussions, underscore the multifaceted approach to addressing natural disasters in South Korea. | {
"original": " I hope that the earthquake will be prepared for a bigger one in the future.",
"refined": "I hope that we will be better prepared for a bigger earthquake in the future.",
"summarized": "The speaker expresses a hope that preparations will be in place for a potentially larger earthquake in the future, and highlights the importance of predicting and preparing for great disasters, possibly referring to a specific event expected in 5 years.",
"translated": "I hope that we will be prepared for a bigger earthquake in the future.",
"translated_llm": "I hope that the earthquake will be prepared for a bigger one in the future.",
"translated_whisper": " The The The The The The The The The The The The The The The The The The The The The The The The The The The The The ... ... ... ... ... ... ... ... ... ... ... ... ... ... Even the most difficult thing is A huge disaster The disaster is coming And now we need more Great disasters to be predicted A new emergency in 5 years That day Now This place will be"
} |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12... | [
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubb... | [
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 ea... | {
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=CXe6_CDrdB8",
"video_description": "찐♡기상청사람들 예고 없이 찾아오는 지진! 한 번 발생하면 큰 피해를 주는 지진이기에 감시하는 일은 한시도 소홀히 할 수 없습니다. 그 최전방에서... 1년 365일 24시간 지진화산 감시 및 분석 업무에 최선을 다해 신속·정확하게 알리고자 노력하는 사람이 있습니다. 지진화산 감시 및 분석 업무 9년 차... 반복되는 주간 근무와 야간 근무가 힘들긴 하지만, 누구보다 묵묵하게 자리를 지키고 있는 진득한 뚝배기 같은 지진업무의 대들보!! 지진화산 감시 업무를 담당하는 기상청 사람을 만나고 왔습니다.(^_^)v 우리나라에서 가장 강력했던 규모 5.8의 경주 지진 때 지진감시 및 분석을 수행했던 기상청 사람은 누구? 지진감시 업무를 들어올 때마다 긴장되는 기상청 사람은 누구? 국민의 안전을 누구보다 걱정하는 기상청 사람은 누구? 지진 올바로 알고 지진 발생 시 빠르게 대처하길 바라는 기상청 사람은 누구? 최근 지진 안전을 홍보해 주시는 지진희 배우님을 그 누구보다 고마워하는 기상청 사람은 누구? 만나볼까요 :) #기상청사람들 #지진화산 #행동하는파수꾼",
"video_id": "CXe6_CDrdB8"
} | 32 | [
"In the current frame, a person is leaning over a desk in an office setting, seemingly focused on analyzing or reporting information on a computer. The visible text in the image includes \"기상청 사라남들\" which translates to \"Meteorological Office People\" and \"예고없이 찾아오는 지진 365일 근정하는 사람들편\" which translates to \"Peopl... | CXe6_CDrdB8 | The video depicts the work of individuals involved in earthquake monitoring and analysis, highlighting the importance of swift and accurate action in responding to seismic events. The setting is primarily an office or control room environment, where personnel are seen analyzing data on computer screens, discussing their findings, and collaborating on earthquake reports. The video focuses on a significant earthquake that occurred in Gyeongju, which was initially reported as a magnitude 1.1 but later determined to be much larger, at 5.8. The individuals involved express a sense of anxiety and tension due to the unpredictability of earthquakes and the critical nature of their work. Despite these challenges, they demonstrate a professional demeanor and a commitment to providing accurate and timely information. The video also touches on the use of early warning systems and the importance of quick response in earthquake management. Throughout, the atmosphere remains tense and focused, reflecting the high stakes and critical nature of earthquake analysis and response. The personnel involved take pride in their work, acknowledging the challenges and responsibilities that come with being in charge of earthquake duty, and they emphasize the need for precision and urgency in managing seismic data. | {
"original": " 국내 뿐만 아니라 국외에서 발생하는 지진을 분석을 해서 일정 규모 이상이 되면 통보를 하고 있고요. 더불어서 화산 정보를 제공을 하고 있습니다. 경제에서 발생한 지진인데요. 아찔한데요. 당시만 해도 규모가 큰 지진은 별로 없었거든요. 분석하고 있는 분은 엄청 떨리고 식은땀은 나고 일단 불안감이 먼저 앞섰습니다. 1.1의 지진을 통보를 했는데 40분, 50분 뒤에 앞서 발표한 지진보다 훨씬 큰 게 감이 오더라고요. 최대한 더 빨리 해야 되겠다 분석을 시작했는데 규모 5.8이 나왔어요. 충분히 만족을 하고 있습니다. 지진이 어느 시각에 발생할지 모르기 때문에 항상 불안하고 긴장감을 가지고 근무하고 있지만 지진을 맡고 있는 담당자의 숙명이라고 생각합니다. 지진이 배우님, 지진 업무를 담당하고 있는 사람으로서 고마움을 느끼고 있습니다. 화이팅입니다. 지진, 올바로 알아야 빠르게 대처할 수 있습니다. 지진은 신속정학입니다. 제가 그 신속정학의 중심에 서겠습니다",
