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 36 | during listlengths 0 30 | metadata dict | num_of_frames int64 16 16 | frame_captions listlengths 16 16 | video_id stringlengths 6 45 | frame2video_caption stringlengths 277 2.52k |
|---|---|---|---|---|---|---|---|---|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"Buildings shaking in Gyeongju, South Korea during the 2016 Gyeongju earthquake.",
"\"Debris falling from buildings in Gyeongju, South Korea after 2016 Gyeongju earthquake.\"",
"\"2016 Gyeongju earthquake rescue efforts in South Korea.\"",
"Emergency vehicles at the scene of the 2016 Gyeongju earthquake in So... | [
"ground shaking during the 2016 Gyeongju earthquake in South Korea.",
"Buildings and structures collapsing due to the earthquake in Gyeongju, South Korea.",
"Debris from the 2016 Gyeongju earthquake in South Korea on September 12.",
"People running or seeking shelter during the 2016 Gyeongju earthquake in Sou... | [
"\"Gyeongju earthquake 2016 12 September\"",
"Buildings and structures collapsing or showing damage in Gyeongju, South Korea due to the 2016 Gyeongju earthquake on 12 September 2016.",
"People running or fleeing in fear near the epicenter of the 2016 Gyeongju earthquake in South Korea, Asia on September 12, 201... | {
"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: 16 Jan 2025\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION:\nTo extract events from the query, I will consider the geographic location and the nature of the event, taking into account that the event could be visualized in a video. I will extract events that are specific, concrete, and relevant to the query, such as events that occurred near Gyeongju, South Korea, and the earthquake itself.\n\nEVENTS:\n1. A magnitude 5.8 earthquake occurring near Gyeongju, South Korea\n2. Buildings and structures collapsing or showing damage in Gyeongju, South Korea\n3. People running or fleeing in fear near the epicenter of the earthquake\n4. Rescue workers or emergency responders arriving at the scene\n5. Emergency vehicles, such as ambulances or fire trucks, driving through the affected area",
"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: 16 Jan 2025\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION:\nTo extract relevant events related to the 2016 Gyeongju earthquake, we consider events that could be visually represented in a video and are closely related to the earthquake. These events should be concrete enough to be shown in a video, and the event text could serve as a reasonable caption for a frame of a video associated with the query.\n\nEVENTS:\n1. Buildings shaking\n2. Debris falling from buildings\n3. Rescue efforts\n4. Emergency vehicles at the scene\n5. Earthquake aftermath damage to buildings",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 16 Jan 2025\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:\n\nThe 2016 Gyeongju earthquake is an event that can be visualized in a video, as it involves a natural disaster that can cause destruction and movement of the earth. Considering the event's location in South Korea and its date, the extracted events should focus on the earthquake itself and its aftermath.\n\nEVENTS:\n\n1. The ground shaking during the earthquake\n2. Buildings and structures collapsing due to the earthquake\n3. Debris scattered on the ground\n4. People running or seeking shelter during the earthquake\n5. Rescue workers or emergency responders on the scene",
"video_URL": "http://youtube.com/watch?v=t8lY-rjy7-Y",
"video_description": "9월 12일, 경주에서는 역대 최대 규모인 5.8 지진이 일어났다. 지진으로 서울과 수도권까지 전국이 흔들렸고, 이로 인해 전화와 카카오톡도 모두 먹통이었다. 정부는 지진 발생 9분이 지나서야 긴급재난문자를 발송했고 이마저도 서울과 수도권 지역 국민들은 문자를 받지 못했다. #경주 #지진 #재난문자",
"video_id": "t8lY-rjy7-Y"
} | 16 | [
"The image shows a group of people, likely students, rushing down a hallway and up a staircase. They appear to be in a hurry, possibly evacuating the building. The timestamp on the image reads \"7시 44분,\" which indicates the time as 7:44 AM. The setting seems to be a school or similar institution.",
"The image sh... | t8lY-rjy7-Y | A group of students at a school were evacuated due to a 7:44 AM earthquake warning detected by the Korean railway system, which also affected the surrounding area. The earthquake caused widespread damage and disruption, with a 9.0 magnitude quake occurring near Gyeongju, 9 kilometers southwest. The school's response to the earthquake was characterized by a hurried evacuation, with students rushing down stairs and corridors. The situation outside the school was also affected, with debris scattered across the ground and caution tape cordoning off the area.
As the situation unfolded, the National Assembly's homepage was reportedly not functioning, and national security-related services were impacted. A government official or representative addressed the media, apologizing for any issues and offering reassurances. The situation was further complicated by a chaotic scene at the school, where students were shown to be confused and distressed.
