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.
|
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=4eNANKub4NE",
"video_description": "7000미라클_포항 지진 피해 돕기 특집방송 1부 본방 2017년 11월 28일(화) 오전 10시 10분 재방 2017년 11월 28일(화) 밤 11시 10분 삼방 2017년 11월 29일(수) 오후 2시 50분 ----------------------------------------------------------------------------------------- 7000미라클_포항 지진 피해 돕기 특집방송 2부 본방 2017년 11월 29일(화) 오전 10시 10분 재방 2017년 11월 29일(화) 밤 11시 10분 삼방 2017년 11월 30일(수) 오후 2시 50분",
"video_id": "4eNANKub4NE"
}
| 2
|
[
"The video shows a person wearing a pink jacket and glasses sitting in a car, looking out of the window. The person appears to be focused on something outside. There is a text overlay in Korean at the top left of the screen, which likely contains information about the video.",
"The video now shows a large cross structure against a cloudy sky, with a text overlay in Korean at the top left, indicating a change in focus from the previous indoor setting to an outdoor scene featuring the cross."
] |
4eNANKub4NE
|
The video depicts a person in a car looking out the window, initially focused on something outside, before the scene shifts to an outdoor setting featuring a large cross structure against a cloudy sky, indicating a change in the person's attention or the narrative's direction.
|
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=QIkpgLcEWMA",
"video_description": "픽업영상|시민들이 보내 준 #포항지진_영상 한동대 외벽 무너지고, 주차장 바닥 갈라져 #JTBC는_여러분들의_제보_기다립니다 ---------------------------------------------------------------------------------------- 📌 소셜스토리 - JTBC 바로가기▼ https://www.facebook.com/JTBCstandbyyou/",
"video_id": "QIkpgLcEWMA"
}
| 2
|
[
"In the image, two people are sitting at a red table in what appears to be a restaurant. They are engaged in eating from a large bowl of food. One person is stirring the food with a spoon, while the other holds a utensil. The background has drawings of dancing figures on a chalkboard. The text on the screen is in Korean, with the word \"소설스토리\" at the top and additional text at the bottom.",
"The image shows the logo for JTBC, a South Korean television network."
] |
QIkpgLcEWMA
|
Two people are eating from a large bowl of food at a restaurant table, engaged in a meal together, before the scene cuts to the logo of JTBC, a South Korean television network, suggesting the video is a segment or show from this network, possibly related to food, culture, or social interaction, given the context of the meal and the Korean text on the screen.
|
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=_vMNNh-x79Q",
"video_description": "경북 포항서 규모 5.4 지진 발생…서울ㆍ부산서도 진동 [앵커] 오늘 오후 경북 포항에서 규모 5.4의 지진이 발생했습니다. 부산을 비롯해 서울에서도 흔들림이 감지됐습니다. 보도국 취재기자 연결해 자세한 내용 들어보겠습니다. 홍정원 기자. [기자] 네, 오늘 오후 2시29분 포항 북구에서 북쪽으로 6킬로미터 지역에서 규모 5.4의 지진이 발생했다고 기상청이 밝혔습니다. 진앙은 북위 36.10도, 동경 129.37도입니다. 포항에서는 창이 흔들리고 책장에서 책이 떨어지는 등 진동의 여파가 상당했던 것으로 전해지고 있는데요. 또한 포항 곳곳에선 여진도 이어진 것으로 전해지고 있습니다. 기상청은 \"이동속도가 빠른 지진파, P파만을 이용해 자동 추정한 정보\"라며 \"여진 등 안전에 주의해야 한다\"고 당부했습니다. 한수원 측은 전국의 원자력발전소는 별다른 문제 없이 가동 중이라고 밝혔습니다. 오늘 지진의 지진동은 서울 등 경기 남부는 물론, 경남권과 호남권 등 전국적으로 감지된 것으로 전해지고 있습니다. 지진 발생 직후 부산소방안전본부와 부산경찰청에는 건물이 흔들린다는 시민들의 문의 전화가 빗발친 것으로 전해졌습니다. 일부 도심 건물이 심하게 흔들리면서 관련 직장인과 시민들이 급히 대피하는 소동이 벌어졌습니다. 다시 한 번 말씀드리겠습니다. 오늘 오후 2시29분 포항 북구에서 북쪽으로 6킬로미터 지역에서 규모 5.4의 지진이 발생했다고 기상청이 밝혔습니다. 포항 곳곳에선 여진이 이어지면서 주민 대피가 속출했으며, 지진동은 서울 등 경기권과 부산 등에서도 감지되면서 전국적으로 우려를 키우고 있습니다. 원자력발전소를 관리하는 한수원 측은 현재까지 가동중인 원전에 별다른 문제가 없다고 밝혔습니다. 아직까지 전국적으로 정확한 인명, 시설 피해 상황은 집계되지 않은 상태입니다. 지금까지 보도국에서 전해드렸습니다. 연합뉴스TV : 02-398-4441(기사문의·제보) 카톡/라인 jebo23 (끝)",
"video_id": "_vMNNh-x79Q"
}
| 2
|
[
"The image shows a large water bottle labeled in Korean, with the text \"동원샘물\" which translates to \"Dongwon Water\" in English. In the background, there is a blurred man holding a smartphone to his ear, suggesting he might be on a call. The scene appears to be set indoors, possibly in an office or home environment, as there is a desk with various items on it, including boxes and possibly a calendar. The lower part of the image has a news ticker with Korean text, indicating that the setting could be a news broadcast or a live television show. The presence of the water bottle and the man on the phone suggests a discussion or commentary might be occurring regarding the product or a related topic.",
"The frame shows a close-up of the same large water bottle labeled \"동원샘물\" (Dongwon Water) on a desk, with additional visible text on the label that reads \"New 5.4 Specifications\" in Korean, indicating a product update or specification change. The man in the background remains on the phone, reinforcing the ongoing discussion or commentary. The setting continues to be indoors, with the news ticker at the bottom of the screen still in view, suggesting the continuation of a live television show or broadcast, likely discussing the water bottle's new specifications or features."
] |
_vMNNh-x79Q
|
A man is on a phone call in an indoor setting, possibly a news broadcast or live television show, where a large water bottle labeled "Dongwon Water" with new specifications is being discussed or showcased. The scene suggests a product update or announcement, with the man likely providing commentary or information about the water bottle's new features.
|
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=k_iUdIJKUUc",
"video_description": "포항 시민들은 눈앞에서 아파트 외벽이 갈라지는 현장을 목격하며 하루종일 공포에 떨었습니다. 시민 700여명은 지금도 집에 돌아가지 못하고 대피소에 머물고 있습니다. [Ch.19] 사실을 보고 진실을 말합니다. ★홈페이지 : http://news.tvchosun.com/ * 뉴스제보 : 이메일(tvchosun@chosun.com), 카카오톡(tv조선제보), 전화(1661-0190)",
"video_id": "k_iUdIJKUUc"
}
| 2
|
[
"The image shows a damaged building with visible cracks and structural damage. There is a tree leaning against the building, and some potted plants are on the balcony. The scene appears to be taken at night. Text on the image mentions an apartment exterior showing signs of collapse and reports of structural damage due to a building collapse.",
"The image continues to depict the damaged building, now with a closer view of the structural damage. The cracks in the building's facade are more pronounced, and the leaning tree against the building is still visible. The potted plants on the balcony remain in place, and the scene is still set at night. Text on the image reiterates the apartment exterior showing signs of collapse and confirms reports of structural damage due to a building collapse, indicating the severity of the situation."
] |
k_iUdIJKUUc
|
The video depicts a damaged apartment building at night, showing significant structural damage with visible cracks and a tree leaning against it. The building's facade has pronounced cracks, and potted plants remain on the balcony, suggesting a recent and potentially catastrophic event. The context indicates a building collapse has occurred, with the video highlighting the severity of the structural damage to the apartment exterior.
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=Be0D3w0LKSg",
"video_description": "(서울=뉴스1) 문동주 기자 = 지난 18일 한국보다 먼저 일본에 상륙한 제14호 태풍 난마돌. 난마돌로 인해 일본에는 엄청난 강풍과 호우 피해가 이어졌다. 사람도 서 있기 힘든 정도의 위력의 비바람에 건물 외장재들이 날아다니고 대중교통 일부도 마비됐다. 동해에 접한 일본 서부 연안을 따라 이동한 난마돌의 위력을 영상으로 확인해보자. #난마돌 #태풍 #일본",
"video_id": "Be0D3w0LKSg"
}
| 2
|
[
"The image shows the interior of a bus that appears to be partially submerged in floodwater. The water level reaches above the floor of the bus, and the windshield wipers are moving, indicating rain. The text on the image is in Korean, which translates to \"Due to flooding, some public transportation is submerged.\"",
"The current frame displays a title screen with the text \"뉴스 TV,\" indicating a transition to a news segment or a news channel. The screen is a solid blue with white text in the center. There are no visible people or actions taking place in this frame."
] |
Be0D3w0LKSg
|
A news segment appears to be reporting on flooding, showing the interior of a bus partially submerged in floodwater, with rain indicated by moving windshield wipers, before transitioning to a news channel title screen labeled "뉴스 TV".
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=AXoJU3hRho0",
"video_description": "월요일인 오늘(19일)은 태풍 난마돌 의 영향으로 경상권과 강원영동 지역에 강한 비바람이 불겠습니다. 태풍14호 난마돌은 오늘(19일) 오전 3시 현재 일본 가고시마 북북서쪽 약 140km 해상에서 시속 17km로 북진할 것으로 예측되는데요.",
"video_id": "AXoJU3hRho0"
}
| 2
|
[
"The image shows a satellite map of a coastal region with several islands and water bodies. The map features various labeled areas in Korean, such as \"포항\" (Pohang), \"울산\" (Ulsan), and \"제주도\" (Jejudo). The main landmass is densely covered with green, indicating a forested or vegetated area, while the surrounding areas are bodies of water.",
"The current frame shows a satellite map of a coastal region with several islands and water bodies. The map features various labeled areas in Korean, such as \"포항\" (Pohang), \"울산\" (Ulsan), and \"제주도\" (Jejudo). The main landmass is densely covered with green, indicating a forested or vegetated area, while the surrounding areas are bodies of water."
] |
AXoJU3hRho0
|
The video depicts a static satellite map of a coastal region in Korea, featuring several islands and water bodies, with labeled areas including Pohang, Ulsan, and Jejudo, showing a densely forested or vegetated main landmass surrounded by bodies of water, with no visible changes or actions occurring between frames.
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=MYkG8SmCWNo",
"video_description": "국제우주정거장에서 포착된 제14호 태풍 '난마돌'의 모습이 공개됐습니다. 소용돌이치는 거대한 구름 덩어리 한가운데로 뚜렷한 태풍의 눈이 보입니다. 미국 항공우주국, 나사 소속 우주 비행사인 밥 하인스가 18일, 트위터에 공개한 사진들인데요. 하인스는 국제우주정거장에서 찍은 난마돌의 사진 3장을 올리며, \"태풍 난마돌 경로에 있는 모든 사람들의 안전을 위해 기도한다\"고 적었습니다. https://imnews.imbc.com/replay/2022/nwtoday/article/6408956_35752.html #태풍, #난마돌, #국제우주정거장",
"video_id": "MYkG8SmCWNo"
}
| 2
|
[
"The image shows a large cloud formation, possibly a storm or weather phenomenon. There are texts in Korean at the bottom and top of the image, with a news channel logo and timestamp. The texts suggest the event is related to a typhoon or tropical cyclone.",
"The image captures a formal ceremony taking place inside a grand hall. Participants in ceremonial attire, including guards in red and black uniforms, stand on either side of a decorated purple and red platform. The text at the top and bottom, along with the MBC logo and timestamp, suggests this is a televised event related to the Prime Minister of Japan's visit, as indicated by the Korean text. The scene is set against a backdrop of classical architecture, with a crowd of onlookers in the background."
] |
MYkG8SmCWNo
|
A news report transitions from covering a severe weather event, likely a typhoon, to a formal diplomatic ceremony. The ceremony takes place in a grand hall with a classical backdrop and involves the Prime Minister of Japan, as indicated by the Korean text. Participants, including guards in distinct uniforms, are present on a decorated platform, suggesting an official visit or meeting. The event is being televised, with the MBC news channel providing live coverage, as evidenced by the logo and timestamp on the screen.
