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
•
36 items
•
Updated
query
stringclasses 259
values | prequel
listlengths 0
30
| sequel
listlengths 0
30
| during
listlengths 0
30
| metadata
dict | num_of_frames
int64 2
2
| frame_captions
listlengths 2
2
| video_id
stringlengths 6
45
| frame2video_caption
stringlengths 88
950
|
|---|---|---|---|---|---|---|---|---|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=t8lY-rjy7-Y",
"video_description": "9월 12일, 경주에서는 역대 최대 규모인 5.8 지진이 일어났다. 지진으로 서울과 수도권까지 전국이 흔들렸고, 이로 인해 전화와 카카오톡도 모두 먹통이었다. 정부는 지진 발생 9분이 지나서야 긴급재난문자를 발송했고 이마저도 서울과 수도권 지역 국민들은 문자를 받지 못했다. #경주 #지진 #재난문자",
"video_id": "t8lY-rjy7-Y"
}
| 2
|
[
"The image shows a black-and-white night vision video of a child lying in bed, partially covered by a blanket. A person is leaning over the child, possibly checking on them. The text at the bottom of the image reads \"서울과 수도권까지 전국이 흐들려,\" which translates to \"The entire country is shaking, including Seoul and the metropolitan area.\"",
"The image shows a black-and-white night vision video of a person leaning over a child in bed, continuing to check on them. The child is partially covered by a blanket. The text at the bottom of the image reads \"서울과 수도권까지 전국이 흐들려,\" which translates to \"The entire country is shaking, including Seoul and the metropolitan area.\""
] |
t8lY-rjy7-Y
|
A person is checking on a child who is lying in bed, in a scene captured by a black-and-white night vision video. The context suggests a significant event is occurring, with the text indicating that the entire country, including Seoul and the metropolitan area, is experiencing disturbances or upheaval, but the focus of the video remains on the person's concern for the child's well-being.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=CXe6_CDrdB8",
"video_description": "찐♡기상청사람들 예고 없이 찾아오는 지진! 한 번 발생하면 큰 피해를 주는 지진이기에 감시하는 일은 한시도 소홀히 할 수 없습니다. 그 최전방에서... 1년 365일 24시간 지진화산 감시 및 분석 업무에 최선을 다해 신속·정확하게 알리고자 노력하는 사람이 있습니다. 지진화산 감시 및 분석 업무 9년 차... 반복되는 주간 근무와 야간 근무가 힘들긴 하지만, 누구보다 묵묵하게 자리를 지키고 있는 진득한 뚝배기 같은 지진업무의 대들보!! 지진화산 감시 업무를 담당하는 기상청 사람을 만나고 왔습니다.(^_^)v 우리나라에서 가장 강력했던 규모 5.8의 경주 지진 때 지진감시 및 분석을 수행했던 기상청 사람은 누구? 지진감시 업무를 들어올 때마다 긴장되는 기상청 사람은 누구? 국민의 안전을 누구보다 걱정하는 기상청 사람은 누구? 지진 올바로 알고 지진 발생 시 빠르게 대처하길 바라는 기상청 사람은 누구? 최근 지진 안전을 홍보해 주시는 지진희 배우님을 그 누구보다 고마워하는 기상청 사람은 누구? 만나볼까요 :) #기상청사람들 #지진화산 #행동하는파수꾼",
"video_id": "CXe6_CDrdB8"
}
| 2
|
[
"The image shows a man standing in front of a large screen displaying various charts and data. The man is wearing glasses, a blue shirt, and a watch on his left wrist. He has a lanyard with an ID badge around his neck. The screen behind him features Korean text and data charts, indicating that he is likely discussing or presenting information related to the content displayed on the screen. The text at the bottom reads, '최대한 더 빨리 (문성) 해야겠다,' which translates to 'I need to do it as quickly as possible (Moon Sung).' The setting appears to be an office or a control room environment.",
"The man is still standing in front of the large screen, which continues to display various charts and data. He appears to be speaking, possibly elaborating on the data presented. The text at the bottom of the image repeats '최대한 더 빨리 (문성) 해야겠다,' reinforcing the urgency of the situation he is addressing. The background and his posture suggest he is making a detailed presentation or analysis."
] |
CXe6_CDrdB8
|
A man, identified as Moon Sung, stands in front of a large screen in an office or control room setting, presenting and analyzing data displayed on the screen, which includes Korean text and charts. He emphasizes the need to take action as quickly as possible, suggesting a sense of urgency in the situation he is addressing.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=uF3x63vtddc",
"video_description": "\"경주 지진, 지하수는 1~2일 전에 미리 알았다\" 지난 12일과 19일 경주에서 규모 5.8을 비롯한 대형 지진이 잇따라 발생하기 하루 이틀 전 주변 지하수 수위가 크게 상승해, 향후 지진예측에 활용할 수 있다는 주장이 나왔습니다. 정상용 부경대 지구환경과학과 교수는 진앙에서 가장 가까운 경북 경주시 산내면에 있는 지하수 관측소 자료를 분석한 결과, 이 같이 밝혔습니다. 자료를 보면 지난 11일 암반 지하수 수위는 하루 사이에 무려 49㎝ 상승했고, 17일에도 39㎝나 올라갔습니다. 정 교수는 지진에 앞서 암석에 강한 압력이 가해져 지하수 수위가 많이 올라간 것으로 보인다며, 규모 4.5 이상의 지진에만 영향을 받았다고 설명했습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "uF3x63vtddc"
}
| 2
|
[
"The image appears to be a still frame from a news broadcast, showing a segment with text overlay in Korean. In the background, there is an indoor setting featuring a decorative mirror and air conditioning units. The text overlay at the bottom indicates the news channel and time, \"연합뉴스TV\" and \"09:35,\" and there is Korean text that translates to \"Police investigation: The suspect was under the influence 1-2 days before the accident.\" The image suggests a focus on a news story related to a police investigation involving a suspect who was intoxicated before an incident.",
"The current frame continues the news broadcast segment with an indoor setting in the background, including a decorative mirror and air conditioning units. The text overlay at the bottom reads \"경주 지진, 지하수는 1~2일 전에 미리 알았다\" which translates to \"Gyeongju earthquake, groundwater detected 1-2 days before.\" This suggests the news story has shifted to cover the Gyeongju earthquake, indicating that there was an early detection of groundwater changes before the earthquake occurred. The scene maintains continuity with the previous news story focus, while updating the viewer with new information related to the earthquake."