The earthquake also led to a broader national response, with a president offering an apology for a specific incident involving a person named Yoon Seok-yeol. The aftermath of the earthquake was marked by widespread disruption and disarray, with students and officials struggling to cope with the situation. The overall context suggests a significant and potentially traumatic event that affected multiple aspects of life in South Korea. |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"Buildings shaking in Gyeongju, South Korea during the 2016 Gyeongju earthquake.",
"\"Debris falling from buildings in Gyeongju, South Korea after 2016 Gyeongju earthquake.\"",
"\"2016 Gyeongju earthquake rescue efforts in South Korea.\"",
"Emergency vehicles at the scene of the 2016 Gyeongju earthquake in So... | [
"ground shaking during the 2016 Gyeongju earthquake in South Korea.",
"Buildings and structures collapsing due to the earthquake in Gyeongju, South Korea.",
"Debris from the 2016 Gyeongju earthquake in South Korea on September 12.",
"People running or seeking shelter during the 2016 Gyeongju earthquake in Sou... | [
"\"Gyeongju earthquake 2016 12 September\"",
"Buildings and structures collapsing or showing damage in Gyeongju, South Korea due to the 2016 Gyeongju earthquake on 12 September 2016.",
"People running or fleeing in fear near the epicenter of the 2016 Gyeongju earthquake in South Korea, Asia on September 12, 201... | {
"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: 16 Jan 2025\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION:\nTo extract events from the query, I will consider the geographic location and the nature of the event, taking into account that the event could be visualized in a video. I will extract events that are specific, concrete, and relevant to the query, such as events that occurred near Gyeongju, South Korea, and the earthquake itself.\n\nEVENTS:\n1. A magnitude 5.8 earthquake occurring near Gyeongju, South Korea\n2. Buildings and structures collapsing or showing damage in Gyeongju, South Korea\n3. People running or fleeing in fear near the epicenter of the earthquake\n4. Rescue workers or emergency responders arriving at the scene\n5. Emergency vehicles, such as ambulances or fire trucks, driving through the affected area",
"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: 16 Jan 2025\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION:\nTo extract relevant events related to the 2016 Gyeongju earthquake, we consider events that could be visually represented in a video and are closely related to the earthquake. These events should be concrete enough to be shown in a video, and the event text could serve as a reasonable caption for a frame of a video associated with the query.\n\nEVENTS:\n1. Buildings shaking\n2. Debris falling from buildings\n3. Rescue efforts\n4. Emergency vehicles at the scene\n5. Earthquake aftermath damage to buildings",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 16 Jan 2025\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:\n\nThe 2016 Gyeongju earthquake is an event that can be visualized in a video, as it involves a natural disaster that can cause destruction and movement of the earth. Considering the event's location in South Korea and its date, the extracted events should focus on the earthquake itself and its aftermath.\n\nEVENTS:\n\n1. The ground shaking during the earthquake\n2. Buildings and structures collapsing due to the earthquake\n3. Debris scattered on the ground\n4. People running or seeking shelter during the earthquake\n5. Rescue workers or emergency responders on the scene",
"video_URL": "http://youtube.com/watch?v=CXe6_CDrdB8",
"video_description": "찐♡기상청사람들 예고 없이 찾아오는 지진! 한 번 발생하면 큰 피해를 주는 지진이기에 감시하는 일은 한시도 소홀히 할 수 없습니다. 그 최전방에서... 1년 365일 24시간 지진화산 감시 및 분석 업무에 최선을 다해 신속·정확하게 알리고자 노력하는 사람이 있습니다. 지진화산 감시 및 분석 업무 9년 차... 반복되는 주간 근무와 야간 근무가 힘들긴 하지만, 누구보다 묵묵하게 자리를 지키고 있는 진득한 뚝배기 같은 지진업무의 대들보!! 지진화산 감시 업무를 담당하는 기상청 사람을 만나고 왔습니다.(^_^)v 우리나라에서 가장 강력했던 규모 5.8의 경주 지진 때 지진감시 및 분석을 수행했던 기상청 사람은 누구? 지진감시 업무를 들어올 때마다 긴장되는 기상청 사람은 누구? 국민의 안전을 누구보다 걱정하는 기상청 사람은 누구? 지진 올바로 알고 지진 발생 시 빠르게 대처하길 바라는 기상청 사람은 누구? 최근 지진 안전을 홍보해 주시는 지진희 배우님을 그 누구보다 고마워하는 기상청 사람은 누구? 만나볼까요 :) #기상청사람들 #지진화산 #행동하는파수꾼",
"video_id": "CXe6_CDrdB8"
} | 16 | [
"In this frame, a man is standing in front of a wall of multiple monitors displaying various data and graphs. He is wearing a blue shirt and a white watch, and appears to be presenting or discussing the content on the screens. The text on the screen reads \"Q 엄무 소개?\" which translates to \"Q Introduction to work?\"... | CXe6_CDrdB8 | A professional or technical video appears to be a presentation or briefing about earthquake monitoring and analysis. The event revolves around the analysis of seismic data, particularly the largest earthquake ever recorded in Gyeongju, South Korea, with a magnitude of 5.8. The presentation focuses on the analysis of earthquake data, discussing speed and timing of forecasts compared to actual occurrences. The video showcases a team of professionals, possibly experts in monitoring and research, working together to interpret seismic data, using various tools and technologies, including computer software, data analysis, and seismic monitoring equipment.
