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 64 64 | frame_captions listlengths 64 64 | video_id stringlengths 6 45 | frame2video_caption stringlengths 575 3.49k | 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"
} | 64 | [
"The frame depicts a bustling street market with numerous people walking and interacting. Some individuals are seen conversing and pointing in various directions, while others are browsing stalls. The scene appears lively with a mix of adults and children engaged in various activities. The text overlay in the frame... | 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, which transitions into a chaotic evacuation scene, likely due to an earthquake drill or simulation. The evacuation scenes show people, possibly students, rushing down staircases and through hallways, emphasizing the urgency and panic of such situations.
As the video progresses, it shifts to a train station, where a train is stationary, and a post-earthquake inspection is being conducted. The scene then moves to a warehouse, highlighting preparedness and logistics, possibly in anticipation of or response to earthquakes.
The video also shows the impact of an earthquake on daily life, including damage, disruptions to transportation, and communication breakdowns. There are scenes of people trying to contact each other, with texts indicating difficulties in communication, such as "통화도 카카오톡도 불통" (Communication, KakaoTalk are also disconnected).
Government response and preparedness are significant themes, with scenes from the Blue House, the executive office of the South Korean government, showing officials discussing and addressing the situation. There's an emphasis on learning from the recent earthquake to better prepare for future seismic events, with a government official stating, "이번 지진을 교훈 삼아" (Taking this earthquake as a lesson).
The video also touches on criticism of the government's handling of the situation, with text overlays translating to "Incompetent government" and scenes of panic and chaos among the public, including students in a library and a classroom, underscoring the urgency and importance of effective earthquake preparedness and response measures.
Throughout the video, the emphasis is on preparedness for potential future earthquakes, with a focus on the government's role in ensuring public safety and the importance of learning from past experiences to improve response and mitigation strategies. The final message, as indicated by the Original ASR Transcript, reiterates the hope for better preparedness in the face of future seismic events, stating, "I hope that we will be prepared for a bigger earthquake in the future." | {
"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"
} | 64 | [
"In the current frame, an individual is working at a desk within a professional office environment. The person appears focused on their task, possibly analyzing data or information. The office has a modern setup with a wooden partition in the foreground, and the background shows windows with blinds, a map on the wa... | CXe6_CDrdB8 | The video depicts the work of earthquake monitoring and analysis personnel, particularly focusing on an individual who is part of a team responsible for analyzing and reporting seismic activity. The setting is a professional office environment with modern equipment, including computer monitors displaying seismic data, maps, and graphs. The individual, often dressed in a blue shirt and wearing glasses, is shown analyzing data, discussing findings with colleagues, and presenting information in front of screens displaying seismic activity.
The narrative revolves around the analysis of a significant earthquake that initially was reported with a magnitude of 1.1 but was later found to be much larger, at 5.8. The individual and their team work under a sense of urgency and anxiety to quickly and accurately determine the earthquake's magnitude and provide updated reports. The video highlights the challenges and responsibilities involved in earthquake duty, including the inability to predict when earthquakes will occur, which creates a constant sense of tension and anxiety among the team members.
Throughout the video, the importance of swift and accurate action in responding to seismic events is emphasized. The individual expresses gratitude for being part of this critical work and commits to being at the forefront of rapid earthquake response and understanding. The video concludes with the individual reaffirming their dedication to their role in earthquake monitoring and analysis, acknowledging the necessity of swift and accurate action in this field.
The overall context suggests that the video is educational or informative, aiming to provide insight into the work of earthquake monitoring personnel and the challenges they face. It underscores the critical nature of their work in providing timely and accurate information about seismic events, which is essential for public safety and awareness. | {
"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"
} | 64 | [
"In the current frame, a male and female news anchor are presenting a news segment in a television studio. The background features multiple screens displaying various images and data related to a news story. The visible text on the screen includes \"채널 23\" and \"연합뉴스TV,\" indicating the news channel and network. T... | uF3x63vtddc | The video depicts a news segment discussing the recent earthquakes in Gyeongju, South Korea, with a focus on the potential use of groundwater level changes as predictive indicators for seismic activity. The segment features two news anchors presenting in a television studio, with various screens displaying images and data related to the earthquakes. The discussion centers around the findings of Professor Jeong Sang-yong, who analyzed data from an underground water observation station and found significant rises in groundwater levels in the days leading up to the earthquakes. The video also shows surveillance footage of outdoor areas, possibly related to the research or monitoring facilities, and scenes of workers repairing traditional Korean roofs, highlighting the aftermath of the earthquakes. The text overlay throughout the video, "경주 지진, 지하수 1~2일 전에 미리 알았다" (Gyeongju Earthquake, Groundwater Predicted 1-2 Days in Advance), reinforces the theme of using groundwater level changes to predict earthquakes. The overall narrative emphasizes the importance of monitoring groundwater levels as a potential early warning system for seismic activity, as well as the ongoing response and recovery efforts in the affected areas. | {
"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",(...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) | 64 | ["The current frame shows a news broadcast featuring two anchors reporting on an ongoing event. In t(...TRUNCATED) | nln3QFJggKs | "The video report discusses the aftermath of the Gyeongju earthquake, focusing on the revised offici(...TRUNCATED) | {"original":" 이딴 강진으로 100억 원이 넘는 것으로 추정됐던 경주시의 공식 (...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) | 64 | ["The image shows two news anchors in traditional Korean attire, presenting a news segment on a tele(...TRUNCATED) | n6UmQ9Kw2GQ | "A news broadcast from Yonhap News TV reports on the aftermath of a 5.8 magnitude earthquake that st(...TRUNCATED) | {"original":" 지난 12일 저녁 발생한 규모 5.8의 경주 지진 탓에 여진이 307차례 (...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) | 64 | ["The current frame shows a news anchor standing in front of a large screen displaying a black-and-w(...TRUNCATED) | uoagwCVoHGM | "A news broadcast reports on an earthquake in the Gyeongju area, which resulted in 8 injuries and 25(...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) | 64 | ["The current frame shows two news anchors dressed in traditional Korean hanbok, reporting from a st(...TRUNCATED) | 5p1N4MtudiI | "The video is a news report about the aftershocks of a 5.8-magnitude earthquake that occurred in Gye(...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) | 64 | ["The current frame features a blurred view of a residential area with traditional Korean rooftops. (...TRUNCATED) | roaxxb8zRLU | "The video depicts the aftermath of an earthquake in Gyeongju, a city in South Korea, and the subseq(...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) | 64 | ["In the current frame, the news broadcast features an outdoor scene where a group of people, includ(...TRUNCATED) | 3ojHTwrvx90 | "The video depicts President Park Geun-hye's response to a series of strong earthquakes in Gyeongju,(...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) | 64 | ["A news anchor, dressed in traditional Korean attire, is reporting on an earthquake in Gyeongju. Th(...TRUNCATED) | w6jdwGYcKZU | "A news report covers the aftermath of a 5.8 magnitude earthquake in Gyeongju, where 23 people were (...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
- 5
Size of downloaded dataset files:
30.3 MB
Size of the auto-converted Parquet files:
30.3 MB
Number of rows:
2,394