] |
uF3x63vtddc
|
A news broadcast shows a segment discussing two separate incidents: a police investigation into an accident involving a suspect who was under the influence 1-2 days prior, and the Gyeongju earthquake, where groundwater changes were detected 1-2 days before the quake. The news anchor presents the information in a studio setting, with updates and details about both stories displayed as text overlays on the screen.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=nln3QFJggKs",
"video_description": "106억 → 58억…경주 지진 피해금액 반토막 잇단 강진으로 100억원이 넘는 것으로 추정됐던 경주시의 공식 피해규모가 58억원 수준에 그치는 것으로 집계됐습니다. 경주시가 지진 발생 뒤 전수조사를 통해 발표한 잠정 추산 피해액은 약 107억원이었지만 사유재산 피해는 대부분 공식 피해액에서 빠졌습니다. 규정상 기와가 떨어지거나 벽체에 금이 가고 담장이 파손된 것은 재산피해 산정되지 않습니다. 이에 따라 사유재산 중에는 지진으로 주택이 완전히 부서지거나 반쯤 허물어진 것만 공식 피해액에 들어갔습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "nln3QFJggKs"
}
| 2
|
[
"The image shows a group of people standing outside a traditional building with a tiled roof. One person is on a ladder, seemingly working on the building, while another is standing on the ground, holding an object, possibly a tool or container. A third individual is sitting nearby, and another is standing beside them, observing the work. The setting appears to be a rural or semi-rural area. Text on the image suggests a news segment, mentioning a location in Gyeongju and a discussion about the impact of a public announcement regarding a project.",
"The current frame focuses on a close-up view of a wall with pink tiles. There is a visible crack along the top edge where the tiles meet the ceiling, indicating structural damage or wear. The bottom edge of the tiles also shows signs of deterioration and peeling. The setting appears to be indoors, possibly in a room undergoing inspection or renovation. The image includes text overlays, with one indicating a location in Gyeongju and another displaying the time as 17:03. The text suggests that this is part of a news segment, discussing the impact of a public announcement regarding a project."
] |
nln3QFJggKs
|
A news segment is reporting on the impact of a public announcement regarding a project in Gyeongju, a rural or semi-rural area. The video shows a traditional building with a tiled roof, where a group of people are gathered, with one person working on the building using a ladder and another holding an object, possibly a tool or container. The building is undergoing inspection or renovation, as evidenced by a close-up view of a wall with pink tiles showing structural damage and deterioration. The context suggests that the project announcement has prompted an examination of the building's condition, with the news segment aiming to discuss the implications of this project on the local area.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=n6UmQ9Kw2GQ",
"video_description": "경주 지진 이후 여진 307회 발생…\"강도 약해져\" 지난 12일 저녁 발생한 규모 5.8의 경주 지진 탓에 여진이 307차례 발생한 것으로 집계됐습니다. 기상청에 따르면 오늘 오후 4시까지 경주 지진 이후 여진은 규모 1.5∼3.0도 292회 등 모두 307차례 발생했습니다. 기상청 관계자는 \"경주 지진 탓에 여진이 계속 발생하고 있지만 강도가 약해지고 있다\"며 \"앞으로 일어날 여진 규모는 3.0 이하로 예상되기 때문에 그렇게 우려하지 않아도 될 것 같다\"고 말했습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "n6UmQ9Kw2GQ"
}
| 2
|
[
"The image shows a hanging light fixture with a decorative pattern, mounted on a ceiling. Text in Korean at the bottom of the image reads \"경주 지진 이후 여진 307회 발생...\" and \"강도 약해져\" which translates to \"After the Gyeongju earthquake, 307 aftershocks occurred...\" and \"The intensity is weakening.\" The text suggests that the image is related to reporting on seismic activity, specifically aftershocks following an earthquake in Gyeongju.",
"The current frame shows another view of the same hanging light fixture with a decorative pattern on the ceiling. The light fixture appears to be swaying slightly. The text at the bottom of the image remains the same: \"경주 지진 이후 여진 307회 발생...\" and \"강도 약해져\" which translates to \"After the Gyeongju earthquake, 307 aftershocks occurred...\" and \"The intensity is weakening.\" This suggests the video is still reporting on the aftershocks following the Gyeongju earthquake, with the swaying light fixture possibly indicating recent seismic activity."