The presentation emphasizes the importance of precise earthquake detection and timely responses, highlighting the significance of accurate data interpretation in enabling effective action. The team is seen working together, discussing and analyzing data, and presenting updates to an audience. The overall context suggests a professional or technical setting, possibly related to data analysis, monitoring, or emergency management. |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"Buildings shaking in Gyeongju, South Korea during the 2016 Gyeongju earthquake.",
"\"Debris falling from buildings in Gyeongju, South Korea after 2016 Gyeongju earthquake.\"",
"\"2016 Gyeongju earthquake rescue efforts in South Korea.\"",
"Emergency vehicles at the scene of the 2016 Gyeongju earthquake in So... | [
"ground shaking during the 2016 Gyeongju earthquake in South Korea.",
"Buildings and structures collapsing due to the earthquake in Gyeongju, South Korea.",
"Debris from the 2016 Gyeongju earthquake in South Korea on September 12.",
"People running or seeking shelter during the 2016 Gyeongju earthquake in Sou... | [
"\"Gyeongju earthquake 2016 12 September\"",
"Buildings and structures collapsing or showing damage in Gyeongju, South Korea due to the 2016 Gyeongju earthquake on 12 September 2016.",
"People running or fleeing in fear near the epicenter of the 2016 Gyeongju earthquake in South Korea, Asia on September 12, 201... | {
"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: 16 Jan 2025\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION:\nTo extract events from the query, I will consider the geographic location and the nature of the event, taking into account that the event could be visualized in a video. I will extract events that are specific, concrete, and relevant to the query, such as events that occurred near Gyeongju, South Korea, and the earthquake itself.\n\nEVENTS:\n1. A magnitude 5.8 earthquake occurring near Gyeongju, South Korea\n2. Buildings and structures collapsing or showing damage in Gyeongju, South Korea\n3. People running or fleeing in fear near the epicenter of the earthquake\n4. Rescue workers or emergency responders arriving at the scene\n5. Emergency vehicles, such as ambulances or fire trucks, driving through the affected area",
"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: 16 Jan 2025\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION:\nTo extract relevant events related to the 2016 Gyeongju earthquake, we consider events that could be visually represented in a video and are closely related to the earthquake. These events should be concrete enough to be shown in a video, and the event text could serve as a reasonable caption for a frame of a video associated with the query.\n\nEVENTS:\n1. Buildings shaking\n2. Debris falling from buildings\n3. Rescue efforts\n4. Emergency vehicles at the scene\n5. Earthquake aftermath damage to buildings",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 16 Jan 2025\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:\n\nThe 2016 Gyeongju earthquake is an event that can be visualized in a video, as it involves a natural disaster that can cause destruction and movement of the earth. Considering the event's location in South Korea and its date, the extracted events should focus on the earthquake itself and its aftermath.\n\nEVENTS:\n\n1. The ground shaking during the earthquake\n2. Buildings and structures collapsing due to the earthquake\n3. Debris scattered on the ground\n4. People running or seeking shelter during the earthquake\n5. Rescue workers or emergency responders on the scene",
"video_URL": "http://youtube.com/watch?v=uF3x63vtddc",
"video_description": "\"경주 지진, 지하수는 1~2일 전에 미리 알았다\" 지난 12일과 19일 경주에서 규모 5.8을 비롯한 대형 지진이 잇따라 발생하기 하루 이틀 전 주변 지하수 수위가 크게 상승해, 향후 지진예측에 활용할 수 있다는 주장이 나왔습니다. 정상용 부경대 지구환경과학과 교수는 진앙에서 가장 가까운 경북 경주시 산내면에 있는 지하수 관측소 자료를 분석한 결과, 이 같이 밝혔습니다. 자료를 보면 지난 11일 암반 지하수 수위는 하루 사이에 무려 49㎝ 상승했고, 17일에도 39㎝나 올라갔습니다. 정 교수는 지진에 앞서 암석에 강한 압력이 가해져 지하수 수위가 많이 올라간 것으로 보인다며, 규모 4.5 이상의 지진에만 영향을 받았다고 설명했습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "uF3x63vtddc"
} | 16 | [
"In the image, two news anchors are standing in a news studio. The male anchor is on the left and the female anchor is on the right. They appear to be delivering a news report. The studio background shows multiple screens displaying various images, likely from other news stories or related footage. \n\nThe text on ... | uF3x63vtddc | A news report discusses the aftermath of an earthquake that occurred in Gyeongju, South Korea. The earthquake, which happened 1-2 days prior to the event, was reportedly predicted by the groundwater level, which indicated the impending disaster. The news report features a series of surveillance footage from various locations in Gyeongju, showing the extent of the damage caused by the earthquake.
The footage depicts the damaged structures, flooded areas, and debris scattered throughout the city. The report also highlights an incident involving a machine that was operational for 1-2 days before the earthquake, which is the focus of the news story. The machine, likely a water pumping system, is shown to have been severely damaged or destroyed, contributing to the flooding in the area.
The report also features scenes of workers on the rooftops, attempting to repair or replace damaged air conditioning units and tiles, indicating the severity of the damage and the ongoing efforts to restore the city's infrastructure.