"refined": "In Korea and abroad, we analyze earthquakes and report those that exceed a certain magnitude. Additionally, we provide volcanic information. I'm referring to the earthquake that occurred in the economy. It was quite alarming. At the time, there weren't many large earthquakes, so the analyst was extremely nervous and anxious. After reporting a 1.1 magnitude earthquake, we felt that a much larger one was coming 40 to 50 minutes later. We began analyzing as quickly as possible and determined it was a 5.8 magnitude earthquake. I'm satisfied with the results. Since earthquakes can occur at any time, I'm always anxious and on edge, but I consider it an occupational hazard. As someone in charge of earthquake duty, I feel grateful. I'll do my best to provide accurate information, as understanding earthquakes correctly is crucial for prompt action.",
"summarized": "The speaker is an earthquake analyst who monitors and reports earthquakes in Korea and other countries. They recall a particular earthquake in Gyeongju that initially seemed small, but later turned out to be much larger, with a magnitude of 5.8. The analyst expresses satisfaction with their work and acknowledges the anxiety and tension that comes with the job, but feels a sense of responsibility and gratitude for being able to contribute to public safety through their work. The speaker emphasizes the importance of accurate and rapid information about earthquakes to facilitate quick response and preparedness.",
"translated": "We analyze earthquakes not only in Korea but also in other countries, and if they exceed a certain magnitude, we report them. Additionally, we provide volcanic information. This is about an earthquake that occurred in the economic sector, which was quite shocking. At the time, there weren't many large earthquakes, so the person analyzing it was extremely nervous, sweating, and felt a great deal of anxiety. We reported an earthquake with a magnitude of 1.1, but 40 to 50 minutes later, it became clear that it was going to be much larger than initially announced. We began analyzing as quickly as possible and determined that the magnitude was 5.8. I'm satisfied with the result. Since we can't predict when an earthquake will occur, we always work with a sense of anxiety and tension, but I believe this is the nature of being in charge of earthquake duty. As someone responsible for earthquake work, I feel grateful. Earthquakes require swift and accurate action, so it's essential to understand them correctly. I will be at the forefront of this rapid response.",
"translated_llm": "The earthquake is a major economic event. It is a painful event. It was not a major earthquake at the time. The person who was analyzing it was very shaken and sweating and I was very anxious. I reported a 1.1 earthquake, but after 40 minutes, 50 minutes, I was told that it was going to be much bigger than the one I had announced earlier. I started the analysis as soon as possible and it was 5.8. I am satisfied.",
"translated_whisper": " What is the earthquake in Korea? We analyze earthquakes in Korea and other countries and if they are of a certain size, we report them. In addition, we provide damage information. This is an earthquake from Gyeongju. It's a bit dizzy. At that time, there weren't many large earthquakes. I was very nervous and cold when I was analyzing. I was worried at first. I reported an earthquake at 1.2. After 40 to 50 minutes, I felt that it was much bigger than the previous earthquake. I started analyzing and I got a 5.8 scale. Q. How do you feel about the earthquake? I'm satisfied with the results. I don't know what the earthquake will look like, so I'm always anxious and nervous. But I think it's the life of the person in charge of the earthquake. Q. How do you feel about the earthquake? As an earthquake actor, I feel grateful as a person in charge of the earthquake. I'm cheering for you. Q. What is the earthquake? You have to know the earthquake correctly to react quickly. The earthquake is a rapid earthquake. I will be the center of that rapid development."