] |
n6UmQ9Kw2GQ
|
The video appears to be a news report or update on the aftermath of the Gyeongju earthquake, specifically focusing on the occurrence of aftershocks. It shows a hanging light fixture on a ceiling, initially stationary and then swaying slightly, which may indicate recent seismic activity. The text overlay, in Korean, informs viewers that 307 aftershocks have occurred since the initial earthquake and that their intensity is weakening, providing context to the gentle swaying of the light fixture. The overall setting suggests an indoor environment, possibly a news studio or a building affected by the earthquake, where the impact of the aftershocks is being visually represented through the movement of the light fixture.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=uoagwCVoHGM",
"video_description": "경주 지진으로 8명 부상…재산피해 253건 어제 저녁 경주 일대에서 발생한 지진으로 인해 8명이 다치고 카카오톡과 국민안전처 홈페이지 등 통신망이 일시적으로 마비되는 등의 장애가 있었습니다. 국민안전처는 경주 일대에서 오늘과 어제에 걸쳐 일어난 지진으로 인해 80살 여성 황 모 씨 등 8명이 경상을 입고 253건의 재산피해가 신고됐다고 밝혔습니다. 이번 지진으로 인해 KTX 대전~부산 구간이 5분가량 정차하기도 했습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "uoagwCVoHGM"
}
| 2
|
[
"In the image, a person is sweeping a floor with a green broom. The text on the screen is in Korean, stating that the person has been fired 253 times for making mistakes and injuring eight people.",
"The image shows three people walking together in a hallway. Two of them are wearing casual clothes and one is wearing a blue jacket. The text on the screen is in Korean, providing details about a specific event related to a car accident and a legal case. The people in the image appear to be in a discussion or conversation as they walk."
] |
uoagwCVoHGM
|
A person, who has a history of making mistakes and injuring others, is shown performing a menial task, sweeping the floor. This individual is then seen walking and discussing an event, possibly related to a car accident and a legal case, with two other people, suggesting a narrative that may involve consequences or repercussions of the person's past actions, potentially leading to a resolution or a new development in the storyline.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=5p1N4MtudiI",
"video_description": "경주 지진 316회 이어가다 현재는 '잠잠' 지난 12일 발생한 규모 5.8의 경주 지진의 여진이 316회 발생한 것으로 집계됐습니다. 기상청은 오늘 오전 11시 기준 여진 횟수가 316회라고 발표했습니다. 규모별 횟수는 1.5에서 3.0이 301차례, 3.0에서 4.0은 14차례, 4.0에서 5.0은 1차례 감지됐습니다. 사흘째 계속된 여진은 일단 멈추는 징후를 보이고 있는 것으로 기상청은 파악하고 있습니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "5p1N4MtudiI"
}
| 2
|
[
"The image shows a computer screen displaying a seismograph with multiple lines indicating seismic activity. The text on the screen is in Korean and mentions \"연합뉴스TV 고속도로 예상 소요시간 서울>목포 7시간 10분,\" which translates to \"Yonhap News TV Estimated travel time on expressways Seoul> Mokpo 7 hours 10 minutes.\" Additionally, there is a news ticker at the bottom with the text \"경주 지진 316회 이어가다 현재는 '잠잠',\" translating to \"Gyeongju earthquake continues for 316 times, currently 'calm'.\" This suggests that the image is part of a news broadcast discussing seismic activity and travel times on expressways.",
"The image continues to show the computer screen displaying a seismograph with multiple lines indicating ongoing seismic activity. The text in the top right corner reads \"연합뉴스TV 고속도로 예상 소요시간 서울>목포 7시간 10분,\" which translates to \"Yonhap News TV Estimated travel time on expressways Seoul> Mokpo 7 hours 10 minutes.\" Additionally, the news ticker at the bottom reiterates \"경주 지진 316회 이어가다 현재는 '잠잠',\" which translates to \"Gyeongju earthquake continues for 316 times, currently 'calm'.\" This suggests that the image is still part of the news broadcast discussing the ongoing seismic activity and travel times on expressways."
] |
5p1N4MtudiI
|
A news broadcast is displaying a seismograph showing ongoing seismic activity, with a focus on the Gyeongju earthquake that has continued for 316 times and is currently calm. The broadcast also provides estimated travel times on expressways, specifically from Seoul to Mokpo, which is expected to take 7 hours and 10 minutes. The video appears to be a static shot of a computer screen showing the seismograph and news ticker, with no changes or updates in the information being displayed between the observed frames.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=roaxxb8zRLU",
"video_description": "국제신문 뉴스&이슈 구독하기 http://goo.gl/FFQL4 국제신문 근교산&기획특집 구독하기 http://goo.gl/SM0fM 국제신문 기사보기 http://iii.im/pk3Z 국제신문 영상팀이 경주 지진피해 복구 현장을 드론으로 담았다.",
"video_id": "roaxxb8zRLU"
}
| 2
|
[
"A group of workers wearing safety helmets and reflective vests are on the roof of a building, working with large blue tarps. They are using ropes to secure and handle the tarps. The text in the image suggests that they are likely engaged in some type of construction or maintenance work.",
"A group of workers wearing safety helmets and reflective vests are on the roof of a traditional tiled building. They are handling and securing a large blue tarp, possibly as part of construction or maintenance work to protect the structure. The workers appear to be coordinating their efforts to manage the tarp effectively. The scene takes place in an overcast environment, suggesting potential weather-related work or preparations."