The news report provides a comprehensive overview of the situation in Gyeongju, highlighting the impact of the earthquake and the challenges faced by the community in the aftermath. The narrative is driven by the ongoing surveillance footage and news updates, providing a detailed and immersive account of the events. |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"Buildings shaking in Gyeongju, South Korea during the 2016 Gyeongju earthquake.",
"\"Debris falling from buildings in Gyeongju, South Korea after 2016 Gyeongju earthquake.\"",
"\"2016 Gyeongju earthquake rescue efforts in South Korea.\"",
"Emergency vehicles at the scene of the 2016 Gyeongju earthquake in So... | [
"ground shaking during the 2016 Gyeongju earthquake in South Korea.",
"Buildings and structures collapsing due to the earthquake in Gyeongju, South Korea.",
"Debris from the 2016 Gyeongju earthquake in South Korea on September 12.",
"People running or seeking shelter during the 2016 Gyeongju earthquake in Sou... | [
"\"Gyeongju earthquake 2016 12 September\"",
"Buildings and structures collapsing or showing damage in Gyeongju, South Korea due to the 2016 Gyeongju earthquake on 12 September 2016.",
"People running or fleeing in fear near the epicenter of the 2016 Gyeongju earthquake in South Korea, Asia on September 12, 201... | {
"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: 16 Jan 2025\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION:\nTo extract events from the query, I will consider the geographic location and the nature of the event, taking into account that the event could be visualized in a video. I will extract events that are specific, concrete, and relevant to the query, such as events that occurred near Gyeongju, South Korea, and the earthquake itself.\n\nEVENTS:\n1. A magnitude 5.8 earthquake occurring near Gyeongju, South Korea\n2. Buildings and structures collapsing or showing damage in Gyeongju, South Korea\n3. People running or fleeing in fear near the epicenter of the earthquake\n4. Rescue workers or emergency responders arriving at the scene\n5. Emergency vehicles, such as ambulances or fire trucks, driving through the affected area",
"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: 16 Jan 2025\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION:\nTo extract relevant events related to the 2016 Gyeongju earthquake, we consider events that could be visually represented in a video and are closely related to the earthquake. These events should be concrete enough to be shown in a video, and the event text could serve as a reasonable caption for a frame of a video associated with the query.\n\nEVENTS:\n1. Buildings shaking\n2. Debris falling from buildings\n3. Rescue efforts\n4. Emergency vehicles at the scene\n5. Earthquake aftermath damage to buildings",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 16 Jan 2025\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:\n\nThe 2016 Gyeongju earthquake is an event that can be visualized in a video, as it involves a natural disaster that can cause destruction and movement of the earth. Considering the event's location in South Korea and its date, the extracted events should focus on the earthquake itself and its aftermath.\n\nEVENTS:\n\n1. The ground shaking during the earthquake\n2. Buildings and structures collapsing due to the earthquake\n3. Debris scattered on the ground\n4. People running or seeking shelter during the earthquake\n5. Rescue workers or emergency responders on the scene",
"video_URL": "http://youtube.com/watch?v=nln3QFJggKs",
"video_description": "106억 → 58억…경주 지진 피해금액 반토막 잇단 강진으로 100억원이 넘는 것으로 추정됐던 경주시의 공식 피해규모가 58억원 수준에 그치는 것으로 집계됐습니다. 경주시가 지진 발생 뒤 전수조사를 통해 발표한 잠정 추산 피해액은 약 107억원이었지만 사유재산 피해는 대부분 공식 피해액에서 빠졌습니다. 규정상 기와가 떨어지거나 벽체에 금이 가고 담장이 파손된 것은 재산피해 산정되지 않습니다. 이에 따라 사유재산 중에는 지진으로 주택이 완전히 부서지거나 반쯤 허물어진 것만 공식 피해액에 들어갔습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "nln3QFJggKs"
} | 16 | [
"The image shows a news broadcast from Yonhap News TV, featuring two news anchors. The male anchor on the left is dressed in a dark suit and red tie, while the female anchor on the right wears a blue blazer over a pink top. Both are standing in front of a backdrop depicting a nighttime street scene. There is a larg... | nln3QFJggKs | The video is a news broadcast reporting on the aftermath of a significant earthquake in Gyeongju, South Korea, where two anchors discuss the estimated damage costs and provide updates on the recovery efforts. The video shows aerial views of the city, highlighting the extensive damage caused by the earthquake, including destroyed buildings, debris, and cracked infrastructure. The anchors, a male and female, provide a mix of updates on the estimated damage costs, which have been reduced from 106 billion to 58 billion won, and the ongoing recovery efforts, including construction and repair work. The video also captures scenes of debris-filled streets, damaged buildings, and community members gathering essential supplies. The anchors discuss the impact of the earthquake, focusing on the structural damage and the need for immediate attention to prevent further deterioration. The video also highlights the cultural significance of some damaged buildings, emphasizing the importance of conducting safety inspections. Overall, the video provides a comprehensive overview of the earthquake's impact and the community's response to the disaster. |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"Buildings shaking in Gyeongju, South Korea during the 2016 Gyeongju earthquake.",
"\"Debris falling from buildings in Gyeongju, South Korea after 2016 Gyeongju earthquake.\"",
"\"2016 Gyeongju earthquake rescue efforts in South Korea.\"",
"Emergency vehicles at the scene of the 2016 Gyeongju earthquake in So... | [
"ground shaking during the 2016 Gyeongju earthquake in South Korea.",
"Buildings and structures collapsing due to the earthquake in Gyeongju, South Korea.",
"Debris from the 2016 Gyeongju earthquake in South Korea on September 12.",
"People running or seeking shelter during the 2016 Gyeongju earthquake in Sou... | [
"\"Gyeongju earthquake 2016 12 September\"",
"Buildings and structures collapsing or showing damage in Gyeongju, South Korea due to the 2016 Gyeongju earthquake on 12 September 2016.",
"People running or fleeing in fear near the epicenter of the 2016 Gyeongju earthquake in South Korea, Asia on September 12, 201... | {
"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: 16 Jan 2025\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION:\nTo extract events from the query, I will consider the geographic location and the nature of the event, taking into account that the event could be visualized in a video. I will extract events that are specific, concrete, and relevant to the query, such as events that occurred near Gyeongju, South Korea, and the earthquake itself.\n\nEVENTS:\n1. A magnitude 5.8 earthquake occurring near Gyeongju, South Korea\n2. Buildings and structures collapsing or showing damage in Gyeongju, South Korea\n3. People running or fleeing in fear near the epicenter of the earthquake\n4. Rescue workers or emergency responders arriving at the scene\n5. Emergency vehicles, such as ambulances or fire trucks, driving through the affected area",