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=waVeQcHP3f0",
"video_description": "\"우리나라에 미치는 영향은 그대로\"…강한 비바람 태풍 ’난마돌’, 매우 강한 위력 유지한 채 북상 비보다는 바람 강한 태풍…영남 해안에 집중호우 제주도와 영남 해안, 울릉도·독도에 35㎧ 돌풍 [앵커] 북상 중인 14호 태풍 '난마돌'의 진로가 동쪽으로 조금 더 치우치는 것으로 분석됐습니다. 하지만 태풍의 세력이 워낙 강해 제주도와 해안가에는 여전히 비바람 피해가 우려됩니다. 취재 기자 연결해 자세한 태풍 상황 알아보겠습니다. 김진두 기자! 태풍이 일본 쪽으로 더 치우쳐 이동한다는 건데, 그래도 강한 비바람은 그대로 유지된다는 거죠? [기자] 네, 그렇습니다. 기상청은 오늘 오전 브리핑에서 태풍 진로가 미세하게 조정됐다고 밝혔습니다. 태풍이 내일 새벽쯤 일본 규슈 북부에 상륙하는 건 그대로지만, 진로가 약간 더 동쪽으로 움직인다는 겁니다. 우리나라로부터 거리가 더 멀어지는 것이지만, 비바람 예보는 그대로 유지됐습니다. 태풍이 '매우 강한' 위력을 지닌 채 북상하기 때문인데요, 우선 바람이 무척 강하게 불겠고 영남 해안과 영동에는 집중호우도 예상되고 있습니다. 기상청은 제주도와 영남 해안, 그리고 울릉도·독도에 순간 최대 풍속이 35m에 달하는 돌풍이 불겠다고 밝혔습니다. 그 밖의 해안가와 경남 내륙에도 최고 초속 25m, 내륙 지방에도 초속 15m의 순간적인 강풍이 예상됩니다. 비는 영남 해안과 영동지방, 그리고 울릉도, 독도에 50~100mm가 오겠고, 특히 영남 해안에는 150mm가 넘는 호우가 쏟아질 것으로 보입니다. 기상청은 이번 태풍의 고비가 오늘 밤부터 내일 오전 사이가 되겠고, 제주도와 해안가에는 폭풍해일이나 월파 가능성도 있다며 철저한 대비를 당부했습니다. 지금까지 YTN 김진두입니다. YTN 김진두 (jdkim@ytn.co.kr) ※ '당신의 제보가 뉴스가 됩니다' [카카오톡] YTN 검색해 채널 추가 [전화] 02-398-8585 [메일] social@ytn.co.kr ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0108_202209181259028146 ▶ 제보 하기 : https://mj.ytn.co.kr/mj/mj_write.php ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN 무단 전재 및 재배포금지",
"video_id": "waVeQcHP3f0"
}
| 2
|
[
"The image shows a coastal area with rough, foamy waves hitting the rocky shore under an overcast sky. Several people are gathered near a railing, observing the sea. A small building is visible on the right, with a colorful mural along its side. A red structure, possibly a phone booth, is located in front of the building. A wire stretches across the top of the image. The text at the top reads \"태풍 '난미돌' 동쪽으로 '우리나라 영향은 비슷'\" which translates to \"Typhoon 'Nanmadol' moving east, 'Similar impact on our country'.\"",
"The image depicts a coastal area with rough, foamy waves hitting the rocky shore under an overcast sky. Several people are gathered near a railing, observing the sea. A small building is visible on the right, with a colorful mural along its side. A red structure, possibly a phone booth, is located in front of the building. A wire stretches across the top of the image. The text at the top reads \"태풍 '난미돌' 동쪽으로 '우리나라 영향은 비슷'\" which translates to \"Typhoon 'Nanmadol' moving east, 'Similar impact on our country'.\""
] |
waVeQcHP3f0
|
A typhoon, named Nanmadol, is moving east and is expected to have a similar impact on the country. The video shows a coastal area with rough, foamy waves hitting the rocky shore under an overcast sky. Several people are gathered near a railing, observing the sea, indicating concern or interest in the storm's approach. The scene is set in front of a small building with a colorful mural and a red structure, possibly a phone booth. The overall context suggests that the video is reporting on or documenting the effects of the typhoon on the coastal area.
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=umbAs-igFhc",
"video_description": "역대급 세력을 지닌 14호 태풍 '난마돌'이 일본에 상륙하면서 우리나라 남해와 동해 상은 물론 영남 해안에도 태풍 경보가 내려졌습니다. 현재 부산과 울산 등 태풍 특보 지역에는 초속 30m 안팎의 돌풍이 불고 있어 강풍 피해가 우려됩니다. 또 포항과 경주에는 산사태 주의보가 발령 중 입니다. 기상청은 14호 태풍 '난마돌'이 어제 저녁 일본 가고시마 남쪽에 상륙한 뒤 태풍의 세력이 매우 강에서 강한 강도로 한 단계 약화했다고 밝혔습니다. 하지만 중심 기압은 여전히 955 헥토파스칼로 강한 세력을 유지하고 있고, 중심 부근에는 초속 40m 돌풍이 몰아치고 있습니다. 특히 강풍 반경이 400km로 넓어 우리나라 남해와 동해상은 물론, 부산과 울산, 포항, 경주 등 영남 해안에도 태풍경보가 발령 중입니다. 기상청은 오늘 영남 해안에는 초속 25에서 35m의 돌풍이 불고, 영남 해안과 영동, 울릉도 독도에는 최고 100mm의 호우가 예상된다고 밝혔습니다. 특히 해상에는 최고 10m의 높은 파도가 일겠고, 해안가에는 월파나 폭풍해일 가능성이 크다며 철저한 대비를 당부했습니다. YTN 정혜윤 (jh0302@ytn.co.kr) ※ '당신의 제보가 뉴스가 됩니다' [카카오톡] YTN 검색해 채널 추가 [전화] 02-398-8585 [메일] social@ytn.co.kr ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0108_202209190411440551 ▶ 제보 하기 : https://mj.ytn.co.kr/mj/mj_write.php ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN 무단 전재 및 재배포금지",
"video_id": "umbAs-igFhc"
}
| 2
|
[
"The video displays a scene at night outside a building. There is a window with bright light inside, and a person is partially visible, possibly holding a device or object in front of the camera. A banner at the bottom of the image contains Korean text that translates to \"The wind speed was relatively low, but the central gust reached 40m.\" The setting appears to be a residential or commercial building, and the atmosphere suggests a focus on wind conditions or storm effects.",
"The scene continues at night outside the building, with a focus on a window where the interior is brightly lit. The person is still partially visible, holding what appears to be a device or object in front of the camera. The Korean text at the bottom of the image remains consistent, translating to \"The wind speed was relatively low, but the central gust reached 40m.\" The setting remains consistent with a residential or commercial building, and the atmosphere continues to suggest a focus on wind conditions or storm effects."
] |
umbAs-igFhc
|
The video depicts a nighttime scene outside a building, focusing on a brightly lit window where a person is partially visible, holding an object or device. The setting suggests a residential or commercial building, and the atmosphere indicates a focus on wind conditions or storm effects, with a mention of relatively low wind speed but a central gust reaching 40m. The consistent scene across frames implies an observational or documentary style, possibly monitoring or discussing the impact of wind or a storm on the building or area.
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=fxLzed6AI2Q",
"video_description": "제14호 태풍 난마돌이 일본 규슈 남부에 상륙했습니다. 일본 기상청은 어제 저녁 7시쯤 태풍이 규슈 남부 가고시마 시 부근에 상륙했다고 발표했습니다. 기상청은 이번 태풍이 규슈 서부 내륙을 따라 북상해 오늘 오전 규슈 북부에서 북동쪽으로 방향을 꺾어 이동할 것으로 예보했습니다. 태풍은 일본 열도를 관통해 오는 21일 오후 홋카이도 동쪽 해역으로 빠져나갈 전망입니다. 일본 기상청은 이번 태풍이 \"지금까지 경험한 적 없는 위험한 태풍\"으로 수십 년에 한 번 있을 만한 대규모 재해가 발생할 가능성이 있다며 각별한 대비를 당부했습니다. 오늘 낮까지 하루 동안 규슈 남부에 최고 500mm, 규슈 북부와 시코쿠에 최고 400mm의 많은 비가 예보돼 있습니다. 한편 가장 먼저 태풍 영향권에 들어선 일본 규슈 남부 지역을 중심으로 10여 명이 강풍에 넘어져 다치는 등 피해가 이어지고 있습니다. 규슈 지역 각 지자체는 주민들을 대상으로 안전한 곳으로 신속히 이동할 것을 권하는 '피난 지시'를 내리는 등 만일의 사태에 대비하고 있습니다. 일본 정부는 재해대책본부를 설치하고 태풍의 움직임과 주민 대피 상황, 그리고 피해 집계 등에 나섰습니다. 기시다 총리는 관계 각료회의를 소집해 국민에게 \"최신 기상 정보와 피난 정보에 주의해 신속히 생명을 지키는 행동을 해달라\"고 촉구했습니다. YTN 이경아 (kalee@ytn.co.kr) ※ '당신의 제보가 뉴스가 됩니다' [카카오톡] YTN 검색해 채널 추가 [전화] 02-398-8585 [메일] social@ytn.co.kr ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0104_202209190251207843 ▶ 제보 하기 : https://mj.ytn.co.kr/mj/mj_write.php ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN 무단 전재 및 재배포금지",
"video_id": "fxLzed6AI2Q"
}
| 2
|
[
"The frame shows a significant structural collapse with debris scattered around. Yellow caution tape is stretched across the area, indicating restricted access. The text in Korean at the bottom reads \"난민들 희생상황...기록적 강풍·호우 피해 속출,\" which translates to \"Refugees suffering...Record-breaking strong winds and heavy rain cause damage.\" This suggests the scene is related to the aftermath of severe weather conditions.",
"The current frame continues to depict the aftermath of a severe structural collapse, with debris still prominently scattered across the scene. Yellow caution tape remains, reinforcing restricted access to the area. The text in Korean at the bottom, \"난민들 희생상황...기록적 강풍·호우 피해 속출,\" translates to \"Refugees suffering...Record-breaking strong winds and heavy rain cause damage,\" indicating ongoing damage and suffering due to extreme weather conditions. The continuity of the scene suggests persistent and significant impact from the weather on the area and its inhabitants."
] |
fxLzed6AI2Q
|
The video depicts the aftermath of a severe structural collapse caused by record-breaking strong winds and heavy rain, resulting in significant damage and suffering for refugees. The scene shows debris scattered around the area, with yellow caution tape restricting access, indicating a hazardous environment. The continuous display of destruction and restricted access suggests a prolonged and severe impact of the extreme weather conditions on the affected area and its inhabitants.