} |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12... | [
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubb... | [
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 ea... | {
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=uF3x63vtddc",
"video_description": "\"경주 지진, 지하수는 1~2일 전에 미리 알았다\" 지난 12일과 19일 경주에서 규모 5.8을 비롯한 대형 지진이 잇따라 발생하기 하루 이틀 전 주변 지하수 수위가 크게 상승해, 향후 지진예측에 활용할 수 있다는 주장이 나왔습니다. 정상용 부경대 지구환경과학과 교수는 진앙에서 가장 가까운 경북 경주시 산내면에 있는 지하수 관측소 자료를 분석한 결과, 이 같이 밝혔습니다. 자료를 보면 지난 11일 암반 지하수 수위는 하루 사이에 무려 49㎝ 상승했고, 17일에도 39㎝나 올라갔습니다. 정 교수는 지진에 앞서 암석에 강한 압력이 가해져 지하수 수위가 많이 올라간 것으로 보인다며, 규모 4.5 이상의 지진에만 영향을 받았다고 설명했습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "uF3x63vtddc"
} | 32 | [
"In the current frame, two news anchors are presenting a news segment. The male anchor on the left is dressed in a suit with a tie, while the female anchor on the right is wearing a blazer with a white blouse. The background shows a newsroom setting with multiple monitors displaying various images and graphics. The... | uF3x63vtddc | The video discusses the potential for predicting earthquakes through changes in groundwater levels, focusing on the recent earthquakes in Gyeongju, South Korea. Two news anchors present a news segment on the topic, citing the work of Professor Jeong Sang-yong, who analyzed data from an underground water observation station near the epicenter of the earthquakes. The data showed significant rises in groundwater levels a day or two before the earthquakes, suggesting a possible correlation between groundwater level changes and earthquake prediction. The video includes footage of residential areas, surveillance camera views, and people working on rooftops, possibly repairing damage from the earthquakes. The overall context is one of scientific investigation and discussion about the potential for early warning systems for earthquakes based on groundwater level changes. The video aims to inform viewers about the research and its implications for earthquake prediction and preparedness. | {
"original": " 지난 11일과 19일 경주에서 규모 5.8을 비롯한 대형 지진이 잇따라 발생하기 하루 이틀 전, 주변 지하수의 수위가 크게 상승해 향후 지진 예측에 활용할 수 있다는 주장이 나왔습니다. 정상용 부경대 지구환경과학과 교수는 진앙에서 가장 가까운 경북 경주시 산내면에 있는 지하수 관측소 자료를 분석한 결과 이같이 밝혔습니다. 자료를 보면 지난 11일 안반 지하수 수위는 하루 사이에 무려 49cm가 상승했고, 17일에도 39cm나 올라갔습니다. 정 교수는 지진에 앞서 암석에 강한 압력이 가해져 지하수의 수위가 많이 올라간 것으로 보인다며 규모 4.5 이상의 지진에만 영향을 받았다고 설명했습니다.",
"refined": "On the 11th and 19th, large earthquakes, including a 5.8-magnitude quake, occurred in Gyeongju. A day or two before the earthquakes, the groundwater level in the surrounding area rose significantly, which could be useful for predicting future earthquakes. Professor Jung of the Department of Earth and Environmental Science at Pukyong National University analyzed data from a groundwater observation facility in Sanin-myeon, Gyeongju, closest to the epicenter. The data shows that the groundwater level in Anban rose by 49cm in one day on the 11th and by 39cm on the 17th. According to Professor Jung, strong pressure on the rock prior to the earthquake caused a significant rise in the groundwater level, which was only affected by earthquakes with a magnitude of 4.5 or higher.",
"summarized": "Research by Professor Jung of the Earth Environment Science department at Pukyong National University suggests that changes in underground water levels may be used to predict future earthquakes. Analyzing data from an underground water observation facility in Gyeongju, the professor found that the water level rose significantly, 49cm on the 11th and 39cm on the 17th, before recent large earthquakes in the area. According to Professor Jung, the increased water level is likely due to strong pressure on rocks before an earthquake, and this phenomenon is only observed with earthquakes of magnitude 4.5 or higher.",