"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: 16 Jan 2025\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION:\nTo extract relevant events related to the 2016 Gyeongju earthquake, we consider events that could be visually represented in a video and are closely related to the earthquake. These events should be concrete enough to be shown in a video, and the event text could serve as a reasonable caption for a frame of a video associated with the query.\n\nEVENTS:\n1. Buildings shaking\n2. Debris falling from buildings\n3. Rescue efforts\n4. Emergency vehicles at the scene\n5. Earthquake aftermath damage to buildings",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 16 Jan 2025\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:\n\nThe 2016 Gyeongju earthquake is an event that can be visualized in a video, as it involves a natural disaster that can cause destruction and movement of the earth. Considering the event's location in South Korea and its date, the extracted events should focus on the earthquake itself and its aftermath.\n\nEVENTS:\n\n1. The ground shaking during the earthquake\n2. Buildings and structures collapsing due to the earthquake\n3. Debris scattered on the ground\n4. People running or seeking shelter during the earthquake\n5. Rescue workers or emergency responders on the scene",
"video_URL": "http://youtube.com/watch?v=n6UmQ9Kw2GQ",
"video_description": "경주 지진 이후 여진 307회 발생…\"강도 약해져\" 지난 12일 저녁 발생한 규모 5.8의 경주 지진 탓에 여진이 307차례 발생한 것으로 집계됐습니다. 기상청에 따르면 오늘 오후 4시까지 경주 지진 이후 여진은 규모 1.5∼3.0도 292회 등 모두 307차례 발생했습니다. 기상청 관계자는 \"경주 지진 탓에 여진이 계속 발생하고 있지만 강도가 약해지고 있다\"며 \"앞으로 일어날 여진 규모는 3.0 이하로 예상되기 때문에 그렇게 우려하지 않아도 될 것 같다\"고 말했습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "n6UmQ9Kw2GQ"
} | 16 | [
"The image shows a news broadcast with two news anchors wearing traditional Korean clothing. The screen behind them displays a weather map highlighting a region in South Korea, indicating a severe weather event. The text on the screen reads, \"경주 지진 이후 여진 307회 발생... '강도 약해져'\" which translates to \"Following the Gy... | n6UmQ9Kw2GQ | A news broadcast discussing the aftermath of the Gyeongju earthquake, which occurred in South Korea, provides a detailed account of the severe weather event and its ongoing impacts on the local population, particularly women. The video showcases a series of frames highlighting the immediate aftermath, including reports on aftershocks, the effects on daily life, and the resilience of the community. The narrative focuses on the experiences of women in the affected areas, discussing the decrease in the intensity of the earthquake's effects over time. The video also touches on logistics and delivery times, suggesting that the earthquake has affected the daily routines and challenges faced by residents. Overall, the video provides a comprehensive look at the long-term impacts of the Gyeongju earthquake on women in South Korea, highlighting both the challenges and the resilience of the community. |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"Buildings shaking in Gyeongju, South Korea during the 2016 Gyeongju earthquake.",
"\"Debris falling from buildings in Gyeongju, South Korea after 2016 Gyeongju earthquake.\"",
"\"2016 Gyeongju earthquake rescue efforts in South Korea.\"",
"Emergency vehicles at the scene of the 2016 Gyeongju earthquake in So... | [
"ground shaking during the 2016 Gyeongju earthquake in South Korea.",
"Buildings and structures collapsing due to the earthquake in Gyeongju, South Korea.",
"Debris from the 2016 Gyeongju earthquake in South Korea on September 12.",
"People running or seeking shelter during the 2016 Gyeongju earthquake in Sou... | [
"\"Gyeongju earthquake 2016 12 September\"",
"Buildings and structures collapsing or showing damage in Gyeongju, South Korea due to the 2016 Gyeongju earthquake on 12 September 2016.",
"People running or fleeing in fear near the epicenter of the 2016 Gyeongju earthquake in South Korea, Asia on September 12, 201... | {
"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: 16 Jan 2025\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION:\nTo extract events from the query, I will consider the geographic location and the nature of the event, taking into account that the event could be visualized in a video. I will extract events that are specific, concrete, and relevant to the query, such as events that occurred near Gyeongju, South Korea, and the earthquake itself.\n\nEVENTS:\n1. A magnitude 5.8 earthquake occurring near Gyeongju, South Korea\n2. Buildings and structures collapsing or showing damage in Gyeongju, South Korea\n3. People running or fleeing in fear near the epicenter of the earthquake\n4. Rescue workers or emergency responders arriving at the scene\n5. Emergency vehicles, such as ambulances or fire trucks, driving through the affected area",
"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: 16 Jan 2025\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION:\nTo extract relevant events related to the 2016 Gyeongju earthquake, we consider events that could be visually represented in a video and are closely related to the earthquake. These events should be concrete enough to be shown in a video, and the event text could serve as a reasonable caption for a frame of a video associated with the query.\n\nEVENTS:\n1. Buildings shaking\n2. Debris falling from buildings\n3. Rescue efforts\n4. Emergency vehicles at the scene\n5. Earthquake aftermath damage to buildings",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 16 Jan 2025\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:\n\nThe 2016 Gyeongju earthquake is an event that can be visualized in a video, as it involves a natural disaster that can cause destruction and movement of the earth. Considering the event's location in South Korea and its date, the extracted events should focus on the earthquake itself and its aftermath.\n\nEVENTS:\n\n1. The ground shaking during the earthquake\n2. Buildings and structures collapsing due to the earthquake\n3. Debris scattered on the ground\n4. People running or seeking shelter during the earthquake\n5. Rescue workers or emergency responders on the scene",
"video_URL": "http://youtube.com/watch?v=uoagwCVoHGM",
"video_description": "경주 지진으로 8명 부상…재산피해 253건 어제 저녁 경주 일대에서 발생한 지진으로 인해 8명이 다치고 카카오톡과 국민안전처 홈페이지 등 통신망이 일시적으로 마비되는 등의 장애가 있었습니다. 국민안전처는 경주 일대에서 오늘과 어제에 걸쳐 일어난 지진으로 인해 80살 여성 황 모 씨 등 8명이 경상을 입고 253건의 재산피해가 신고됐다고 밝혔습니다. 이번 지진으로 인해 KTX 대전~부산 구간이 5분가량 정차하기도 했습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "uoagwCVoHGM"
} | 16 | [
"A news anchor in a purple blazer and light pink top is presenting a story. Behind her is a black-and-white surveillance image showing a scene with water, possibly from a flood, as it flows over a barrier. The image features several potted plants and a railing on the left side. The text on the screen, in Korean, me... | uoagwCVoHGM | A devastating earthquake, referred to as the Gyeongju earthquake, has occurred in a specific area. The video captures the aftermath of the disaster, providing an overview of the impact on both individuals and property. The incident resulted in 8 injuries and 253 reported property damages. The event is being reported by a news anchor, who presents updates on the situation through a combination of news footage and on-screen text.