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=tVUSMdbETuE",
"video_description": "오늘도 맑은 하늘 보긴 어렵겠습니다. 중국으로 향하는 태풍 '무이파'의 간접영향으로 오전까지 서쪽 지방에는 약한 비가 내리겠는데요, 비의 양이 적어서 낮 동안 활동하시는 데 큰 불편함은 없겠습니다. 때아닌 늦더위도 계속되겠습니다. 오늘 서울이 한낮에 28도, 광주가 31도까지 오르는 등 어제보다 높아 다소 덥겠습니다. 서울 등 수도권은 낮부터 비가 그치고 점차 갤 것으로 보입니다. 오늘 낮 기온은 예년보다 1∼4도가량 높겠고, 특히, 호남 지방을 중심으로 기온이 크게 오르겠습니다. 서울 28도, 전주 30도, 광주 31도가 예상됩니다. 다가오는 주말에는 서울 낮 기온이 30도까지 오르는 등 늦더위가 기승을 부리겠고요, 제주도와 동쪽 지방을 중심으로 비가 내릴 전망입니다. 한편, 오늘 오전 3시쯤, 일본 오키나와 동쪽 해상에서 제14호 태풍 '난마돌'이 발생했습니다. 이 태풍은 세력이 강해지면서 느리게 북상해 다음 주 월요일, 서귀포 남동쪽 약 280km 부근 해상까지 올라오겠습니다. 이후 진로는 유동적이지만, 일본 규슈 부근이나 대한해협으로 이동할 가능성이 있습니다. 앞으로 발표되는 태풍 정보를 잘 확인해주시기 바랍니다. 현재, 태풍 '무이파'의 간접 영향으로, 제주도와 남해안에는 '강풍주의보'가, 대부분 해상에는 '풍랑주의보'가 발효 중입니다. 내륙은 비가 대부분 그쳤지만 동해안과 제주도에는 비가 더 내릴 가능성 있는 만큼 시설물 관리와 해안가 안전사고에 각별히 유의하시기 바랍니다. 지금까지 YTN 원이다입니다. YTN 원이다 (wonleeda95@ytn.co.kr) ※ '당신의 제보가 뉴스가 됩니다' [카카오톡] YTN 검색해 채널 추가 [전화] 02-398-8585 [메일] social@ytn.co.kr ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0108_202209141027402664 ▶ 제보 하기 : https://mj.ytn.co.kr/mj/mj_write.php ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN 무단 전재 및 재배포금지",
"video_id": "tVUSMdbETuE"
}
| 2
|
[
"The video displays a weather forecast overlay on a city street scene. The forecast predicts temperatures for the upcoming week, with sunny weather and temperatures ranging from 21°C to 29°C. People are walking and crossing the street, some with backpacks, and a few are riding bicycles. A green bus is visible on the road, and a modern building is seen in the background.",
"A woman in a purple dress is holding a microphone with the \"YTN NEWS\" logo, standing outdoors in front of green trees and a circular structure, likely reporting the news."
] |
tVUSMdbETuE
|
A news report is being filmed in a city, starting with a scene showing everyday life on a street with people walking, cycling, and a bus passing by, accompanied by a weather forecast overlay indicating sunny weather for the week. The scene then shifts to a female news reporter, identified by the "YTN NEWS" logo on her microphone, standing in a different outdoor location in front of trees and a circular structure, suggesting she is about to or is currently reporting on a story, possibly related to the weather or current events in the city.
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=d6fZyZvF88k",
"video_description": "어젯밤 일본 규슈에 상륙한 태풍 난마돌의 영향으로 수십 명이 다치는 등 피해가 잇따르고 있습니다. NHK는 이번 태풍으로 현재까지 강풍에 넘어져 다치는 등 40여 명이 부상을 입은 것으로 집계됐다고 전했습니다. 이와 함께 태풍 영향권에 있는 지역 주민 약 960만 명에게는 신속한 안전 확보를 요청하는 최고 수준의 재해 경보와 피난 지시 등이 발령됐습니다. 순간최대풍속 50m/s에 이르는 강풍으로 공사용 대형 크레인이 꺾이고 지붕이 날아가는 등 물적 피해도 속출했습니다. 규슈 미야자키에는 지난 15일 이후 1,000mm에 이르는 비가 내리는 등 집중 호우로 인한 도로와 주택 침수도 잇따랐습니다. 많은 비로 하천 수위가 올라가 현재 30여 곳이 범람 위험 수위를 넘어선 것으로 나타났습니다. 일본 국토교통성은 댐 100여 곳의 수문을 미리 열어 범람을 막기 위해 방류를 실시했는데 이런 대규모 방류는 사상 처음입니다. 이와 함께 규슈부터 시코쿠 지역까지 약 31만 가구가 정전됐습니다. 항공과 선박, 철도 등 교통편도 태풍의 영향에서 벗어날 때까지 운행이 대부분 중단됩니다. 규슈 지역을 중심으로 큰 피해를 남긴 태풍 난마돌은 내일 일본 혼슈를 관통해 홋카이도 남쪽 바다로 빠져나갈 전망입니다. 일본 재해 당국은 많은 비가 내린 뒤 토사 붕괴 등 추가 피해가 발생할 가능성에 대비하며 태풍 움직임을 주시하고 있습니다. YTN 이경아 (kalee@ytn.co.kr) ※ '당신의 제보가 뉴스가 됩니다' [카카오톡] YTN 검색해 채널 추가 [전화] 02-398-8585 [메일] social@ytn.co.kr ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0104_202209191047268893 ▶ 제보 하기 : https://mj.ytn.co.kr/mj/mj_write.php ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN 무단 전재 및 재배포금지",
"video_id": "d6fZyZvF88k"
}
| 2
|
[
"The video shows a nighttime scene with a person wearing a high-visibility vest with a reflective pattern, standing near a fence. The setting appears to be a construction or maintenance area, as indicated by the safety equipment and the presence of barriers. There is a sign with text in a foreign language at the bottom left of the image. The scene suggests a focus on safety or maintenance activities.",
"The current frame depicts a flooded urban area, likely caused by heavy rainfall. The floodwater inundates a circular amphitheater-like structure and a nearby road, with strong currents visible in the water. Palm trees and a bridge can be seen in the background, suggesting an urban coastal environment. The scene is overcast, indicating ongoing storm conditions. Korean text appears on the screen, which likely relates to the cause or impact of the flooding."
] |
d6fZyZvF88k
|
The video depicts two distinct scenes related to maintenance and a natural disaster. It begins with a person wearing a high-visibility vest standing near a fence in what appears to be a construction or maintenance area at night, suggesting a focus on safety or maintenance activities. The scene then shifts to a flooded urban area, likely caused by heavy rainfall, where a circular amphitheater-like structure and a nearby road are inundated with water, and strong currents are visible. The setting is an urban coastal environment with palm trees and a bridge in the background, under overcast storm conditions.
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=ItDO3MSUQRQ",
"video_description": "힌남노의 상처가 채 가시기도 전에 이번에는 제 14호 태풍 '난마돌'이 북상하고 있습니다. 아직 경로는 유동적이지만 기상청은 다음주 월요일쯤 제주도를 향해 북진할 가능성이 있다고 보고 상황을 예의주시하고 있습니다. #가을태풍#태풍#태풍경로#힌남노#난마돌#태풍난마돌#제14호태풍#기상청#므르복#기상정보#이슈픽#자막뉴스 ☞MBN NEWS 구독하기 : https://www.youtube.com/channel/UCG9aFJTZ-lMCHAiO1KJsirg?sub_confirmation=1 ☞MPLAY 구독하기 : https://www.youtube.com/channel/UC84IlgY5HIzxKBZOt8XM5UA?sub_confirmation=1 ☞MBN Entertainment 구독하기 : https://www.youtube.com/channel/UCYyLIlOJyqkAFKlVjzX5img?sub_confirmation=1 ☞MBN 공식 홈페이지 : https://www.mbn.co.kr",
"video_id": "ItDO3MSUQRQ"
}
| 2
|
[
"The image shows a street with debris scattered across the road, including large rocks and smaller debris. The area appears to be affected by some form of damage, possibly from a natural disaster or vandalism. The sky is hazy, and there are buildings and trees visible in the background. The text in Korean at the bottom of the image reads: \"강도 '강은 기차를 탈선시킬 수 있을 정도의 위력\" which translates to \"Gangdo 'Gang has the power to derail a train'\".",
"The image depicts a bridge partially submerged by floodwaters, with turbulent water visible around the supports of the bridge. The scene is foggy, and the water's surface is choppy, indicating strong currents. The text in Korean at the top right corner reads: \"MBN\", suggesting this is a broadcast image. The bridge and surrounding area are shrouded in mist, emphasizing the severity of the flooding."
] |
ItDO3MSUQRQ
|
The video appears to depict the aftermath of a severe natural disaster, likely a flood, that has caused significant damage to a town or city. The scene shows a street filled with debris, including large rocks, and a bridge partially submerged in turbulent floodwaters. The disaster has affected the infrastructure, with the power to cause substantial destruction, as hinted by the text "Gang has the power to derail a train". The setting is characterized by a hazy sky, fog, and choppy waters, emphasizing the severity of the event. The video seems to be a news broadcast, as indicated by the "MBN" text, suggesting that it is coverage of a real-world disaster.
|
Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Flooding in coastal cities and low-lying areas due to typhoons in the Philippines and Japan",
"Debris-filled streets and damaged buildings after typhoon in Philippines and Japan",
"People evacuating to shelters and higher ground during typhoons in the Philippines and Japan",
"Cars and ships being tossed about by powerful storm surges during typhoons in the Philippines and Japan"
] |
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines and Japan",
"Heavy rainfall from typhoons causing flooding in urban areas of the Philippines and Japan",
"Storm surges from typhoons crashing against coastal defenses in the Philippines and Japan",
"Debris scattered across roads and streets in Philippines and Japan after typhoon",
"Emergency responders evacuating people from flooded areas in the Philippines and Japan during typhoon events"
] |
[
"Residents in the Philippines and Japan boarding up windows and securing outdoor furniture in preparation for the upcoming typhoon",
"Strong winds and heavy rainfall from typhoon hitting coastal areas of Japan and the Philippines",
"Floodwaters rising in streets and low-lying areas during typhoons in the Philippines and Japan",
"People evacuating to shelters or higher ground during a typhoon in the Philippines and Japan",
"Debris scattered on roads and damage to buildings after a typhoon passes in the Philippines and Japan"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%82%9C%EB%A7%88%EB%8F%8C_(2022%EB%85%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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and scenes associated with a powerful tropical cyclone impacting a region, such as Japan. These events should reflect common visual elements of typhoon coverage, including storm preparations, the storm itself, and its aftermath.\n\nEVENTS:\n1. Residents boarding up windows and securing outdoor furniture in preparation for the storm\n2. Strong winds and heavy rainfall hitting coastal areas of Japan\n3. Floodwaters rising in streets and low-lying areas\n4. People evacuating to shelters or higher ground\n5. Debris scattered on roads and damage to buildings after the storm passes",
"en_article_excerpt": "Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Nanmadol_(2022)",
"event_category": "disasters",
"event_name": "typhoon_nanmadol",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, flooding, and damage to infrastructure, as these are common visual elements that would be captured in a video of the event. Given the location of the typhoon's impact, Japan, the events should be tailored to the country's geography and urban landscape.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. Debris-filled streets and damaged buildings\n4. People evacuating to shelters and higher ground\n5. Cars and ships being tossed about by powerful storm surges",
"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: Typhoon Nanmadol, known in the Philippines as Super Typhoon Josie, was a powerful tropical cyclone that impacted Japan.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about Typhoon Nanmadol, also known as Super Typhoon Josie, it makes sense to extract events related to the typical effects and aftermath of a powerful tropical cyclone, such as strong winds, heavy rainfall, and resulting damage. These events are likely to be visually captured in a video associated with the query, showcasing the storm's impact on Japan.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Storm surges crashing against coastal defenses\n4. Debris scattered across roads and streets\n5. Emergency responders evacuating people from flooded areas",
"video_URL": "http://youtube.com/watch?v=ZuMemCoZIUY",
"video_description": "북상 중인 제14호 태풍 '난마돌'이 일본 규슈에 상륙할 것으로 보입니다. 기상청은 '난마돌'이 서귀포 남동쪽 먼바다까지 북상한 뒤 급격히 방향을 틀어 다음 주 월요일쯤 일본 규슈에 상륙할 것으로 내다봤습니다. 이후 일본 열도를 따라 계속 북동진할 것으로 보입니다. 따라서 우리나라에 큰 피해를 줄 가능성은 낮아졌지만, 제주도와 남해안, 영남 동해안은 태풍의 직간접적인 영향권에 들어 비바람이 강하게 불 것으로 보입니다. 기상청은 태풍의 진로가 아직은 유동적인 만큼 앞으로 발표되는 태풍 진로에 주의를 기울여 달라고 당부했습니다. YTN 김진두 (jdkim@ytn.co.kr) #태풍난마돌 #난마돌 #규슈 [YTN 사이언스 기사원문] https://science.ytn.co.kr/program/program_view.php?s_mcd=0082&s_hcd=&key=202209151243393568 [프로그램 제작 문의] legbiz@ytn.co.kr",
"video_id": "ZuMemCoZIUY"
}
| 2
|
[
"The video shows a street with cars parked and moving along it, including a red KIA car and a silver car in motion. There are palm trees and a building with a sign in Korean in the background. The scene is set in daylight.",
"The video transitions to an outdoor public space near the ocean, featuring a large statue of a man with a hat and a bag, possibly indicating a historical or cultural figure. Several square-shaped seating arrangements are scattered around the area. A person is seen sitting in the background, enjoying the seaside view. The ocean waves can be seen in the distance, creating a serene atmosphere."