"translated": "A day or two before the recent large earthquakes, including a 5.8-magnitude quake, struck Gyeongju on the 11th and 19th, the groundwater level in the surrounding area rose significantly, prompting claims that this phenomenon could be used to predict future earthquakes. Professor Jeong Sang-yong of the Department of Earth and Environmental Science at Pukyong National University analyzed data from an underground water observation station in Sanneom-myeon, Gyeongju, which is closest to the epicenter, and reported these findings. According to the data, the groundwater level in Anban rose by 49cm in just one day on the 11th and by 39cm on the 17th. Professor Jeong explained that the increase in groundwater level appeared to be caused by strong pressure on the rocks before the earthquake and that only earthquakes with a magnitude of 4.5 or higher had an impact.",
"translated_llm": "The data from the nearest underground water observatory in the mountains of North Korea, located in the heart of North Korea, showed that the underground water level rose by 49 cm in the past 11 days and rose by 39 cm on the 17th. The professor explained that the underground water level appeared to have risen a lot before the earthquake and that the earthquake was only affected by a strong pressure on the rocks.",
"translated_whisper": " On the 11th and 19th, a large earthquake of 5.8 in Gyeongju, two days before the earthquake, The number of underground water around the area has risen significantly, and it is estimated that it can be used to predict the future. Professor of Earth Environment Science at the National University of Gyeongju, Gyeongsang-do, The data of the underground water observation facility in the mountains in Gyeongju, which is the closest to the Jinhang, has been analyzed. According to the data, the underground water level in Anban was 49cm higher in a day on the 11th, and it rose to 39cm on the 17th. Professor Jung said that the strong pressure of the rock was applied to the earthquake, and the underground water level rose a lot, and that it was only affected by an earthquake of 4.5 or more."
} |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12... | [
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubb... | [
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 ea... | {
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=nln3QFJggKs",
"video_description": "106억 → 58억…경주 지진 피해금액 반토막 잇단 강진으로 100억원이 넘는 것으로 추정됐던 경주시의 공식 피해규모가 58억원 수준에 그치는 것으로 집계됐습니다. 경주시가 지진 발생 뒤 전수조사를 통해 발표한 잠정 추산 피해액은 약 107억원이었지만 사유재산 피해는 대부분 공식 피해액에서 빠졌습니다. 규정상 기와가 떨어지거나 벽체에 금이 가고 담장이 파손된 것은 재산피해 산정되지 않습니다. 이에 따라 사유재산 중에는 지진으로 주택이 완전히 부서지거나 반쯤 허물어진 것만 공식 피해액에 들어갔습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "nln3QFJggKs"
} | 32 | [
"The current frame shows two news anchors seated at a desk in a news studio. The male anchor is on the left wearing a dark suit and red tie, while the female anchor is on the right dressed in a blue blazer and light pink blouse. Behind them, there is a split-screen image: the left side shows a nighttime street scen... | nln3QFJggKs | The video depicts the aftermath of an earthquake in Gyeongju, South Korea, focusing on the assessment and revision of the official damage estimate. Initially expected to exceed 10 billion won, the estimate was revised downward to approximately 5.8 billion won following a thorough survey. The revision was due to the exclusion of private property damages such as cracks in walls, broken fences, and decreased building foundations, which are not considered official