] |
roaxxb8zRLU
|
A group of construction workers, wearing safety helmets and reflective vests, are performing maintenance or repair work on the roof of a traditional tiled building. They are using large blue tarps, which they carefully secure and handle using ropes, likely to protect the structure from potential weather conditions, given the overcast environment. The workers are coordinating their efforts to manage the tarps effectively, suggesting a collaborative and potentially weather-related construction or maintenance project.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=3ojHTwrvx90",
"video_description": "박 대통령, 경주 지진현장 방문 \"특별재난지역 선포\" 박근혜 대통령은 최근 강진이 잇따라 발생한 경북 경주 지역을 찾아 특별재난지역 선포를 적극 검토하라고 지시했습니다. 이어 지진 등 재난 안전 시스템을 원점에서 재점검할 것도 주문했습니다. 박 대통령은 아울러 인근 월성 원자력발전소를 찾아 \"원전은 단 한치의 실수도 용납되지 않는다\"며 지진 방재대책을 철저히 재점검해달라고 당부했습니다. 박 대통령의 지시에 국민안전처 또한 경주시를 특별재난지역으로 선포할 예정입니다. 특별재난지역으로 지정되면 지자체의 피해 복구비 부담이 완화되고, 피해 주민들은 공공요금 감면혜택을 받게됩니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "3ojHTwrvx90"
}
| 2
|
[
"The image shows a group of people, mostly wearing yellow jackets, standing closely together. The individuals appear to be involved in some sort of formal or official event. The text at the bottom of the image is in Korean and mentions \"박대통령, 경주 지진현장 방문 '특별재난지역 선정\" which translates to \"President Park visits Gyeongju earthquake site 'designates special disaster area'.\" The time is shown as 08:50, and there is additional text at the bottom of the image mentioning weather conditions. The setting suggests a press conference or public announcement related to disaster response.",
"The current frame shows the same group of people, still wearing yellow jackets, now walking outside. They are accompanied by individuals in dark clothing, suggesting the continuation of the formal event. The text at the bottom of the image is in Korean and mentions \"미국방 '주한미군, 육림 독도' which translates to 'US Department of Defense 'South Korea, army, and Dokdo'.\" The time remains 08:50, and there is additional text mentioning weather conditions. The setting appears to be an outdoor event or inspection related to defense and national security."
] |
3ojHTwrvx90
|
A video depicting a formal event related to disaster response and national security, featuring a group of people, mostly wearing yellow jackets, led by President Park. The event begins with a press conference or public announcement at 08:50, where President Park designates a special disaster area in response to an earthquake in Gyeongju. The group then proceeds to an outdoor location, accompanied by individuals in dark clothing, for an inspection or discussion related to defense and national security, with a mention of the US Department of Defense and the disputed territory of Dokdo.
|
The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.
|
[
"People running out of buildings during the 2016 Gyeongju, South Korea earthquake on September 12",
"Emergency responders searching through rubble after the 2016 Gyeongju, South Korea earthquake on September 12, 2016",
"Cars driving away from the affected area in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Buildings with cracked walls and broken windows in Gyeongju, South Korea after the earthquake on 12 September 2016",
"Rescue teams carrying injured people on stretchers during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"Buildings collapsing or showing significant structural damage during the 12 September 2016 earthquake in Gyeongju, South Korea",
"People evacuating their homes and gathering in safe areas in Gyeongju, South Korea after the earthquake on September 12, 2016",
"Emergency responders searching for survivors in rubble after the 2016 Gyeongju, South Korea earthquake on September 12",
"Roads blocked by debris and damaged vehicles after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Residents assessing damage to their homes and belongings after the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
[
"People running out of buildings during the earthquake in Gyeongju, South Korea on September 12, 2016",
"Rescue teams searching through rubble after the 12 September 2016 earthquake in Gyeongju, South Korea",
"Buildings with cracked walls and fallen debris in Gyeongju, South Korea after the 12 September 2016 earthquake",
"Emergency vehicles rushing to the scene after the 2016 Gyeongju, South Korea earthquake on September 12",
"People gathering in open spaces for safety during the 12 September 2016 earthquake in Gyeongju, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_%EA%B2%BD%EC%A3%BC_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the consequences and aftermath of an earthquake, as these are the most likely to be visualized in a video. Events such as damage to buildings, rescue operations, and people reacting to the quake are plausible and commonly seen in earthquake-related videos.\n\nEVENTS:\n1. People running out of buildings\n2. Rescue teams searching through rubble\n3. Buildings with cracked walls and fallen debris\n4. Emergency vehicles rushing to the scene\n5. People gathering in open spaces for safety",
"en_article_excerpt": "The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.",
"en_article_url": "https://en.wikipedia.org/wiki/2016_Gyeongju_earthquake",
"event_category": "disasters",
"event_name": "gyeongju_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the aftermath or impact of an earthquake, as these would be the most visually apparent and relevant to a video about the 2016 Gyeongju earthquake. Events such as destruction, evacuation, and rescue efforts are likely to be seen in a video associated with this query.\n\nEVENTS:\n1. People running out of buildings\n2. Emergency responders searching through rubble\n3. Cars driving away from the affected area\n4. Buildings with cracked walls and broken windows\n5. Rescue teams carrying injured people on stretchers",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2016 Gyeongju earthquake occurred on September 12 near Gyeongju, South Korea.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2016 Gyeongju earthquake, it makes sense to extract events that are directly related to the aftermath and impact of an earthquake, such as damage to infrastructure, rescue efforts, and evacuation procedures. These events are likely to be visually represented in a video associated with the query, providing a concrete and tangible depiction of the earthquake's effects.\n\nEVENTS:\n1. Buildings collapsing or showing significant structural damage\n2. People evacuating their homes and gathering in safe areas\n3. Emergency responders searching for survivors in rubble\n4. Roads blocked by debris and damaged vehicles\n5. Residents assessing damage to their homes and belongings",