] |
ZuMemCoZIUY
|
The video depicts a scene that transitions from a bustling street with moving cars and palm trees to a serene outdoor public space near the ocean. The street scene shows various cars, including a red KIA and a silver car, set against a backdrop of a building with a Korean sign, indicating the scene is possibly set in Korea or a Korean community. The video then shifts to a coastal area featuring a statue of a historical or cultural figure, square seating areas, and a person enjoying the view of the ocean waves in the distance. The overall context suggests a daytime setting that moves from urban activity to a peaceful seaside atmosphere.
|
On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.
|
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022",
"Cars and vehicles submerged in floodwater during the Seoul floods in Gangnam District, South Korea on 8 August 2022",
"Emergency responders rescuing individuals from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and property damage from floodwaters in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing out flooded homes and businesses in Seoul's Gangnam District after floods on 8 August 2022"
] |
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022 during floods",
"Cars and buses submerged in floodwater during the 8 August 2022 floods in Seoul's Gangnam District, South Korea",
"Emergency responders rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing debris and damaged belongings from their homes after floods in Gangnam District, Seoul, South Korea on 8 August 2022",
"Floodwaters overflowing from rivers and streams in Gangnam District, Seoul, South Korea during the floods on 8 August 2022"
] |
[
"People wading through floodwaters in the streets of Gangnam District Seoul South Korea during the floods on 8 August 2022",
"Cars and buses submerged in water on flooded roads in Gangnam District, Seoul, South Korea during the floods on August 8, 2022",
"Residents evacuating their homes and seeking higher ground in Seoul, South Korea, Gangnam District due to floods on 8 August 2022",
"Emergency responders, such as firefighters and police, rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and damaged furniture floating in the floodwaters during the 8 August 2022 floods in Gangnam District, Seoul, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2022%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A4%91%EB%B6%80_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District, it makes sense to extract events that are commonly associated with flooding in urban areas, such as people evacuating, floodwaters rising, and damage to infrastructure. These events are likely to be visualized in a video capturing the aftermath of the flood.\n\nEVENTS:\n1. People wading through floodwaters in the streets of Gangnam District\n2. Cars and buses submerged in water on flooded roads\n3. Residents evacuating their homes and seeking higher ground\n4. Emergency responders, such as firefighters and police, rescuing people from flooded areas\n5. Debris and damaged furniture floating in the floodwaters",
"en_article_excerpt": "On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.",
"en_article_url": "https://en.wikipedia.org/wiki/2022_South_Korean_floods",
"event_category": "disasters",
"event_name": "2022_floods",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, particularly the Gangnam District and surrounding areas, it makes sense to extract events that are directly related to flooding and its immediate consequences, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visually captured in a video documenting the floods and their impact on the affected areas.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and vehicles submerged in floodwater\n3. Emergency responders rescuing individuals from flooded areas\n4. Debris and property damage from floodwaters\n5. Residents clearing out flooded homes and businesses",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District and surrounding areas, it makes sense to extract events that are commonly associated with flooding, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visualized in a video capturing the aftermath and response to the flooding in Seoul.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and buses submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Residents clearing debris and damaged belongings from their homes\n5. Floodwaters overflowing from rivers and streams in the affected areas",
"video_URL": "http://twitter.com/i/status/1556640821054787588",
"video_description": "I just found out about the subway floods in Korea, 모두 건강 유의하세요 ! 아무쪼록 인명피해는 없게 해주세요.",
"video_id": "1556640821054787588"
}
| 2
|
[
"Water is leaking from the ceiling in a subway station, causing a large puddle on the floor.",
"The water continues to leak from the ceiling in the subway station, creating a larger puddle on the floor."
] |
1556640821054787588
|
A water leak in the ceiling of a subway station is causing a growing puddle on the floor, with the leak persisting over time.
|
On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.
|
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022",
"Cars and vehicles submerged in floodwater during the Seoul floods in Gangnam District, South Korea on 8 August 2022",
"Emergency responders rescuing individuals from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and property damage from floodwaters in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing out flooded homes and businesses in Seoul's Gangnam District after floods on 8 August 2022"
] |
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022 during floods",
"Cars and buses submerged in floodwater during the 8 August 2022 floods in Seoul's Gangnam District, South Korea",
"Emergency responders rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing debris and damaged belongings from their homes after floods in Gangnam District, Seoul, South Korea on 8 August 2022",
"Floodwaters overflowing from rivers and streams in Gangnam District, Seoul, South Korea during the floods on 8 August 2022"
] |
[
"People wading through floodwaters in the streets of Gangnam District Seoul South Korea during the floods on 8 August 2022",
"Cars and buses submerged in water on flooded roads in Gangnam District, Seoul, South Korea during the floods on August 8, 2022",
"Residents evacuating their homes and seeking higher ground in Seoul, South Korea, Gangnam District due to floods on 8 August 2022",
"Emergency responders, such as firefighters and police, rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and damaged furniture floating in the floodwaters during the 8 August 2022 floods in Gangnam District, Seoul, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2022%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A4%91%EB%B6%80_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District, it makes sense to extract events that are commonly associated with flooding in urban areas, such as people evacuating, floodwaters rising, and damage to infrastructure. These events are likely to be visualized in a video capturing the aftermath of the flood.\n\nEVENTS:\n1. People wading through floodwaters in the streets of Gangnam District\n2. Cars and buses submerged in water on flooded roads\n3. Residents evacuating their homes and seeking higher ground\n4. Emergency responders, such as firefighters and police, rescuing people from flooded areas\n5. Debris and damaged furniture floating in the floodwaters",
"en_article_excerpt": "On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.",
"en_article_url": "https://en.wikipedia.org/wiki/2022_South_Korean_floods",
"event_category": "disasters",
"event_name": "2022_floods",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, particularly the Gangnam District and surrounding areas, it makes sense to extract events that are directly related to flooding and its immediate consequences, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visually captured in a video documenting the floods and their impact on the affected areas.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and vehicles submerged in floodwater\n3. Emergency responders rescuing individuals from flooded areas\n4. Debris and property damage from floodwaters\n5. Residents clearing out flooded homes and businesses",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District and surrounding areas, it makes sense to extract events that are commonly associated with flooding, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visualized in a video capturing the aftermath and response to the flooding in Seoul.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and buses submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Residents clearing debris and damaged belongings from their homes\n5. Floodwaters overflowing from rivers and streams in the affected areas",
"video_URL": "http://twitter.com/i/status/1556678909436932096",
"video_description": "This is absolutely insane video in South Korea. Extreme flooding that hasn’t been seen in 80 years or more. Very extreme flooding, causing massive problems in Seoul and the entirety of the country. #SouthKorea #flooding #weather",
"video_id": "1556678909436932096"
}
| 2
|
[
"The video shows a flooded urban street with several vehicles, including a bus and cars, navigating through the water. The text indicates excitement about the heavy rain, mentioning that the flood was so severe that it could be seen as a bus ride, a boat ride, and even a swimming race.",
"In this frame, the flooded urban street continues to be filled with fast-moving, muddy water, as evidenced by the ripples and waves around the black bollards protruding from the water. Vehicles, including a white car and a blue bus, are still visible, navigating through the deep floodwaters, emphasizing the severity of the flooding. The text humorously remarks on the ongoing rainfall and the significant inundation, suggesting that the flood is so deep that even the poles in the water seem to be sinking slightly."
] |
1556678909436932096
|
The video depicts a severe flooding event in an urban area, where a street is completely inundated with fast-moving, muddy water. Vehicles, including buses and cars, are shown navigating through the deep floodwaters, highlighting the extreme conditions. The flood is so severe that it has become a dominant feature of the scene, with water covering the road and surrounding objects, and even causing the poles to appear as if they are sinking. The overall context suggests a heavy rainfall event that has caused significant disruption to the urban environment.
|
On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.
|
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022",
"Cars and vehicles submerged in floodwater during the Seoul floods in Gangnam District, South Korea on 8 August 2022",
"Emergency responders rescuing individuals from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and property damage from floodwaters in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing out flooded homes and businesses in Seoul's Gangnam District after floods on 8 August 2022"
] |
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022 during floods",
"Cars and buses submerged in floodwater during the 8 August 2022 floods in Seoul's Gangnam District, South Korea",
"Emergency responders rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing debris and damaged belongings from their homes after floods in Gangnam District, Seoul, South Korea on 8 August 2022",
"Floodwaters overflowing from rivers and streams in Gangnam District, Seoul, South Korea during the floods on 8 August 2022"
] |
[
"People wading through floodwaters in the streets of Gangnam District Seoul South Korea during the floods on 8 August 2022",
"Cars and buses submerged in water on flooded roads in Gangnam District, Seoul, South Korea during the floods on August 8, 2022",
"Residents evacuating their homes and seeking higher ground in Seoul, South Korea, Gangnam District due to floods on 8 August 2022",
"Emergency responders, such as firefighters and police, rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and damaged furniture floating in the floodwaters during the 8 August 2022 floods in Gangnam District, Seoul, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2022%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A4%91%EB%B6%80_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District, it makes sense to extract events that are commonly associated with flooding in urban areas, such as people evacuating, floodwaters rising, and damage to infrastructure. These events are likely to be visualized in a video capturing the aftermath of the flood.\n\nEVENTS:\n1. People wading through floodwaters in the streets of Gangnam District\n2. Cars and buses submerged in water on flooded roads\n3. Residents evacuating their homes and seeking higher ground\n4. Emergency responders, such as firefighters and police, rescuing people from flooded areas\n5. Debris and damaged furniture floating in the floodwaters",
"en_article_excerpt": "On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.",
"en_article_url": "https://en.wikipedia.org/wiki/2022_South_Korean_floods",
"event_category": "disasters",
"event_name": "2022_floods",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, particularly the Gangnam District and surrounding areas, it makes sense to extract events that are directly related to flooding and its immediate consequences, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visually captured in a video documenting the floods and their impact on the affected areas.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and vehicles submerged in floodwater\n3. Emergency responders rescuing individuals from flooded areas\n4. Debris and property damage from floodwaters\n5. Residents clearing out flooded homes and businesses",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District and surrounding areas, it makes sense to extract events that are commonly associated with flooding, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visualized in a video capturing the aftermath and response to the flooding in Seoul.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and buses submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Residents clearing debris and damaged belongings from their homes\n5. Floodwaters overflowing from rivers and streams in the affected areas",
"video_URL": "http://twitter.com/i/status/1556973165556903939",
"video_description": "Visuals after yesterday's floods... Rains continue in S. Korea on Tuesday; \"level 3\" warning in operation to prevent damage. Be careful.. stay Safe.. #SouthKorea #flooding #flood #Seoul #climate #rain",
"video_id": "1556973165556903939"
}
| 2
|
[
"A group of people is walking down a wet, city street at night, holding umbrellas to shield themselves from the rain. Bright advertisements and signs are visible on the buildings in the background, illuminating the scene with various colors.",
"The current frame continues to depict a group of people walking down the wet city street at night, still holding umbrellas to shield themselves from the rain. The bright advertisements and signs on the buildings remain visible, illuminating the scene with various colors. A white car is now present, adding to the urban nighttime atmosphere."