property damage according to regulations. Only cases of complete or partial destruction of homes were included in the official tally. The video shows news anchors discussing the revised estimate, aerial views of the city, and scenes of damaged buildings, roads, and infrastructure, highlighting the extent of the earthquake's impact. Workers are seen engaged in repair activities, such as replacing broken tiles on traditional Korean roofs, and individuals are inspecting damaged houses and public areas, including cracked sidewalks and roads. The video emphasizes the challenges in assessing and addressing the earthquake's impact, particularly in distinguishing between included and excluded types of damage in the official damage estimate. Overall, the video provides a detailed look at the earthquake's aftermath in Gyeongju, the revision of the damage estimate, and the ongoing efforts to repair and recover from the disaster. | {
"original": " 이딴 강진으로 100억 원이 넘는 것으로 추정됐던 경주시의 공식 피해 규모가 58억 원 수준에 그치는 것으로 집계됐습니다. 경주시가 지진 발생 뒤 전수조사를 통해 발표한 잠정추산 피해액은 약 107억 원이었지만 사유재산 피해는 대부분 공식 피해액에서 빠졌습니다. 규정상 기화가 떨어지거나 벽체에 금이 가고 담장이 파손된 것은 재산 피해로 산정되지 않습니다. 사유재산 중에는 지진으로 주택이 완전히 부서지거나 반쯤 허물어진 것만 공식 피해에게 들어갔습니다.",
"refined": "The official damage in Gyeongju, initially estimated to exceed 10 billion won, has been recalculated to around 5.8 billion won. Following a thorough investigation after the earthquake, the city reported a preliminary estimated damage of approximately 10.7 billion won, but most private property damage was excluded from the official total. According to regulations, damage such as cracks in walls or broken fences is not considered property damage. Only private properties that were completely destroyed or partially demolished due to the earthquake were included in the official damage report.",
"summarized": "Gyeongju city's official damage from the earthquake was estimated to be over 1 billion won, but the final calculation is around 580 million won. The initial estimate of 1.07 billion won was reduced as most private property damages, such as cracks in walls or broken fences, were not included due to regulations. Only severe cases of private property damage, such as completely or partially destroyed houses, were accounted for in the official damage total.",
"translated": "The official damage estimate for Gyeongju, initially expected to exceed 10 billion won, has been revised to approximately 5.8 billion won. Following a thorough survey after the earthquake, the city reported preliminary estimated damages of around 10.7 billion won. However, most private property damages were not included in the official tally. According to regulations, damages such as cracks in walls, broken fences, or decreased building foundations are not considered property damage. Only cases where homes were completely or partially destroyed due to the earthquake were counted in the official damage estimate.",
"translated_llm": "The official damage estimated by the city of 경주 to be over 10 billion won was estimated to be at 58 billion won. The estimated damage was about 107 billion won, but most of the damage was lost from the official damage.",
"translated_whisper": " The official damage of Gyeongju, which was estimated to be over 1 billion won, has reached the level of 5.8 billion won. The total damage of the dam was about 1.7 billion won, which was announced through a full-scale survey after the earthquake. But most of the damage to the property was removed from the official damage. According to the regulations, the damage to the dam is not determined as damage to the property. Accordingly, the property was damaged by an earthquake, or half of the property was destroyed."