The video begins with a black-and-white surveillance image of water flowing over a barrier, suggesting a flood or strong currents. This is followed by a close-up view of a damaged indoor area, showcasing the extent of the destruction. The scene shifts to a chaotic and disorganized environment, with debris and rubble scattered throughout, as people work to assess the damage and conduct cleanup efforts.
As the video progresses, it becomes clear that the earthquake has affected multiple locations, including a store, a building, and an airport. The scenes depict the severity of the damage, with cracked walls, destroyed structures, and people working to restore order. The presence of a news anchor and the use of on-screen text emphasize the ongoing reporting of the incident.
The video also captures the response efforts, showing people working to clean up debris, assess damage, and provide aid. The airport scene shows individuals walking through the terminal, suggesting an evacuation or response process. The video concludes with a news broadcast logo, further emphasizing the importance of disseminating information to the public about the disaster.
Throughout the video, the focus remains on the human impact of the earthquake, with a strong emphasis on the 8 reported injuries and 253 property damages. The overall context suggests a significant natural disaster, and the video serves as a documentation of the aftermath and response efforts. |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"Buildings shaking in Gyeongju, South Korea during the 2016 Gyeongju earthquake.",
"\"Debris falling from buildings in Gyeongju, South Korea after 2016 Gyeongju earthquake.\"",
"\"2016 Gyeongju earthquake rescue efforts in South Korea.\"",
"Emergency vehicles at the scene of the 2016 Gyeongju earthquake in So... | [
"ground shaking during the 2016 Gyeongju earthquake in South Korea.",
"Buildings and structures collapsing due to the earthquake in Gyeongju, South Korea.",
"Debris from the 2016 Gyeongju earthquake in South Korea on September 12.",
"People running or seeking shelter during the 2016 Gyeongju earthquake in Sou... | [
"\"Gyeongju earthquake 2016 12 September\"",
"Buildings and structures collapsing or showing damage in Gyeongju, South Korea due to the 2016 Gyeongju earthquake on 12 September 2016.",
"People running or fleeing in fear near the epicenter of the 2016 Gyeongju earthquake in South Korea, Asia on September 12, 201... | {
"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: 16 Jan 2025\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION:\nTo extract events from the query, I will consider the geographic location and the nature of the event, taking into account that the event could be visualized in a video. I will extract events that are specific, concrete, and relevant to the query, such as events that occurred near Gyeongju, South Korea, and the earthquake itself.\n\nEVENTS:\n1. A magnitude 5.8 earthquake occurring near Gyeongju, South Korea\n2. Buildings and structures collapsing or showing damage in Gyeongju, South Korea\n3. People running or fleeing in fear near the epicenter of the earthquake\n4. Rescue workers or emergency responders arriving at the scene\n5. Emergency vehicles, such as ambulances or fire trucks, driving through the affected area",
"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: 16 Jan 2025\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION:\nTo extract relevant events related to the 2016 Gyeongju earthquake, we consider events that could be visually represented in a video and are closely related to the earthquake. These events should be concrete enough to be shown in a video, and the event text could serve as a reasonable caption for a frame of a video associated with the query.\n\nEVENTS:\n1. Buildings shaking\n2. Debris falling from buildings\n3. Rescue efforts\n4. Emergency vehicles at the scene\n5. Earthquake aftermath damage to buildings",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 16 Jan 2025\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:\n\nThe 2016 Gyeongju earthquake is an event that can be visualized in a video, as it involves a natural disaster that can cause destruction and movement of the earth. Considering the event's location in South Korea and its date, the extracted events should focus on the earthquake itself and its aftermath.\n\nEVENTS:\n\n1. The ground shaking during the earthquake\n2. Buildings and structures collapsing due to the earthquake\n3. Debris scattered on the ground\n4. People running or seeking shelter during the earthquake\n5. Rescue workers or emergency responders on the scene",
"video_URL": "http://youtube.com/watch?v=5p1N4MtudiI",
"video_description": "경주 지진 316회 이어가다 현재는 '잠잠' 지난 12일 발생한 규모 5.8의 경주 지진의 여진이 316회 발생한 것으로 집계됐습니다. 기상청은 오늘 오전 11시 기준 여진 횟수가 316회라고 발표했습니다. 규모별 횟수는 1.5에서 3.0이 301차례, 3.0에서 4.0은 14차례, 4.0에서 5.0은 1차례 감지됐습니다. 사흘째 계속된 여진은 일단 멈추는 징후를 보이고 있는 것으로 기상청은 파악하고 있습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "5p1N4MtudiI"
} | 16 | [