"video_URL": "http://youtube.com/watch?v=w6jdwGYcKZU",
"video_description": "안전처 \"경주지진 부상자 23명ㆍ재산피해 1,118건\" 국민안전처는 경주에서 발생한 규모 5.8의 지진으로 부상자 23명이 발생하고, 재산상 피해는 1천118건으로 집계됐다고 밝혔습니다. 안전처와 보건복지부에 따르면 부상자 23명 가운데 7명은 병원에서 치료를 받고 귀가했으며, 16명은 입원 중입니다. 지역별 부상자는 경북이 12명으로 가장 많고, 울산 4명, 대구 2명, 부산·인천·충북·전남·경남 각 1명입니다. 안전처는 균열이 발생한 주택을 대상으로 구조기술사 등과 함께 안전점검을 하고 귀가 여부와 추가 안전조치 등을 검토할 예정입니다. 연합뉴스TV : 02-398-4409(제보) 4441(기사문의), 카톡/라인 jebo23 (끝)",
"video_id": "w6jdwGYcKZU"
}
| 2
|
[
"The image shows a wet floor with visible water droplets, indicating recent rain or a spill. The text in Korean at the bottom of the image discusses a situation involving 23 employees and a significant number of orders. The text suggests a news broadcast with a focus on a financial or operational issue.",
"The frame continues to display a wet floor, maintaining continuity with the previous image. The water droplets and surface texture suggest ongoing or recent moisture. The text in Korean remains, reinforcing the context of a news broadcast about a financial or operational issue involving 23 employees and a large number of orders. The additional text in the top right corner refers to a scheduled showtime, which might be part of the ongoing news segment."
] |
w6jdwGYcKZU
|
A news broadcast discusses a financial or operational issue involving 23 employees and a significant number of orders, set against the backdrop of a wet floor, indicating recent rain or a spill, with the scene maintaining continuity across frames and including text in Korean that reinforces the context of the news segment.
|
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.
|
[
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching for trapped people in rubble after the 2017 Pohang earthquake in Heunghae, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in open spaces after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks forming in roads and sidewalks as the ground shakes during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders searching for survivors in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cars and debris scattered on the streets after earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in safe zones after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders rushing to the scene in ambulances and fire trucks during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Rescue teams searching for trapped people in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks and damage to roads and buildings caused by the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=oK2O8Xtkrvs",
"video_description": "15일 오후 2시 29분쯤 경북 포항시 북구 북쪽 9㎞ 지역에서 규모 5.4의 지진이 발생했다. 오마이TV는 지진 발생 당시 포항시 북구 한살림협동조합 매장을 촬영한 CCTV영상을 제보받아 공개한다. 이 영상에는 갑자기 진열대 물건들이 쏟아져내리는 장면이 들어있다. 한살림협동조합에 근무하는 박혜령(경북 영덕군)씨는 영상을 제보하면서 \"당시 사무실에 있었는데 벽지와 창문이 20초 이상 심하게 흔들렸다\"며 \"아직도 가슴이 진정되지 않는다\"고 말했다. 그는 \"바닥이 계속 흔들려 모두 밖으로 나왔고 안으로 들어갈 엄두를 내지 못했다\"며 \"이후 여진을 알리는 재난문자가 세 차례 왔다\"고 당시 상황을 설명했다. (영상제보 : 박혜령 씨/ 영상편집 : 황지희 기자)",
"video_id": "oK2O8Xtkrvs"
}
| 2
|
[
"The current frame shows the interior of a grocery store with a messy aisle filled with fallen products and items scattered on the floor. There are shelves on both sides, and some products appear to be broken or crushed. The text at the bottom of the image reads in Korean: \"시민 제보 포항 지진 시간, 쓸아진 진열대,\" which translates to \"Citizen report: Pohang earthquake time, toppled display.\" This suggests the image captures the aftermath of an earthquake in Pohang.",
"The current frame displays a logo for \"OhmyTV\" with the website \"www.ohmynews.com\" underneath. The text below the logo states in Korean: \"이 영상은 10만인클럽 회원들의 소중한 후원으로 제작되었습니다,\" which translates to \"This video was produced by the support of 100,000 members of the 100,000 club.\" This indicates that the video is being produced through the financial support of members of a particular community or group."
] |
oK2O8Xtkrvs
|
The video appears to depict the aftermath of an earthquake in Pohang, showing a grocery store with a messy aisle and fallen products. The scene suggests damage and destruction caused by the earthquake, with toppled shelves and broken items scattered on the floor. The video is a citizen report, produced with the support of a community group, OhmyTV, and its members, indicating a collaborative effort to document and share the impact of the earthquake.
|
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.
|
[
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching for trapped people in rubble after the 2017 Pohang earthquake in Heunghae, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in open spaces after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks forming in roads and sidewalks as the ground shakes during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders searching for survivors in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cars and debris scattered on the streets after earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in safe zones after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders rushing to the scene in ambulances and fire trucks during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Rescue teams searching for trapped people in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks and damage to roads and buildings caused by the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=6HhGFKbHFbs",
"video_description": "경북 포항에서 규모 5.4의 지진과 여진이 발생, 전국이 지진파에 흔들거리면서 주민들이 불안에 떨고 있다. 15일 기상청에 따르면 이날 오후 2시29분쯤 포항시 북구 흥해 6㎞ 지점에서 지진이 발생했다. http://www.hankookilbo.com/v/38f7f1c1597443e5ac55aca087a5dae2",
"video_id": "6HhGFKbHFbs"
}
| 2
|
[
"The frame captures a busy urban street scene with several pedestrians. A person is walking down the center of the street, holding a phone to their ear. Other individuals are seen walking or standing on the sidewalks, some in front of shop entrances, and one person appears to be entering a store. The scene suggests a lively atmosphere, possibly in a shopping district, with various storefronts lining the street.",
"The current frame shows a green digital display with the text \"HANKOOKILBO.COM\" and additional Korean text underneath, indicating a website or a related digital platform. There is no depiction of urban street scenes or pedestrians, as the frame focuses solely on the digital content. The display is clean and minimalistic, with no other objects or background elements visible."