] |
1556973165556903939
|
A group of people walk down a city street at night, using umbrellas to protect themselves from the rain. The scene is set against the backdrop of a vibrant urban environment, with illuminated advertisements and signs on the buildings. As they walk, a car appears, further adding to the nighttime city atmosphere, but the primary focus remains on the group navigating through the rainy street.
|
On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.
|
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022",
"Cars and vehicles submerged in floodwater during the Seoul floods in Gangnam District, South Korea on 8 August 2022",
"Emergency responders rescuing individuals from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and property damage from floodwaters in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing out flooded homes and businesses in Seoul's Gangnam District after floods on 8 August 2022"
] |
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022 during floods",
"Cars and buses submerged in floodwater during the 8 August 2022 floods in Seoul's Gangnam District, South Korea",
"Emergency responders rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing debris and damaged belongings from their homes after floods in Gangnam District, Seoul, South Korea on 8 August 2022",
"Floodwaters overflowing from rivers and streams in Gangnam District, Seoul, South Korea during the floods on 8 August 2022"
] |
[
"People wading through floodwaters in the streets of Gangnam District Seoul South Korea during the floods on 8 August 2022",
"Cars and buses submerged in water on flooded roads in Gangnam District, Seoul, South Korea during the floods on August 8, 2022",
"Residents evacuating their homes and seeking higher ground in Seoul, South Korea, Gangnam District due to floods on 8 August 2022",
"Emergency responders, such as firefighters and police, rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and damaged furniture floating in the floodwaters during the 8 August 2022 floods in Gangnam District, Seoul, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2022%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A4%91%EB%B6%80_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District, it makes sense to extract events that are commonly associated with flooding in urban areas, such as people evacuating, floodwaters rising, and damage to infrastructure. These events are likely to be visualized in a video capturing the aftermath of the flood.\n\nEVENTS:\n1. People wading through floodwaters in the streets of Gangnam District\n2. Cars and buses submerged in water on flooded roads\n3. Residents evacuating their homes and seeking higher ground\n4. Emergency responders, such as firefighters and police, rescuing people from flooded areas\n5. Debris and damaged furniture floating in the floodwaters",
"en_article_excerpt": "On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.",
"en_article_url": "https://en.wikipedia.org/wiki/2022_South_Korean_floods",
"event_category": "disasters",
"event_name": "2022_floods",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, particularly the Gangnam District and surrounding areas, it makes sense to extract events that are directly related to flooding and its immediate consequences, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visually captured in a video documenting the floods and their impact on the affected areas.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and vehicles submerged in floodwater\n3. Emergency responders rescuing individuals from flooded areas\n4. Debris and property damage from floodwaters\n5. Residents clearing out flooded homes and businesses",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District and surrounding areas, it makes sense to extract events that are commonly associated with flooding, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visualized in a video capturing the aftermath and response to the flooding in Seoul.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and buses submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Residents clearing debris and damaged belongings from their homes\n5. Floodwaters overflowing from rivers and streams in the affected areas",
"video_URL": "http://twitter.com/i/status/1556659852054634496",
"video_description": "Dorimcheon stream in #Seoul's Gwanak District right now. People are now asking where President Yoon Suk-yeol is and what he's doing. Mayor Oh has just returned to office to deal with disaster, but it's not just Seoul. #SouthKorea #flooding #floodsituation",
"video_id": "1556659852054634496"
}
| 2
|
[
"The image shows a flooded street at night, with water flowing rapidly. In the foreground, a metal railing and part of a bicycle are visible, indicating the presence of a balcony or porch. Buildings with lit windows are in the background, and streetlights illuminate the scene. The water appears to be turbulent, suggesting heavy rainfall or a storm.",
"The video continues to depict a flooded street at night, with water still flowing rapidly. The metal railing and part of a bicycle remain visible in the foreground, indicating the same balcony or porch. Buildings with lit windows are still in the background, and streetlights continue to illuminate the scene. The water remains turbulent, suggesting ongoing heavy rainfall or a storm."
] |
1556659852054634496
|
A nighttime scene of a flooded street is depicted, with rapidly flowing water illuminated by streetlights and the lit windows of surrounding buildings. The presence of a metal railing and a bicycle in the foreground suggests the scene is being observed from a balcony or porch. The turbulent water indicates heavy rainfall or a storm, which appears to be ongoing as the flooding continues without change, creating a consistent and intense scene throughout the video.
|
On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.
|
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022",
"Cars and vehicles submerged in floodwater during the Seoul floods in Gangnam District, South Korea on 8 August 2022",
"Emergency responders rescuing individuals from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and property damage from floodwaters in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing out flooded homes and businesses in Seoul's Gangnam District after floods on 8 August 2022"
] |
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022 during floods",
"Cars and buses submerged in floodwater during the 8 August 2022 floods in Seoul's Gangnam District, South Korea",
"Emergency responders rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing debris and damaged belongings from their homes after floods in Gangnam District, Seoul, South Korea on 8 August 2022",
"Floodwaters overflowing from rivers and streams in Gangnam District, Seoul, South Korea during the floods on 8 August 2022"
] |
[
"People wading through floodwaters in the streets of Gangnam District Seoul South Korea during the floods on 8 August 2022",
"Cars and buses submerged in water on flooded roads in Gangnam District, Seoul, South Korea during the floods on August 8, 2022",
"Residents evacuating their homes and seeking higher ground in Seoul, South Korea, Gangnam District due to floods on 8 August 2022",
"Emergency responders, such as firefighters and police, rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and damaged furniture floating in the floodwaters during the 8 August 2022 floods in Gangnam District, Seoul, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2022%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A4%91%EB%B6%80_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District, it makes sense to extract events that are commonly associated with flooding in urban areas, such as people evacuating, floodwaters rising, and damage to infrastructure. These events are likely to be visualized in a video capturing the aftermath of the flood.\n\nEVENTS:\n1. People wading through floodwaters in the streets of Gangnam District\n2. Cars and buses submerged in water on flooded roads\n3. Residents evacuating their homes and seeking higher ground\n4. Emergency responders, such as firefighters and police, rescuing people from flooded areas\n5. Debris and damaged furniture floating in the floodwaters",
"en_article_excerpt": "On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.",
"en_article_url": "https://en.wikipedia.org/wiki/2022_South_Korean_floods",
"event_category": "disasters",
"event_name": "2022_floods",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, particularly the Gangnam District and surrounding areas, it makes sense to extract events that are directly related to flooding and its immediate consequences, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visually captured in a video documenting the floods and their impact on the affected areas.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and vehicles submerged in floodwater\n3. Emergency responders rescuing individuals from flooded areas\n4. Debris and property damage from floodwaters\n5. Residents clearing out flooded homes and businesses",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District and surrounding areas, it makes sense to extract events that are commonly associated with flooding, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visualized in a video capturing the aftermath and response to the flooding in Seoul.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and buses submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Residents clearing debris and damaged belongings from their homes\n5. Floodwaters overflowing from rivers and streams in the affected areas",
"video_URL": "http://twitter.com/i/status/1556995436052873218",
"video_description": "Heavy rain in Seoul floods train stations, submerges vehicles. #Seoul #flooding #floods #SouthKorea",
"video_id": "1556995436052873218"
}
| 2
|
[
"The image shows a flooded stairwell with water cascading down the steps, causing a surge at the bottom. The stairwell is enclosed with tiled walls and has handrails on either side.",
"The image continues to depict the flooded stairwell with water cascading down the steps, now reaching a higher level and increasing the surge at the bottom. The stairwell remains enclosed with tiled walls and handrails on either side, highlighting the severity of the flooding."
] |
1556995436052873218
|
A flooded stairwell is depicted, with water cascading down the steps and causing a surge at the bottom, which worsens over time as the water level rises, indicating a severe flooding event in an enclosed area with tiled walls and handrails.
|
On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.
|
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022",
"Cars and vehicles submerged in floodwater during the Seoul floods in Gangnam District, South Korea on 8 August 2022",
"Emergency responders rescuing individuals from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and property damage from floodwaters in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing out flooded homes and businesses in Seoul's Gangnam District after floods on 8 August 2022"
] |
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022 during floods",
"Cars and buses submerged in floodwater during the 8 August 2022 floods in Seoul's Gangnam District, South Korea",
"Emergency responders rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing debris and damaged belongings from their homes after floods in Gangnam District, Seoul, South Korea on 8 August 2022",
"Floodwaters overflowing from rivers and streams in Gangnam District, Seoul, South Korea during the floods on 8 August 2022"
] |
[
"People wading through floodwaters in the streets of Gangnam District Seoul South Korea during the floods on 8 August 2022",
"Cars and buses submerged in water on flooded roads in Gangnam District, Seoul, South Korea during the floods on August 8, 2022",
"Residents evacuating their homes and seeking higher ground in Seoul, South Korea, Gangnam District due to floods on 8 August 2022",
"Emergency responders, such as firefighters and police, rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and damaged furniture floating in the floodwaters during the 8 August 2022 floods in Gangnam District, Seoul, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2022%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A4%91%EB%B6%80_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District, it makes sense to extract events that are commonly associated with flooding in urban areas, such as people evacuating, floodwaters rising, and damage to infrastructure. These events are likely to be visualized in a video capturing the aftermath of the flood.\n\nEVENTS:\n1. People wading through floodwaters in the streets of Gangnam District\n2. Cars and buses submerged in water on flooded roads\n3. Residents evacuating their homes and seeking higher ground\n4. Emergency responders, such as firefighters and police, rescuing people from flooded areas\n5. Debris and damaged furniture floating in the floodwaters",
"en_article_excerpt": "On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.",
"en_article_url": "https://en.wikipedia.org/wiki/2022_South_Korean_floods",
"event_category": "disasters",
"event_name": "2022_floods",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, particularly the Gangnam District and surrounding areas, it makes sense to extract events that are directly related to flooding and its immediate consequences, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visually captured in a video documenting the floods and their impact on the affected areas.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and vehicles submerged in floodwater\n3. Emergency responders rescuing individuals from flooded areas\n4. Debris and property damage from floodwaters\n5. Residents clearing out flooded homes and businesses",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District and surrounding areas, it makes sense to extract events that are commonly associated with flooding, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visualized in a video capturing the aftermath and response to the flooding in Seoul.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and buses submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Residents clearing debris and damaged belongings from their homes\n5. Floodwaters overflowing from rivers and streams in the affected areas",
"video_URL": "http://twitter.com/i/status/1556833205671456768",
"video_description": "After heavy rain and #flashflood hit South Korea, water started coming inside the apartment as well. #Gangnam #Seoul #flooding #SouthKorea",
"video_id": "1556833205671456768"
}
| 2
|
[
"The video displays an empty elevator in what appears to be a building, likely a hotel or office complex. The elevator is labeled with the number \"B2,\" indicating it is for the basement level. The walls of the elevator and the surrounding area are made of marble, and the door is closed. The text \"서초아크로비스타\" is visible, which translates to \"Seocho A Cube Vista,\" suggesting the location or name of the building.",
"The video continues to display the same empty elevator in what appears to be a building, likely a hotel or office complex. The elevator is still labeled with the number \"B2,\" indicating it is for the basement level. The walls of the elevator and the surrounding area are still made of marble, and the door remains closed. The text \"서초아크로비스타\" is still visible, which translates to \"Seocho A Cube Vista,\" suggesting the location or name of the building."