"The image is a still from a news broadcast on EBS TV. Two presenters are standing in front of a cityscape backdrop, featuring a bridge over a river with buildings in the background. The presenters are dressed in traditional Korean hanbok attire. The text at the bottom of the screen in Korean mentions \"The 316th I... | 5p1N4MtudiI | A news broadcast on EBS TV is being interrupted due to a significant seismic event. The 316th Invention Exhibition, a significant event that has not been held for 31 years, is now in a state of "Deadlock." A detailed analysis of seismic activity is being conducted on a computer screen, with a focus on monitoring and tracking the impact of the earthquake on the Korean Peninsula. The event is being closely followed, with updates displayed on the screen, including temperature, time, and data points related to seismic activity. The analysis is centered around a significant seismic event with a magnitude of 3.1, and a depth of 20.0 km. The event has been reported to have caused a red dot on a map, which is being tracked by the analysts. The broadcast is also discussing the impact of the event on public discourse, with 2,000 comments being received regarding the 20th National Assembly. The event is being closely monitored, with the analysts providing updates in real-time. |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"Buildings shaking in Gyeongju, South Korea during the 2016 Gyeongju earthquake.",
"\"Debris falling from buildings in Gyeongju, South Korea after 2016 Gyeongju earthquake.\"",
"\"2016 Gyeongju earthquake rescue efforts in South Korea.\"",
"Emergency vehicles at the scene of the 2016 Gyeongju earthquake in So... | [
"ground shaking during the 2016 Gyeongju earthquake in South Korea.",
"Buildings and structures collapsing due to the earthquake in Gyeongju, South Korea.",
"Debris from the 2016 Gyeongju earthquake in South Korea on September 12.",
"People running or seeking shelter during the 2016 Gyeongju earthquake in Sou... | [
"\"Gyeongju earthquake 2016 12 September\"",
"Buildings and structures collapsing or showing damage in Gyeongju, South Korea due to the 2016 Gyeongju earthquake on 12 September 2016.",
"People running or fleeing in fear near the epicenter of the 2016 Gyeongju earthquake in South Korea, Asia on September 12, 201... | {
"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: 16 Jan 2025\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION:\nTo extract events from the query, I will consider the geographic location and the nature of the event, taking into account that the event could be visualized in a video. I will extract events that are specific, concrete, and relevant to the query, such as events that occurred near Gyeongju, South Korea, and the earthquake itself.\n\nEVENTS:\n1. A magnitude 5.8 earthquake occurring near Gyeongju, South Korea\n2. Buildings and structures collapsing or showing damage in Gyeongju, South Korea\n3. People running or fleeing in fear near the epicenter of the earthquake\n4. Rescue workers or emergency responders arriving at the scene\n5. Emergency vehicles, such as ambulances or fire trucks, driving through the affected area",
"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: 16 Jan 2025\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION:\nTo extract relevant events related to the 2016 Gyeongju earthquake, we consider events that could be visually represented in a video and are closely related to the earthquake. These events should be concrete enough to be shown in a video, and the event text could serve as a reasonable caption for a frame of a video associated with the query.\n\nEVENTS:\n1. Buildings shaking\n2. Debris falling from buildings\n3. Rescue efforts\n4. Emergency vehicles at the scene\n5. Earthquake aftermath damage to buildings",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 16 Jan 2025\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:\n\nThe 2016 Gyeongju earthquake is an event that can be visualized in a video, as it involves a natural disaster that can cause destruction and movement of the earth. Considering the event's location in South Korea and its date, the extracted events should focus on the earthquake itself and its aftermath.\n\nEVENTS:\n\n1. The ground shaking during the earthquake\n2. Buildings and structures collapsing due to the earthquake\n3. Debris scattered on the ground\n4. People running or seeking shelter during the earthquake\n5. Rescue workers or emergency responders on the scene",
"video_URL": "http://youtube.com/watch?v=roaxxb8zRLU",
"video_description": "국제신문 뉴스&이슈 구독하기 http://goo.gl/FFQL4 국제신문 근교산&기획특집 구독하기 http://goo.gl/SM0fM 국제신문 기사보기 http://iii.im/pk3Z 국제신문 영상팀이 경주 지진피해 복구 현장을 드론으로 담았다.",
"video_id": "roaxxb8zRLU"
} | 16 | [
"The image shows an aerial view of a traditional Korean village with numerous houses featuring black-tiled roofs. The text on the image is in Korean and reads \"하늘에서 본 경주\" (Jeju seen from the sky) and \"9.24일 도요미 경주시 황남동 일대\" (On September 24, Toyomi, Hwangnam-dong area of Gyeongju City). The view captures the den... | roaxxb8zRLU | The video showcases a traditional Korean village, Gyeongju, in South Korea, which was severely affected by the 9.24 Gyeongju earthquake. The sequence of aerial views highlights the village's layout, showcasing black-tiled roofs, mountains, and lush greenery. The frames reveal a community effort to restore and preserve the village's heritage through various repair and reconstruction works. Workers are seen on rooftops, in the process of fixing damaged structures, with the aid of cranes and tarps.
The frames also capture the beauty of the surrounding landscape, including the Gimseongdae, a historic monument and cultural site, and a school affected by the earthquake. The video includes aerial views of rural areas, fault lines, and a winding road, emphasizing the geographical context of the region.
The frames transition to a newspaper logo, "국제신문" (Kookje Shinmun), indicating a shift from the aerial views to an informational segment about the newspaper. This suggests that the video may be discussing the role of the newspaper in covering the earthquake and its aftermath, providing insights into the local news and community responses.