] |
6HhGFKbHFbs
|
A person is walking down a busy urban street, likely in a shopping district, while on a phone call, surrounded by other pedestrians and storefronts. The scene then cuts to a digital display showing a website or platform, "HANKOOKILBO.COM", suggesting a potential connection or transition to an online context, possibly related to the individual's phone call or the urban environment.
|
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.
|
[
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching for trapped people in rubble after the 2017 Pohang earthquake in Heunghae, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in open spaces after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks forming in roads and sidewalks as the ground shakes during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders searching for survivors in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cars and debris scattered on the streets after earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in safe zones after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders rushing to the scene in ambulances and fire trucks during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Rescue teams searching for trapped people in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks and damage to roads and buildings caused by the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=1sXMvTYhnn0",
"video_description": "+--------------------------------------------------------------------------------+ ◈ 중앙일보 공식 SNS 채널 ◈ - 페이스북 : https://www.facebook.com/joongang/ - 인스타그램 : https://www.instagram.com/joongangilbo - 트위터 : http://www.twitter.com/joongangilbo - 유튜브 : https://goo.gl/DyGoPC - 네이버 TV : http://tvcast.naver.com/joongangsisa - 네이버포스트 : https://goo.gl/eeYh4k 당신이 원하는 뉴스, 중앙일보 SNS 채널과 함께하세요. +--------------------------------------------------------------------------------+",
"video_id": "1sXMvTYhnn0"
}
| 2
|
[
"The image shows a street scene with a few people walking on the sidewalk near storefronts. One person appears to be crossing the street. The storefront has Korean text, including a phone number. In the foreground, parts of a car's side mirror and a vehicle's rear are visible. The text at the bottom of the image suggests a negative perception of a specific area or neighborhood, indicating a judgment or opinion.",
"The image continues to show a street scene with several people walking on the sidewalk near storefronts. The storefront still has Korean text and a phone number displayed. In the foreground, parts of a car's side mirror and a vehicle's rear are visible. The text at the bottom of the image reiterates a negative perception of the specific area or neighborhood, suggesting a judgment or opinion."
] |
1sXMvTYhnn0
|
The video appears to depict a street scene in a neighborhood with Korean storefronts, where people are walking on the sidewalk and crossing the street. The presence of a car in the foreground suggests that the video may have been recorded from a vehicle. The text overlays in the frames express a negative opinion about the area or neighborhood, implying that the video may be presenting a critical or judgmental perspective on the location. Overall, the video seems to be showcasing everyday activity in a specific urban area while conveying a particular viewpoint about that area.
|
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.
|
[
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching for trapped people in rubble after the 2017 Pohang earthquake in Heunghae, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in open spaces after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks forming in roads and sidewalks as the ground shakes during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders searching for survivors in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cars and debris scattered on the streets after earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in safe zones after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders rushing to the scene in ambulances and fire trucks during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Rescue teams searching for trapped people in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks and damage to roads and buildings caused by the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=MH6_TeWDitQ",
"video_description": "포항 북구 북쪽 9Km 지역서 5.4 지진 이어 여진…전국서 감지 2.2, 2.6 전진 이어 3.6 여진도 발생 기상청은 15일 오후 2시 29분 쯤 경북 포항시 북구 북쪽 9㎞ 지역에서 규모 5.4의 지진이 발생했다고 밝혔습니다. 진앙은 북위 36.10도, 동경 129.37도입니다. 기상청은 이 지진의 깊이를 9㎞로 파악했습니다. 기상청은 당초 지진 발생지역과 규모를 포항시 북구 북쪽 6㎞ 지점, 규모 5.5로 발표했으나 잠시 후 수정하는 등 혼선이 이어지고 있습니다. 이날 오후 2시49분에는 포항시 북구 북쪽 7km에서 규모 3.6의 여진도 발생했습니다. 기상청은 \"이동속도가 빠른 지진파(P파)만을 이용해 자동 추정한 정보\"라며 \"여진 등 안전에 주의해야 한다\"고 당부했습니다. 이날 지진으로 경북과 경남은 물론 서울 지역에서도 건물 흔들림이 느껴지는 등 전국 곳곳에서 진동이 감지됐습니다. 이보다 앞서 이 인근에서는 두 차례 지진이 있었다고 기상청은 발표했습니다. 오후 2시 22분 32초 포항시 북구 북쪽 7km 지역(북위 36.11도, 동경 129.36도)에서 규모 2.2의 지진이 난 후 2시 22분 44초에는 비슷한 지점(북위 36.08도, 동경 129.31도)에서 규모 2.6의 지진이 발생했습니다. (끝)",
"video_id": "MH6_TeWDitQ"
}
| 2
|
[
"A group of people is standing in a crosswalk, waiting to cross the street. The scene is set in a busy urban area, with several cars and a bus visible. Buildings are seen in the background, including one with a sign written in Korean, indicating a commercial or office setting. The weather appears to be clear, and the overall activity suggests a typical day in a bustling city environment.",
"The group of people is still standing in the crosswalk, waiting to cross the street. The scene remains in a busy urban area with several cars and a bus visible. The weather continues to be clear, and the overall activity suggests a typical day in a bustling city environment."