] |
1556833205671456768
|
The video depicts an empty elevator, labeled "B2" for the basement level, in a building likely to be a hotel or office complex named "Seocho A Cube Vista". The elevator remains stationary with its doors closed throughout the observed frames, showing no movement or activity.
|
On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.
|
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022",
"Cars and vehicles submerged in floodwater during the Seoul floods in Gangnam District, South Korea on 8 August 2022",
"Emergency responders rescuing individuals from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and property damage from floodwaters in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing out flooded homes and businesses in Seoul's Gangnam District after floods on 8 August 2022"
] |
[
"People evacuating flooded buildings and streets in Gangnam District, Seoul, South Korea on August 8, 2022 during floods",
"Cars and buses submerged in floodwater during the 8 August 2022 floods in Seoul's Gangnam District, South Korea",
"Emergency responders rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Residents clearing debris and damaged belongings from their homes after floods in Gangnam District, Seoul, South Korea on 8 August 2022",
"Floodwaters overflowing from rivers and streams in Gangnam District, Seoul, South Korea during the floods on 8 August 2022"
] |
[
"People wading through floodwaters in the streets of Gangnam District Seoul South Korea during the floods on 8 August 2022",
"Cars and buses submerged in water on flooded roads in Gangnam District, Seoul, South Korea during the floods on August 8, 2022",
"Residents evacuating their homes and seeking higher ground in Seoul, South Korea, Gangnam District due to floods on 8 August 2022",
"Emergency responders, such as firefighters and police, rescuing people from flooded areas in Gangnam District, Seoul, South Korea during the floods on 8 August 2022",
"Debris and damaged furniture floating in the floodwaters during the 8 August 2022 floods in Gangnam District, Seoul, South Korea"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2022%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A4%91%EB%B6%80_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District, it makes sense to extract events that are commonly associated with flooding in urban areas, such as people evacuating, floodwaters rising, and damage to infrastructure. These events are likely to be visualized in a video capturing the aftermath of the flood.\n\nEVENTS:\n1. People wading through floodwaters in the streets of Gangnam District\n2. Cars and buses submerged in water on flooded roads\n3. Residents evacuating their homes and seeking higher ground\n4. Emergency responders, such as firefighters and police, rescuing people from flooded areas\n5. Debris and damaged furniture floating in the floodwaters",
"en_article_excerpt": "On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.",
"en_article_url": "https://en.wikipedia.org/wiki/2022_South_Korean_floods",
"event_category": "disasters",
"event_name": "2022_floods",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, particularly the Gangnam District and surrounding areas, it makes sense to extract events that are directly related to flooding and its immediate consequences, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visually captured in a video documenting the floods and their impact on the affected areas.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and vehicles submerged in floodwater\n3. Emergency responders rescuing individuals from flooded areas\n4. Debris and property damage from floodwaters\n5. Residents clearing out flooded homes and businesses",
"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: On 8 August 2022, large scale floods hit the capital of South Korea, Seoul, especially Gangnam District and surrounding areas.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about large-scale floods hitting Seoul, especially the Gangnam District and surrounding areas, it makes sense to extract events that are commonly associated with flooding, such as evacuation efforts, property damage, and rescue operations. These events are likely to be visualized in a video capturing the aftermath and response to the flooding in Seoul.\n\nEVENTS:\n1. People evacuating flooded buildings and streets\n2. Cars and buses submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Residents clearing debris and damaged belongings from their homes\n5. Floodwaters overflowing from rivers and streams in the affected areas",
"video_URL": "http://twitter.com/i/status/1557013913216352258",
"video_description": "Summers in South Korea be like... #southkorea #Monsoon2022 #monsoonseason #summer2022 #flooding #summersouthkorea #여름 #침수 #summertime",
"video_id": "1557013913216352258"
}
| 2
|
[
"A flooded street is depicted with significant water accumulation, reaching up to the knees. Several people are seen walking through the water, using umbrellas to shield themselves from the rain. The storefronts in the background have bright, illuminated signage, indicating it is likely nighttime or dusk. A few vehicles are partially visible, parked behind the fence.",
"The flooded street continues to be visible with water reaching ankle level. The street is now more illuminated, suggesting the presence of more streetlights or ambient light. A few vehicles are partially visible, parked behind the fence. The storefronts in the background have bright, illuminated signage. The overall scene appears to be during nighttime or dusk."
] |
1557013913216352258
|
A nighttime or dusk scene is depicted, showing a flooded street with water levels initially reaching up to the knees and later receding to ankle level. People are navigating through the water, using umbrellas for protection from the rain. The setting appears to be a commercial area with storefronts and parked vehicles, illuminated by streetlights and storefront signage. The overall context suggests a rainy event or flooding incident in an urban environment.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=SCkWqQ49yUQ",
"video_description": "이천 물류센터 화재와 관련해 관할 지자체가 재난안전대책본부를 구성했습니다. 경기 이천시는 엄태준 시장을 본부장으로 30명 규모의 재난안전대책본부를 편성했다고 밝혔습니다. 의료구호반과 장비지원반 등 11개 반으로 꾸려진 대책본부는 환자 이송과 현장 수색 작업 등에 참여합니다. 신준명[shinjm7529@ytn.co.kr] ※ '당신의 제보가 뉴스가 됩니다' YTN은 여러분의 소중한 제보를 기다립니다. [카카오톡] YTN을 검색해 채널 추가 [전화] 02-398-8585 [메일] social@ytn.co.kr [온라인 제보] www.ytn.co.kr ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0103_202004292044009865 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, social@ytn.co.kr, #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN & YTN PLUS 무단 전재 및 재배포금지",
"video_id": "SCkWqQ49yUQ"
}
| 2
|
[
"The image shows a damaged building with a large, blackened window, suggesting a fire incident. The text in the image indicates that the building was a molybdenum center inspection agency, and the event resulted in 38 deaths and 8 injuries.",
"The image continues to depict the aftermath of a fire incident at a building, focusing on a large, blackened window indicating severe damage. The text in the image reiterates the same details: the building was an inspection agency for a molybdenum center, and the incident caused 38 deaths and 8 injuries."
] |
SCkWqQ49yUQ
|
A severe fire incident occurred at a molybdenum center inspection agency, resulting in significant damage to the building, including a large, blackened window. The incident was fatal, causing 38 deaths and injuring 8 people, as evident from the aftermath shown in the consecutive frames.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=oRy1PP3KzDs",
"video_description": "29일 오후 경기도 이천 물류창고 공사현장에서 화재가 발생해 큰 인명피해를 냈습니다. 오후 7시30분 현재 확인된 사망자만 36명입니다.",
"video_id": "oRy1PP3KzDs"
}
| 2
|
[
"The image shows a building engulfed in thick, dark smoke, suggesting a large fire. Firefighters are actively using hoses to spray water towards the structure. The text on the image indicates a news broadcast, with the number of confirmed casualties at 11 and 14 individuals still in critical condition. The scene appears to be part of a news report covering the fire incident.",
"The current frame shows the logo of a news channel, with text indicating the location of the incident: 경기도 소방재난본부 (Gyeonggi-do Fire and Disaster Prevention Headquarters). This suggests the scene is part of a news report from a local emergency response agency, possibly continuing the coverage of the fire incident described in the previous frame."
] |
oRy1PP3KzDs
|
A large fire has broken out at a building, with firefighters actively working to extinguish the flames using hoses. The incident has resulted in significant casualties, with 11 confirmed and 14 individuals in critical condition. The event is being covered by a news broadcast, with the Gyeonggi-do Fire and Disaster Prevention Headquarters involved, indicating the fire occurred in their jurisdiction.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=rqRqdg-oxkU",
"video_description": "이번에도 샌드위치 패널... 처참한 이천 물류센터 화재현장",
"video_id": "rqRqdg-oxkU"
}
| 2
|
[
"The image shows a large building that is heavily damaged by fire. There are multiple streams of water being sprayed towards the structure by fire trucks, indicating that firefighters are actively working to extinguish the blaze. The building's exterior is charred, and thick smoke is billowing out from various points. The presence of emergency personnel suggests an ongoing rescue or firefighting operation.",
"The image continues to show the large building heavily damaged by fire. Thick smoke is billowing out from various points, and the building's exterior remains charred. Multiple streams of water are still being sprayed towards the structure by fire trucks, indicating the ongoing efforts of firefighters to extinguish the blaze. The presence of emergency personnel suggests that the firefighting operation is still in progress."
] |
rqRqdg-oxkU
|
A large building is engulfed in a severe fire, with thick smoke billowing out and its exterior heavily charred. Firefighters, assisted by multiple fire trucks, are actively working to extinguish the blaze, spraying streams of water onto the structure. The ongoing presence of emergency personnel indicates a rescue or firefighting operation in progress, suggesting a serious and potentially dangerous situation.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=6Z2tI74NGGQ",
"video_description": "[당시 현장 목격자 : 고개 돌리는 순간 연기가 엄청 심하게 나오더라고요. 설마 저게 불일까 그랬는데, 폭발음과 함께 불꽃이 일기 시작한 거죠.] 삽시간에 불길 번져 인명 피해 잇따라 \"우레탄 작업 중 폭발\" 추정 [서승현 / 경기 이천소방서장 : 화상 당하신 분들이 옷이 다 탄 걸로 봐서는 유증기가 폭발하면서 일어난 것으로 추정….] 완공 2개월 앞두고 참사 또 발생한 대형 화재 사상자 속출 ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0103_202004292050572443 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, social@ytn.co.kr, #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN & YTN PLUS 무단 전재 및 재배포금지",
"video_id": "6Z2tI74NGGQ"
}
| 2
|
[
"A building is engulfed in thick smoke, indicating a fire. A fire hose is spraying water onto the structure, suggesting that firefighters are actively working to extinguish the blaze.",
"Firefighters in full gear are actively working to extinguish the fire at a building. They are using hoses to spray water into the structure, where significant smoke and flames are visible. The text in Korean indicates a large fire has occurred and a resident has died."
] |
6Z2tI74NGGQ
|
A building fire is being actively extinguished by firefighters, who are using hoses to spray water into the smoke-filled structure. The fire is significant, with substantial smoke and flames visible, and has resulted in the death of at least one resident.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=JCKK0gu12zI",
"video_description": "경기 이천시 물류센터 화재가 대응 2단계로 격상한 가운데 인명피해가 속출하고 있다. 29일 경기도소방재난본부에 따르면 이날 오후 1시 32분 이천시 모가면 소고리 연면적 약 1만1043㎡인 물류센터 신축 공사현장에서 화재가 발생해 11명이 인명피해를 입었다.",
"video_id": "JCKK0gu12zI"
}
| 2
|
[
"The image shows a large building engulfed in heavy smoke and flames, indicating a significant fire. Firefighters are using hoses to spray water on the building, trying to control the fire. The building appears to be a multi-story structure, and there are several containers and equipment near the fire site. The text at the top of the image reads \"이천 물류센터 화재 현장,\" which translates to \"Fire scene at Icheon logistics center.\"",
"The current frame shows the logo of the Ministry of Land, Infrastructure and Transport, along with the text \"경로별 리더의 지름길\" (Route-wise leader's shortcut) and \"참여 뉴스통신\" (Participatory News Communication). This indicates a transition or segment in the video that focuses on updates or reports regarding the incident at the Icheon logistics center. The logo and text suggest that the video is providing official or detailed information related to the logistics center fire, possibly offering guidance or updates for different routes or areas affected by the incident."
] |
JCKK0gu12zI
|
A large fire broke out at the Icheon logistics center, a multi-story building, with firefighters attempting to control the blaze using hoses. The incident prompted an official response, with the Ministry of Land, Infrastructure and Transport providing updates and guidance on the situation, potentially including information on affected routes and areas.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=ZFWsFwpfGlE",
"video_description": "경찰 오늘 이천 물류창고 화재 중간 수사결과 발표 [전국네트워크] 경기남부지방경찰청이 오늘 오전 38명의 목숨을 앗아간 '경기도 이천 물류창고 화재' 사고에 대한 중간 수사 결과를 발표합니다. 지난 4월 29일 경기 이천시의 한 물류창고 공사현장에서 불이 나 38명이 숨지고 10명이 다친 바 있는데, 화재 원인은 지하 2층 우레탄 작업 중 발생한 미상의 화원에 의한 폭발로 추정되고 있습니다. 경찰은 4차례의 대규모 현장 감식과 함께 화재와 관련된 80여 명을 조사해 이 가운데 17명에 대해 업무상 과실치사상 혐의 등을 적용해 입건했습니다. ☞ MBN 유튜브 구독하기 ☞ https://goo.gl/6ZsJGT 📢 MBN 유튜브 커뮤니티https://www.youtube.com/user/mbn/community?disable_polymer=1 MBN 페이스북 http://www.facebook.com/mbntv MBN 인스타그램 https://www.instagram.com/mbn_news/ #MBN뉴스#전국네트워크#이천물류창고",
"video_id": "ZFWsFwpfGlE"
}
| 2
|
[
"In the image, two individuals wearing white protective suits and face masks are walking on the side of a road. One person is holding a green bag. They appear to be walking past traffic, including a truck. A person in the background is taking photos or videos of them, using a camera or similar device.",
"The current frame shows a group of people walking in an area with debris and trash, suggesting they are inspecting or investigating a site. One individual holds a blue folder, possibly containing documents or notes. The environment appears to be a neglected or damaged area, with scattered waste and industrial elements like barrels. The group is dressed casually, indicating they might be on a routine inspection or cleanup operation. The text \"MBN\" in the corner indicates that this is footage from a media outlet."