} |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12... | [
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubb... | [
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 ea... | {
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=n6UmQ9Kw2GQ",
"video_description": "경주 지진 이후 여진 307회 발생…\"강도 약해져\" 지난 12일 저녁 발생한 규모 5.8의 경주 지진 탓에 여진이 307차례 발생한 것으로 집계됐습니다. 기상청에 따르면 오늘 오후 4시까지 경주 지진 이후 여진은 규모 1.5∼3.0도 292회 등 모두 307차례 발생했습니다. 기상청 관계자는 \"경주 지진 탓에 여진이 계속 발생하고 있지만 강도가 약해지고 있다\"며 \"앞으로 일어날 여진 규모는 3.0 이하로 예상되기 때문에 그렇게 우려하지 않아도 될 것 같다\"고 말했습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "n6UmQ9Kw2GQ"
} | 32 | [
"The current frame shows two news anchors presenting a report on an earthquake and its aftershocks. The anchor on the left is dressed in traditional Korean attire and appears to be reading from a script, while the anchor on the right, also in traditional attire, stands beside a map displaying seismic activity. The ... | n6UmQ9Kw2GQ | The video depicts the aftermath of a 5.8 magnitude earthquake that struck Gyeongju, focusing on the news coverage and the effects of the earthquake on daily life. The news anchors, dressed in traditional Korean attire, report on the earthquake and its 307 aftershocks, with the majority ranging from 1.5 to 3.0 in magnitude. The anchors stand in front of a cityscape background and beside a map displaying seismic activity, highlighting the location of the earthquake and its aftershocks.
The video transitions to CCTV footage of various indoor settings, including a hallway, a kitchen, and a living room, showing no significant damage or disturbance, emphasizing the resilience and normalcy of daily life despite the aftershocks. The footage also shows everyday objects, such as a baby bouncer and bottles of water, appearing undamaged and intact.
Throughout the video, the on-screen text reinforces the message that the intensity of the aftershocks is diminishing, with future aftershocks expected to have a magnitude of 3.0 or less, according to the Korea Meteorological Administration. The overall narrative suggests a gradual return to normalcy following the earthquake, with the video providing a coherent and reassuring account of the event and its aftermath. | {
"original": " 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 1.5에서 3.0도 292회 등 모두 307차례 발생했습니다. 기상청 관계자는 경주 지진 탓에 여진이 계속 발생하고 있지만 강도가 약해지고 있다며 앞으로 일어날 여진 규모는 3.0 이하로 예상되기 때문에 그렇게 우려하지 않아도 될 것 같다고 말했습니다.",
"refined": "On the evening of the 12th, a 5.8 magnitude earthquake occurred in Gyeongju, resulting in 307 aftershocks. According to the weather agency, as of 4 pm today, there have been 307 aftershocks with magnitudes ranging from 1.5 to 3.0 since the Gyeongju earthquake. An agency official stated that although aftershocks are continuing due to the Gyeongju earthquake, their intensity is weakening, and it is expected that future aftershocks will have a magnitude of 3.0 or less, so there is no need to worry.",
"summarized": "A magnitude 5.8 earthquake occurred in Gyeongju on the 12th, resulting in 307 aftershocks, with 292 of them ranging from 1.5 to 3.0 in magnitude. According to the Korea Meteorological Administration, although aftershocks are still occurring due to the earthquake, their intensity is weakening. Officials expect future aftershocks to have a magnitude of 3.0 or less, indicating no significant concern is warranted.",
"translated": "Following the 5.8 magnitude earthquake that struck Gyeongju on the evening of the 12th, a total of 307 aftershocks have been recorded. According to the Korea Meteorological Administration, as of 4 pm today, there have been 307 aftershocks, with 292 of them ranging from 1.5 to 3.0 in magnitude. An official from the Meteorological Administration noted that while aftershocks are still occurring due to the Gyeongju earthquake, their intensity is weakening, and it is expected that future aftershocks will have a magnitude of 3.0 or less, so there is no need for significant concern.",
"translated_llm": "The latest estimates are that 307 earthquakes have occurred due to the 5.8 magnitude earthquake that occurred on the 12th evening. According to the Meteorological Office, as of 4 pm today, the earthquake has caused 307 earthquakes ranging from 1.5 to 3.0 degrees and 292 rounds.",
"translated_whisper": " The last 12 days, there were 5.8 times of earthquakes in Gyeongju, and 307 times of the earthquake in Yeojin. According to the Ministry of Emergency Situations, Yeojin has been 3 times in Gyeongju since the earthquake in Gyeongju, from 1.5 to 3.0 degrees 292 times. The Kisangcheon official said that the earthquake is still happening due to the Gyeongju earthquake, but the intensity is getting weaker, and the expected earthquake size to occur in the future is 3.0 or less, so it is not necessary to worry."