] |
MH6_TeWDitQ
|
A group of people are waiting to cross the street in a busy urban area with cars and a bus present, set against the backdrop of commercial or office buildings on a clear day, in what appears to be a typical scene of city life.
|
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.
|
[
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching for trapped people in rubble after the 2017 Pohang earthquake in Heunghae, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in open spaces after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks forming in roads and sidewalks as the ground shakes during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders searching for survivors in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cars and debris scattered on the streets after earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in safe zones after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders rushing to the scene in ambulances and fire trucks during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Rescue teams searching for trapped people in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks and damage to roads and buildings caused by the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=_HN3DpC6m6I",
"video_description": "[현장] 포항 지진 피해 상황은…\"여진 등 안전 주의\" 오늘 오후 2시 29분 쯤 경북 포항시 북구에서 규모 5.4의 지진이 발생했습니다. 이번 지진은 작년 9월 12일 경북 경주시에서 발생한 규모 5.8의 지진에 이어 우리나라에서 일어난 지진 중 역대 두번째 규모입니다. 기상청에 따르면 포항지진 발생 지점은 포항시 북구 북쪽 9㎞, 북위 36.10도, 동경 129.37도입니다. 기상청은 이 지진의 깊이를 9㎞로 파악했습니다. 기상청은 당초 지진 발생지역과 규모를 포항시 북구 북쪽 6㎞ 지점, 규모 5.5로 발표했으나 지진 규모를 하향조정하는 등 혼선을 겪었습니다. 규모 5.4 지진에 앞서 오후 2시 22분 32초 포항시 북구 북쪽 7km 지역에서 규모 2.2, 2시 22분 44초 비슷한 지점(북위 36.08도, 동경 129.31도)에서 규모 2.6의 지진 등 전진이 발생했습니다. 아울러 이날 오후 2시 49분 규모 3.6 지진을 시작으로 오후 3시0분 54초께 규모 2.9 지진, 오후 3시 9분 49초 규모 3.6 지진 등 여진도 이어지고 있습니다. 기상청은 \"이동속도가 빠른 지진파(P파)만을 이용해 자동 추정한 정보\"라며 \"여진 등 안전에 주의해야 한다\"고 당부했습니다. 그러면서 \"계속해서 여진이 발생하고 있어 상황을 면밀히 분석 중\"이라며 \"발생 지점이 내륙 쪽으로 들어가 있어 해일의 가능성은 없는 것으로 판단한다\"고 덧붙였습니다. 이날 지진으로 경북과 경남은 물론 서울 지역에서도 건물 흔들림이 느껴지는 등 전국 곳곳에서 진동이 감지됐습니다. 연합뉴스TV : 02-398-4441(기사문의ㆍ제보) 카톡/라인 jebo23 ▣ 연합뉴스TV 유튜브 채널 구독 https://goo.gl/VuCJMi ▣ 대한민국 뉴스의 시작 연합뉴스TV / Yonhap News TV http://www.yonhapnewstv.co.kr/",
"video_id": "_HN3DpC6m6I"
}
| 2
|
[
"The image shows a shattered glass window with debris scattered on the ground. A red banner with Korean text is visible, hanging from the broken window. The scene appears to depict damage, possibly from an impact or vandalism.",
"The current frame depicts a large gathering of people outdoors in front of a building, with a large crowd of individuals standing together. The participants are dressed in winter clothing, and some people are looking around or talking to each other. The text in the frame mentions 기상청 (\"weather forecast\"), and there is a reference to \"제보영상\" (\"report video\") and \"여진 등 안전에 주의해야...\" (\"be careful about safety due to aftershocks...\"). The context suggests that the gathering is related to weather or emergency preparedness, particularly cautioning about safety due to possible aftershocks."
] |
_HN3DpC6m6I
|
A video depicting the aftermath of an incident, possibly an earthquake, shows a shattered glass window with a red banner and debris. The scene then shifts to a large gathering of people outdoors, dressed in winter clothing, in front of a building, where they appear to be discussing or awaiting information related to weather or emergency preparedness, with a focus on safety due to possible aftershocks.
|
The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.