] |
ZFWsFwpfGlE
|
A group of individuals, including some wearing protective suits, are inspecting and investigating a neglected or damaged area with debris and trash. They appear to be on a routine inspection or cleanup operation, with some carrying items such as a green bag and a blue folder possibly containing documents or notes. The scene is being documented by a person taking photos or videos, and the footage is from a media outlet, suggesting a potential environmental or industrial incident is being assessed and reported on.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=2SCMvAXvBLM",
"video_description": "경기도 이천 모가면의 한 물류창고 공사현장에서 29일 오후 1시32분 쯤 불이 나 현재까지 5명이 사망한 것으로 확인되고 있습니다. 소방당국은 대응 2단계를 발령하고 소방대원 60명과 펌프차 등 장비 27대를 투입해 진화작업을 벌이고 있습니다. 소방 관계자에 따르면 물류창고의 지하 공사현장에서 불이 시작된 것으로 보이며, 사망자는 앞으로 더 늘어날 전망입니다. 소방 대응단계는 화재 규모에 따라 1~3단계로 나뉘어지는데, 1단계는 4개 이하 소방서가 합동 대응하며 2단계는 5~9개 소방서, 3단계는 10개 이상 소방서가 함께 진화작업을 벌입니다. https://imnews.imbc.com/original/todayfield/5749059_32167.html #경기도 #이천 #물류창고 #화재 #소방당국 #대응 2단계 #진화작업",
"video_id": "2SCMvAXvBLM"
}
| 2
|
[
"The image depicts a large building engulfed in smoke and fire, with thick black smoke billowing from the structure. There are several vehicles, including fire trucks, parked nearby, indicating an emergency response. People are gathered around the scene, possibly evacuating or observing the situation. The text \"Right Now\" suggests that the video is live or showing current events.",
"The current frame shows a large building still engulfed in thick black smoke. Fire trucks and emergency vehicles are positioned nearby, actively working to address the situation. People are visible in the vicinity, likely coordinating the response or waiting for further instructions. The text \"Right Now\" continues to indicate that this is a live broadcast or up-to-date footage."
] |
2SCMvAXvBLM
|
A large building is on fire, with thick black smoke billowing from the structure, and emergency responders are actively working to address the situation, with fire trucks and vehicles on the scene, while people evacuate or observe from a distance, as captured in a live or real-time video broadcast.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=n8dcNr14bm8",
"video_description": "38명이 숨진 경기도 이천 물류창고 공사장 화재 현장에서 경찰이 아직 수습되지 않은 유해 일부와 유류품 등을 찾기 위한 정밀 수색을 하고 있습니다. 경기남부지방경찰청 과학수사대는 오늘(2일) 오전 9시부터 중장비와 과학수사요원 15명을 투입해 이천시 모가면 물류창고 공사 현장을 정밀 수색하고 있습니다. 오늘 수색은 사고로 숨진 사망자들의 유해 가운데 아직 수습되지 않은 일부와 유류품을 찾는 데 주력한다는 방침입니다. 앞서 경찰은 국립과학수사연구원에 의뢰한 DNA 조사를 통해 신원이 확인되지 않은 9명 가운데 8명의 신원을 확인해 유가족들에게 전했습니다. 경찰은 남은 신원 미확인자 1명의 DNA 검사 결과도 오늘 안에 나올 것으로 기대하고 있습니다. ※ '당신의 제보가 뉴스가 됩니다' YTN은 여러분의 소중한 제보를 기다립니다. [카카오톡] YTN을 검색해 채널 추가 [전화] 02-398-8585 [메일] social@ytn.co.kr [온라인 제보] www.ytn.co.kr ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0103_202005021020478614 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, social@ytn.co.kr, #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN & YTN PLUS 무단 전재 및 재배포금지",
"video_id": "n8dcNr14bm8"
}
| 2
|
[
"The image shows two individuals in protective white suits with one wearing a black helmet labeled \"과학 수사\" (scientific investigation) and a gas mask. They appear to be part of a scientific investigation team. The text at the bottom reads \"경찰, 이천 물류창고 화재현장 정밀 수색\" (police, detailed search of the Incheon logistics warehouse fire scene). The scene suggests a response to a fire incident at a warehouse, with the focus on the search and investigation.",
"The individuals in protective white suits and helmets, including the one labeled \"과학 수사\" (scientific investigation), are continuing their detailed search of the Incheon logistics warehouse fire scene. They are examining the area closely, likely looking for evidence or signs of the cause of the fire. The scene emphasizes the ongoing and thorough nature of the investigation."
] |
n8dcNr14bm8
|
A team of investigators, including a scientific investigation expert, in protective gear, conduct a detailed search of a logistics warehouse in Incheon following a fire incident, examining the area closely for evidence and signs of the fire's cause.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=Z1TmlndGWrg",
"video_description": "대규모 인명 피해가 발생한 경기 이천 물류센터 공사장 화재와 관련해 경찰이 전담 수사본부를 편성했습니다. 경기 남부지방경찰청은 광역수사대와 과학수사대 등 125명 규모의 전담 수사본부를 편성했다고 밝혔습니다. 수사본부는 오늘(30일) 오전 10시 반 국립과학수사연구원, 소방당국과 함께 합동으로 현장감식을 진행할 예정입니다. 또, 공사 과정에서 소방법이나 건축법을 위반한 사항이 있는지 확인할 방침입니다. 신준명[shinjm7529@ytn.co.kr] ※ '당신의 제보가 뉴스가 됩니다' YTN은 여러분의 소중한 제보를 기다립니다. [카카오톡] YTN을 검색해 채널 추가 [전화] 02-398-8585 [메일] social@ytn.co.kr [온라인 제보] www.ytn.co.kr ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0103_202004300027155233 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, social@ytn.co.kr, #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN & YTN PLUS 무단 전재 및 재배포금지",
"video_id": "Z1TmlndGWrg"
}
| 2
|
[
"The frame shows a damaged building with a severely cracked and shattered window. There is visible smoke or dust around the window, indicating a recent incident such as an explosion or fire. Text in Korean at the top of the image suggests it's related to a water tanker explosion, and additional text at the bottom mentions a demolition and a date, indicating the event's timeline. A vehicle is partially visible in the foreground, possibly parked nearby.",
"The current frame depicts a building with a severely damaged window, characterized by large cracks and shattered glass, indicating a significant incident. The window appears to be part of a water tanker, as suggested by the Korean text. The smoke or dust around the window reinforces the impression of a recent explosion or fire. Additional Korean text at the bottom of the image provides context about the demolition and a specific date, suggesting the event is being covered in a news report. A vehicle is partially visible in the foreground, likely parked nearby, which could be related to emergency services or witnesses."
] |
Z1TmlndGWrg
|
A water tanker explosion occurred at a building, causing significant damage to a window, characterized by large cracks and shattered glass, and surrounded by smoke or dust. The incident is part of a news report, with the building slated for demolition on a specified date. Emergency services or witnesses may be present, as indicated by a vehicle parked nearby.
|
A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.
|
[
"Flames engulfing the construction site in Icheon, South Korea on April 29, 2020, during a fire incident",
"Firefighters battling the blaze with water hoses during the Icheon, South Korea fire on 29 April 2020",
"Emergency responders rushing to rescue trapped workers during the Icheon, South Korea fire on April 29, 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Aerial footage of the construction site fire in Icheon, South Korea showing the extent of the damage on 29 April 2020"
] |
[
"Firefighters battling the blaze at the construction site in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing people trapped in the burning building during the Icheon, South Korea fire on 29 April 2020",
"Paramedics treating injured people at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Police investigating the cause of the fire in Icheon, South Korea on 29 April 2020",
"Rescue teams searching for missing people in the rubble after the Icheon, South Korea fire on 29 April 2020"
] |
[
"Flames engulfing the construction site in Icheon, South Korea during the fire on 29 April 2020",
"People running away from the burning building during the Icheon fire in South Korea on April 29, 2020",
"Firefighters arriving at the scene of a fire in Icheon, South Korea on April 29, 2020",
"Emergency responders rescuing injured individuals from a fire in Icheon, South Korea on 29 April 2020",
"Smoke billowing into the air as the fire rages on in Icheon, South Korea on 29 April 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%EC%9D%B4%EC%B2%9C_%EB%AC%BC%EB%A5%98%EC%84%BC%ED%84%B0_%EA%B3%B5%EC%82%AC%EC%9E%A5_%ED%99%94%EC%9E%AC",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, as these would be the most visual and relevant aspects of the incident. The extracted events should focus on the fire, rescue efforts, and potential damage, as these are the most likely to be captured on video.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. People running away from the burning building\n3. Firefighters arriving at the scene\n4. Emergency responders rescuing injured individuals\n5. Smoke billowing into the air as the fire rages on",
"en_article_excerpt": "A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Icheon_fire",
"event_category": "disasters",
"event_name": "icheon_fire",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the typical scenes that could be visualized in a video associated with a major fire at a construction site, such as the fire itself, rescue efforts, and the aftermath. Given the location and context of the event, it is likely that the extracted events will involve emergency responders, construction equipment, and damaged buildings.\n\nEVENTS:\n1. Flames engulfing the construction site\n2. Firefighters battling the blaze with water hoses\n3. Emergency responders rushing to rescue trapped workers\n4. Paramedics treating injured people at the scene\n5. Aerial footage of the construction site showing the extent of the damage",
"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: A major fire occurred on 29 April 2020 at a construction site in Icheon, South Korea, killing 39 people and injuring another 10.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a major fire at a construction site in Icheon, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage assessment, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the construction site\n2. Emergency responders rescuing people trapped in the burning building\n3. Paramedics treating injured people at the scene\n4. Police investigating the cause of the fire\n5. Rescue teams searching for missing people in the rubble",
"video_URL": "http://youtube.com/watch?v=tHSh4jwdIJg",
"video_description": "29일 오후 1시 반쯤 경기도 이천시 모가면의 한 물류창고 공사현장에서 불이 났습니다. 이 불로 오후 5시 기준 25명이 숨진 것으로 소방당국은 추정하고 있습니다. 불이 났을 당시 현장에서 9개 업체, 80여 명이 작업 중이던 것으로 알려져 인명 피해가 더 커질 가능성도 있는 상황입니다. 물류창고 지하 2층에서 불이 시작된 것으로 추정하며, 소방당국은 \"불이 빠르게 확산되는 것으로 봐서 가연성 물질인 우레탄폼 작업 중 화재가 난 것으로 추정한다\"고 말했습니다. 현장 영상을 전해드립니다. 이천 물류창고 화재 현장 상황…소방당국 \"우레탄폼 원인 추정\" / 비디오머그 ✔신뢰할 수 있는 재미, 비디오머그 VIDEOMUG #비디오머그 #이천 #물류창고_화재 ▶비디오머그 채널 구독하기 : https://n.sbs.co.kr/mugTube ▶Homepage : https://n.sbs.co.kr/videomug ▶Facebook : https://www.facebook.com/videomug ▶Twitter : https://twitter.com/videomug_sbs",
"video_id": "tHSh4jwdIJg"
}
| 2
|
[
"The current frame shows a large building engulfed in smoke and fire. The building is in the process of burning, with thick smoke billowing out from various parts of its structure. There are vehicles on a nearby road, indicating a populated area. A person is visible walking near the building. Text on the image in Korean suggests that the fire may have started during a work shift involving a robot in a specific room of the building.",
"The current frame continues to depict the large building engulfed in smoke and fire, with thick smoke still billowing out. The fire appears to be intensifying, as flames are visible on the building's exterior. Vehicles are still on the nearby road, indicating the area remains accessible. The person who was previously seen walking near the building is now further away, suggesting they may be moving away from the fire. The text in Korean remains on the image, reinforcing the suspicion that the fire began during a work shift involving a robot in a specific room of the building."