} |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | ["People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",(...TRUNCATED) | ["Buildings collapsing or showing significant structural damage during the 12 September 2016 earthqu(...TRUNCATED) | ["People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 20(...TRUNCATED) | {"article_url":"https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84","(...TRUNCATED) | 32 | ["The current frame shows a news anchor standing in front of a large screen displaying a surveillanc(...TRUNCATED) | uoagwCVoHGM | "A news report covers the aftermath of an earthquake in the Gyeongju area, which resulted in 8 injur(...TRUNCATED) | {"original":" 어제저녁 경주 일대에서 발생한 지진으로 인해 8명이 다치고, 카(...TRUNCATED) |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | ["People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",(...TRUNCATED) | ["Buildings collapsing or showing significant structural damage during the 12 September 2016 earthqu(...TRUNCATED) | ["People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 20(...TRUNCATED) | {"article_url":"https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84","(...TRUNCATED) | 32 | ["The current frame shows two news anchors, a man and a woman, dressed in traditional Korean attire,(...TRUNCATED) | 5p1N4MtudiI | "The video appears to be a news broadcast discussing the aftermath of a 5.8-magnitude earthquake tha(...TRUNCATED) | {"original":" 지난 12일에 발생한 규모 5.8의 경주 지진의 여진이 316회 발생한 (...TRUNCATED) |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | ["People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",(...TRUNCATED) | ["Buildings collapsing or showing significant structural damage during the 12 September 2016 earthqu(...TRUNCATED) | ["People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 20(...TRUNCATED) | {"article_url":"https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84","(...TRUNCATED) | 32 | ["The frame depicts a traditional Korean neighborhood with a dense collection of buildings featuring(...TRUNCATED) | roaxxb8zRLU | "The video depicts the aftermath and recovery efforts following an earthquake in Gyeongju, South Kor(...TRUNCATED) | {"original":" ល្ពបានដោយើងមំខងានដំល ១ េការអណា(...TRUNCATED) |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | ["People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",(...TRUNCATED) | ["Buildings collapsing or showing significant structural damage during the 12 September 2016 earthqu(...TRUNCATED) | ["People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 20(...TRUNCATED) | {"article_url":"https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84","(...TRUNCATED) | 32 | ["The current frame shows a news broadcast discussing President Park Geun-hye's recent instructions (...TRUNCATED) | 3ojHTwrvx90 | "The video depicts President Park Geun-hye's response to a series of strong earthquakes in the Gyeon(...TRUNCATED) | {"original":" 박근혜 대통령이 최근 강진이 잇따라 발생한 경북 경주지역을 찾(...TRUNCATED) |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | ["People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",(...TRUNCATED) | ["Buildings collapsing or showing significant structural damage during the 12 September 2016 earthqu(...TRUNCATED) | ["People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 20(...TRUNCATED) | {"article_url":"https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84","(...TRUNCATED) | 32 | ["The frame shows a news presenter dressed in traditional attire standing in front of a cityscape ba(...TRUNCATED) | w6jdwGYcKZU | "A news report covers a 5.8 magnitude earthquake in Gyeongju, resulting in 23 injuries and 1,118 cas(...TRUNCATED) | {"original":" 국민안전처는 경주에서 발생한 규모 5.8의 지진으로 부상자 23명(...TRUNCATED) |
End of preview. Expand
in Data Studio
README.md exists but content is empty.
- Downloads last month
- 6
Size of downloaded dataset files:
20.9 MB
Size of the auto-converted Parquet files:
20.9 MB
Number of rows:
2,394