|
[
"People running out of buildings as the earthquake strikes in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Buildings crumbling or collapsing due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"Emergency responders searching for trapped people in rubble after the 2017 Pohang earthquake in Heunghae, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in open spaces after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks forming in roads and sidewalks as the ground shakes during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings crumbling and collapsing during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"People running out of buildings and seeking safety during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders searching for survivors in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cars and debris scattered on the streets after earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017",
"Residents evacuating the area and gathering in safe zones after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
[
"Buildings shaking and crumbling due to the earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea on 15 November 2017",
"People running for cover and seeking safety outdoors during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Emergency responders rushing to the scene in ambulances and fire trucks during the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Rescue teams searching for trapped people in rubble after the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea",
"Cracks and damage to roads and buildings caused by the 15 November 2017 earthquake in Heunghae, Pohang, North Gyeongsang Province, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2017%EB%85%84_%ED%8F%AC%ED%95%AD_%EC%A7%80%EC%A7%84",
"during_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to decompose the ongoing event in multiple simple events. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: The 2017 Pohang earthquake is a significant event that would have caused destruction and disruption in the affected area, so it makes sense to extract events that are directly related to the earthquake's impact, such as damage to buildings and infrastructure, and the response of emergency services. These events would be concrete and visual, making them suitable for a video caption.\n\nEVENTS:\n1. Buildings shaking and crumbling due to the earthquake\n2. People running for cover and seeking safety outdoors\n3. Emergency responders rushing to the scene in ambulances and fire trucks\n4. Rescue teams searching for trapped people in rubble\n5. Cracks and damage to roads and buildings",
"en_article_excerpt": "The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.",
"en_article_url": "https://en.wikipedia.org/wiki/2017_Pohang_earthquake",
"event_category": "disasters",
"event_name": "pohang_earthquake",
"language": "korean",
"prequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what previous events could lead to this given event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the immediate consequences and aftermath of the earthquake, as these would be the most visually striking and relevant to a video about the 2017 Pohang earthquake. Events such as damage to buildings, rescue efforts, and people reacting to the earthquake would be likely to be seen in a video associated with the query.\n\nEVENTS:\n1. People running out of buildings as the earthquake strikes\n2. Buildings crumbling or collapsing due to the earthquake\n3. Emergency responders searching for trapped people in rubble\n4. Residents evacuating the area and gathering in open spaces\n5. Cracks forming in roads and sidewalks as the ground shakes",
"sequel_prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nYou are given a video search query. Assume the video search query is an ongoing event. You have to find out what events can be the outcome of this ongoing event. The extracted events should be concrete enough to be visualized in a video.\n\nHere are some guidelines: \n- Extract events that could be visualized in a video.\n- Before extracting an event, consider whether the event text could serve as a reasonable caption for a frame of a video associated with the query.\n- Give specific events related to the query, use your previous WORLD KNOWLEDGE to extract events that are likely to be seen in a video. For example, if the query is \"2019 Christmas Eve Protests in Hong Kong\", you might return \"Protesters marching in the streets\", but not \"Protestors marching in snow\" because it is not likely to have snow in Hong Kong, though its pretty common in other places. \n- First, explain your reasoning in 1-2 sentences about which events it makes sense to extract. Then, provide a numbered list with the events (anywhere from one to five event; use your best judgement to determine how many to extract)\n- Structure your response into two sections, \"\"EXPLANATION:\"\" and then \"\"EVENTS:\"\". The events sections should contain nothing but the events. \n\nHere is the query I'd like you to extract events from: The 2017 Pohang earthquake, measuring magnitude 5.4 on the Richter magnitude scale, struck Heunghae, Pohang, North Gyeongsang Province, South Korea on November 15, 2017.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2017 Pohang earthquake, it makes sense to extract events that are directly related to the aftermath and impact of the earthquake, as these would be concrete and visualizable in a video. The events should reflect the typical consequences of an earthquake, such as damage to infrastructure, rescue efforts, and public response, tailored to the specific context of Pohang, South Korea.\n\nEVENTS:\n1. Buildings crumbling and collapsing\n2. People running out of buildings and seeking safety\n3. Emergency responders searching for survivors in rubble\n4. Cars and debris scattered on the streets\n5. Residents evacuating the area and gathering in safe zones",
"video_URL": "http://youtube.com/watch?v=bADRfbUZewY",
"video_description": "산림청은 오는 4일 포항산림조합 목재유통센터에서 국유림에서 생산된 임산 연료를 지진피해를 입은 포항 주민들에게 무상으로 공급하는 행사를 갖기로 했습니다. ◀ＥＮＤ▶ 지진피해 주민과 홀몸노인, 기초생활보장 수급자 등을 대상으로 가구당 1톤씩 모두 21가구를 지원합니다. 이번에 공급하는 장작은 봉화군 장군봉 선도산림경영단지 내 금강소나무 육성사업지에서 생산된 참나무와 벚나무, 박달나무 등입니다.",
"video_id": "bADRfbUZewY"
}
| 2
|
[
"In the current frame, a group of people wearing red helmets and black outfits are seen working outside a building. They are handling and moving logs, with some carrying them and others organizing them into piles. The setting appears to be an industrial or work area, possibly a factory or workshop, as indicated by the large pile of logs in the foreground. The text in the image reads \"자료화면,\" which suggests that this is an archival or stock footage scene.",
"The group of people in red helmets and black outfits are actively engaged in logging activities outside a building. Several individuals are seen handling and moving logs, with some lifting and carrying them while others organize them into piles. The setting remains consistent with an industrial or work area, indicated by the ongoing log-handling activities and the presence of a large pile of logs in the foreground. The text \"자료화면\" reiterates that this scene is archival or stock footage, capturing the laborious nature of the logging process."
] |
bADRfbUZewY
|
A group of workers, distinguishable by their red helmets and black outfits, are engaged in logging activities outside a building in an industrial or work area, such as a factory or workshop. They are involved in handling and moving logs, with tasks including carrying, lifting, and organizing them into piles. The scene, identified as archival or stock footage, captures the labor-intensive process of logging, highlighting the physical effort and organization required in this line of work.
|
End of preview. Expand
in Data Studio
README.md exists but content is empty.
- Downloads last month
- 9
Size of downloaded dataset files:
3.22 MB
Size of the auto-converted Parquet files:
3.22 MB
Number of rows:
2,394