The overall essence of the video revolves around the impact of the earthquake on the Gyeongju region, the community's efforts to restore and preserve the village's heritage, and the role of local media in reporting on the disaster. |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | [
"Buildings shaking in Gyeongju, South Korea during the 2016 Gyeongju earthquake.",
"\"Debris falling from buildings in Gyeongju, South Korea after 2016 Gyeongju earthquake.\"",
"\"2016 Gyeongju earthquake rescue efforts in South Korea.\"",
"Emergency vehicles at the scene of the 2016 Gyeongju earthquake in So... | [
"ground shaking during the 2016 Gyeongju earthquake in South Korea.",
"Buildings and structures collapsing due to the earthquake in Gyeongju, South Korea.",
"Debris from the 2016 Gyeongju earthquake in South Korea on September 12.",
"People running or seeking shelter during the 2016 Gyeongju earthquake in Sou... | [
"\"Gyeongju earthquake 2016 12 September\"",
"Buildings and structures collapsing or showing damage in Gyeongju, South Korea due to the 2016 Gyeongju earthquake on 12 September 2016.",
"People running or fleeing in fear near the epicenter of the 2016 Gyeongju earthquake in South Korea, Asia on September 12, 201... | {
"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: 16 Jan 2025\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION:\nTo extract events from the query, I will consider the geographic location and the nature of the event, taking into account that the event could be visualized in a video. I will extract events that are specific, concrete, and relevant to the query, such as events that occurred near Gyeongju, South Korea, and the earthquake itself.\n\nEVENTS:\n1. A magnitude 5.8 earthquake occurring near Gyeongju, South Korea\n2. Buildings and structures collapsing or showing damage in Gyeongju, South Korea\n3. People running or fleeing in fear near the epicenter of the earthquake\n4. Rescue workers or emergency responders arriving at the scene\n5. Emergency vehicles, such as ambulances or fire trucks, driving through the affected area",
"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: 16 Jan 2025\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION:\nTo extract relevant events related to the 2016 Gyeongju earthquake, we consider events that could be visually represented in a video and are closely related to the earthquake. These events should be concrete enough to be shown in a video, and the event text could serve as a reasonable caption for a frame of a video associated with the query.\n\nEVENTS:\n1. Buildings shaking\n2. Debris falling from buildings\n3. Rescue efforts\n4. Emergency vehicles at the scene\n5. Earthquake aftermath damage to buildings",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 16 Jan 2025\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:\n\nThe 2016 Gyeongju earthquake is an event that can be visualized in a video, as it involves a natural disaster that can cause destruction and movement of the earth. Considering the event's location in South Korea and its date, the extracted events should focus on the earthquake itself and its aftermath.\n\nEVENTS:\n\n1. The ground shaking during the earthquake\n2. Buildings and structures collapsing due to the earthquake\n3. Debris scattered on the ground\n4. People running or seeking shelter during the earthquake\n5. Rescue workers or emergency responders on the scene",
"video_URL": "http://youtube.com/watch?v=3ojHTwrvx90",
"video_description": "박 대통령, 경주 지진현장 방문 \"특별재난지역 선포\" 박근혜 대통령은 최근 강진이 잇따라 발생한 경북 경주 지역을 찾아 특별재난지역 선포를 적극 검토하라고 지시했습니다. 이어 지진 등 재난 안전 시스템을 원점에서 재점검할 것도 주문했습니다. 박 대통령은 아울러 인근 월성 원자력발전소를 찾아 \"원전은 단 한치의 실수도 용납되지 않는다\"며 지진 방재대책을 철저히 재점검해달라고 당부했습니다. 박 대통령의 지시에 국민안전처 또한 경주시를 특별재난지역으로 선포할 예정입니다. 특별재난지역으로 지정되면 지자체의 피해 복구비 부담이 완화되고, 피해 주민들은 공공요금 감면혜택을 받게됩니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "3ojHTwrvx90"
} | 16 | [
"The current frame features two news anchors presenting a news story. In the background, a group of people is gathered, with one woman in a yellow jacket speaking to the crowd. The text on the screen indicates the news is about President Park visiting a local community, mentioning a special voting area.",
"In the... | 3ojHTwrvx90 | President Park's delegation, consisting of officials and staff dressed in yellow jackets, visits a special voting area in Jeonju, where a 'special voting area election' is taking place. The group is actively engaged in ensuring the smooth operation of the voting process, despite a damaged building at the site. They coordinate efforts to address the situation, review plans, and discuss strategies to overcome the challenges posed by the damaged building. The delegation is led by President Park, who is attending the event to oversee the voting process. The group's collective efforts are focused on ensuring the elections run smoothly, as indicated by the repeated display of "President Park, special voting area election 'special deployment'". |
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea. | ["Buildings shaking in Gyeongju, South Korea during the 2016 Gyeongju earthquake.","\"Debris falling(...TRUNCATED) | ["ground shaking during the 2016 Gyeongju earthquake in South Korea.","Buildings and structures coll(...TRUNCATED) | ["\"Gyeongju earthquake 2016 12 September\"","Buildings and structures collapsing or showing damage (...TRUNCATED) | {"article_url":"https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84","(...TRUNCATED) | 16 | ["A news anchor is delivering a report in front of a cityscape background. The text on the screen in(...TRUNCATED) | w6jdwGYcKZU | "A news report covers the aftermath of an earthquake that hit Gyeongju, a city in South Korea, resul(...TRUNCATED) |
End of preview. Expand
in Data Studio
README.md exists but content is empty.
- Downloads last month
- 18
Size of downloaded dataset files:
8.8 MB
Size of the auto-converted Parquet files:
8.8 MB
Number of rows:
2,394