] |
tHSh4jwdIJg
|
A large building in a populated area is on fire, with thick smoke and flames visible. The fire appears to have started during a work shift involving a robot in a specific room, as indicated by text in Korean. A person is present near the building initially but moves away as the fire intensifies, suggesting an evacuation or attempt to escape the danger zone. The fire continues to spread, with vehicles remaining in the nearby area, indicating that the road is still accessible despite the emergency.
|
On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.
|
[
"A person setting fire to the office building in Daegu, South Korea on 9 June 2022",
"A person setting fire to the office building during the arson attack in Daegu, South Korea on 9 June 2022",
"Flames engulfing a building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing the building during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating the office building in a state of panic due to a fire in Daegu, South Korea on 9 June 2022",
"People evacuating the office building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Firefighters arriving at the scene of a fire in Daegu, South Korea on 9 June 2022 to extinguish the blaze",
"Firefighters arriving at the scene to extinguish the fire during the arson attack in Daegu, South Korea on June 9, 2022",
"Paramedics treating injured people outside the building after fire in Daegu, South Korea on 9 June 2022",
"Paramedics treating injured people outside the building after arson attack in Daegu, South Korea on June 9, 2022"
] |
[
"Firefighters battling the blaze at the office building in Daegu, South Korea on June 9, 2022",
"Firefighters battling the blaze at the office building in Daegu, South Korea after alleged arson attack on 9 June 2022",
"People evacuating a building in a state of panic due to a fire in Daegu, South Korea on June 9, 2022",
"People evacuating the building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Emergency responders providing medical aid to injured victims of the June 9, 2022 fire in Daegu, South Korea",
"Emergency responders providing medical aid to injured victims of the June 9 2022 arson attack in Daegu, South Korea",
"Flames engulfing parts of the office building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing parts of the office building in Daegu, South Korea during the arson attack on 9 June 2022",
"Rescue teams searching for survivors in the building damaged by the fire in Daegu, South Korea on 9 June 2022",
"Rescue teams searching for survivors in the damaged building after the arson attack in Daegu, South Korea on 9 June 2022"
] |
[
"Flames engulfing the office building in Daegu, South Korea on 9 June 2022 fire incident",
"Flames engulfing the office building in Daegu, South Korea due to arson attack on 9 June 2022",
"Firefighters arriving at the scene and battling the blaze in Daegu, South Korea on 9 June 2022 during a large fire incident",
"Firefighters arriving at the scene and battling the blaze during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating building after fire in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"People evacuating building after arson attack in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"Emergency medical personnel treating injured individuals outside the building after fire in Daegu, South Korea on 9 June 2022",
"Emergency medical personnel treating injured individuals outside the building after the arson attack in Daegu, South Korea on June 9, 2022",
"Damage to the office building in Daegu, South Korea after the fire on 9 June 2022 has been extinguished",
"Damage to the office building in Daegu, South Korea after the arson attack fire was extinguished on 9 June 2022"
] |
{
"article_url": "https://namu.wiki/w/%EB%8C%80%EA%B5%AC%20%EB%B3%80%ED%98%B8%EC%82%AC%20%EC%82%AC%EB%AC%B4%EC%8B%A4%20%EB%B0%A9%ED%99%94%20%EC%82%AC%EA%B1%B4",
"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: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: To extract events from the given query, it makes sense to focus on the concrete and visual aspects of the fire and its aftermath, considering what could be reasonably captured in a video. This includes the fire itself, the response of emergency services, and the impact on the building and its occupants.\n\nEVENTS:\n1. Flames engulfing the office building in Daegu\n2. Firefighters arriving at the scene and battling the blaze\n3. People evacuating the building, some injured and covered in soot\n4. Emergency medical personnel treating injured individuals outside the building\n5. Damage to the office building after the fire has been extinguished",
"en_article_excerpt": "On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.",
"en_article_url": "https://en.wikipedia.org/wiki/Daegu_office_fire",
"event_category": "disasters",
"event_name": "daegu_office_fire",
"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: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the actions and consequences leading up to and resulting from the arson attack, such as the fire breaking out, people evacuating, and emergency responders arriving. These events are concrete, visual, and likely to be captured in a video related to the incident.\n\nEVENTS:\n1. A person setting fire to the office building\n2. Flames engulfing the building\n3. People evacuating the office building in a state of panic\n4. Firefighters arriving at the scene to extinguish the fire\n5. Paramedics treating injured people outside the building",
"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: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a fire at an office building in Daegu, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage to the building, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the office building\n2. People evacuating the building in a state of panic\n3. Emergency responders providing medical aid to injured victims\n4. Flames engulfing parts of the office building\n5. Rescue teams searching for survivors in the damaged building",
"video_URL": "http://youtube.com/watch?v=I2CxZCzE5pE",
"video_description": "지금부턴 어제(9일) 대구의 한 변호사 사무실에서 난 화재 관련해서 저희가 새롭게 취재한 내용 전해드리겠습니다. 저희 취재진이 사고가 난 건물의 내부 영상을 입수했습니다. 불이 시작된 건물 2층은 형체를 알아보기 어려울 정도로 검게 타버린 모습이었습니다. ▶ 기사 전문 https://news.jtbc.joins.com/html/151/NB12062151.html ▶ 뉴스룸 다시보기 (https://bit.ly/2nxI8jQ) #이승환기자 #JTBC뉴스룸 ☞JTBC뉴스레터 구독하기 (https://bit.ly/3IOFY5H) ☞JTBC유튜브 구독하기 (https://bit.ly/2hYgWZg) ☞JTBC유튜브 커뮤니티 (https://bit.ly/2LZIwke) #JTBC뉴스 공식 페이지 (홈페이지) https://news.jtbc.joins.com (APP) https://bit.ly/1r04W2D 페이스북 https://www.facebook.com/jtbcnews 트위터 https://twitter.com/JTBC_news 인스타그램 https://www.instagram.com/jtbcnews ☏ 제보하기 https://bit.ly/1krluzF 방송사 : JTBC (https://jtbc.joins.com)",
"video_id": "I2CxZCzE5pE"
}
| 2
|
[
"The current frame shows a nighttime scene in an urban setting, possibly inside a building or near a public transportation facility. The area is dimly lit with reflections visible on the glass door. There is a sign with the numbers \"2\" and \"1\" indicating directions or floor levels. The text in Korean at the top of the image reads \"지옥이 된 '검은 사무실'\" which translates to \"The 'dark office' turned into hell,\" and the text at the bottom reads \"황급히 대피했던 사람들은 다시 사고 현장 찾아와\" which translates to \"People who hastily evacuated are back at the accident site.\" This suggests that the video is discussing a recent incident or accident involving a place referred to as a 'dark office,' and individuals who previously evacuated are now returning to the site.",
"The scene continues in the same dimly lit urban setting, likely within a building or near a public transportation area. The reflection on the glass remains visible, and the \"2\" and \"1\" directional sign is still present. The ongoing theme is the aftermath of a distressing event at a place known as the 'dark office,' with individuals returning to the accident site after a hurried evacuation."
] |
I2CxZCzE5pE
|
The video depicts the aftermath of a distressing incident at a location referred to as the "dark office," set in a dimly lit urban environment, possibly within a building or near a public transportation facility. Individuals who had hastily evacuated the scene are shown returning to the accident site, suggesting that the initial emergency has passed, and people are now assessing the situation or investigating what happened. The setting appears to be indoors, with visible signs indicating floor levels, and the overall context implies a serious event occurred, prompting an evacuation and a subsequent return by those involved.
|
On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.
|
[
"A person setting fire to the office building in Daegu, South Korea on 9 June 2022",
"A person setting fire to the office building during the arson attack in Daegu, South Korea on 9 June 2022",
"Flames engulfing a building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing the building during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating the office building in a state of panic due to a fire in Daegu, South Korea on 9 June 2022",
"People evacuating the office building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Firefighters arriving at the scene of a fire in Daegu, South Korea on 9 June 2022 to extinguish the blaze",
"Firefighters arriving at the scene to extinguish the fire during the arson attack in Daegu, South Korea on June 9, 2022",
"Paramedics treating injured people outside the building after fire in Daegu, South Korea on 9 June 2022",
"Paramedics treating injured people outside the building after arson attack in Daegu, South Korea on June 9, 2022"
] |
[
"Firefighters battling the blaze at the office building in Daegu, South Korea on June 9, 2022",
"Firefighters battling the blaze at the office building in Daegu, South Korea after alleged arson attack on 9 June 2022",
"People evacuating a building in a state of panic due to a fire in Daegu, South Korea on June 9, 2022",
"People evacuating the building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Emergency responders providing medical aid to injured victims of the June 9, 2022 fire in Daegu, South Korea",
"Emergency responders providing medical aid to injured victims of the June 9 2022 arson attack in Daegu, South Korea",
"Flames engulfing parts of the office building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing parts of the office building in Daegu, South Korea during the arson attack on 9 June 2022",
"Rescue teams searching for survivors in the building damaged by the fire in Daegu, South Korea on 9 June 2022",
"Rescue teams searching for survivors in the damaged building after the arson attack in Daegu, South Korea on 9 June 2022"
] |
[
"Flames engulfing the office building in Daegu, South Korea on 9 June 2022 fire incident",
"Flames engulfing the office building in Daegu, South Korea due to arson attack on 9 June 2022",
"Firefighters arriving at the scene and battling the blaze in Daegu, South Korea on 9 June 2022 during a large fire incident",
"Firefighters arriving at the scene and battling the blaze during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating building after fire in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"People evacuating building after arson attack in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"Emergency medical personnel treating injured individuals outside the building after fire in Daegu, South Korea on 9 June 2022",
"Emergency medical personnel treating injured individuals outside the building after the arson attack in Daegu, South Korea on June 9, 2022",
"Damage to the office building in Daegu, South Korea after the fire on 9 June 2022 has been extinguished",
"Damage to the office building in Daegu, South Korea after the arson attack fire was extinguished on 9 June 2022"
] |
{
"article_url": "https://namu.wiki/w/%EB%8C%80%EA%B5%AC%20%EB%B3%80%ED%98%B8%EC%82%AC%20%EC%82%AC%EB%AC%B4%EC%8B%A4%20%EB%B0%A9%ED%99%94%20%EC%82%AC%EA%B1%B4",
"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: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: To extract events from the given query, it makes sense to focus on the concrete and visual aspects of the fire and its aftermath, considering what could be reasonably captured in a video. This includes the fire itself, the response of emergency services, and the impact on the building and its occupants.\n\nEVENTS:\n1. Flames engulfing the office building in Daegu\n2. Firefighters arriving at the scene and battling the blaze\n3. People evacuating the building, some injured and covered in soot\n4. Emergency medical personnel treating injured individuals outside the building\n5. Damage to the office building after the fire has been extinguished",
"en_article_excerpt": "On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.",
"en_article_url": "https://en.wikipedia.org/wiki/Daegu_office_fire",
"event_category": "disasters",
"event_name": "daegu_office_fire",
"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: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the actions and consequences leading up to and resulting from the arson attack, such as the fire breaking out, people evacuating, and emergency responders arriving. These events are concrete, visual, and likely to be captured in a video related to the incident.\n\nEVENTS:\n1. A person setting fire to the office building\n2. Flames engulfing the building\n3. People evacuating the office building in a state of panic\n4. Firefighters arriving at the scene to extinguish the fire\n5. Paramedics treating injured people outside the building",
"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: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a fire at an office building in Daegu, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage to the building, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the office building\n2. People evacuating the building in a state of panic\n3. Emergency responders providing medical aid to injured victims\n4. Flames engulfing parts of the office building\n5. Rescue teams searching for survivors in the damaged building",
"video_URL": "http://youtube.com/watch?v=oVzTD-Qy5HM",
"video_description": "대구 변호사 사무실 빌딩 방화 추정 화재…7명 사망 [앵커] 오늘(9일) 낮 대구 지법 근처의 한 변호사 사무실에서 방화로 보이는 화재가 발생해, 방화 용의자 1명을 포함해 7명이 숨지고 40여 명이 다쳤습니다. 현장 취재기자 연결해 자세한 소식 들어봅니다. 정지훈 기자. [기자] 네, 대구 변호사 사무실 빌딩 화재 현장에 나와 있습니다. 제 바로 뒤편 건물을 보시면 전면 유리창들이 깨진 걸 보실 수 있을텐데요. 신고를 받고 출동한 소방당국이 화재 진압과 구조를 위해 일부러 깨드린 겁니다. 당시 상황이 얼마나 긴박했는지를 알 수 있습니다. 이 건물은 지하 2층, 지상 5층짜리 건물로 오늘(9일) 오전 10시 55분쯤 건물 2층에서 불이 났습니다. 불은 소방 당국에 의해 20여 분만에 꺼졌지만, 남자 5명, 여자 2명 등 7명이 숨지고 40여 명이 화상 또는 연기를 흡입해 병원 치료를 받고 있습니다. 이들 사망자는 2층 203호에서 모두 발견됐는데요. 화재 발생 당시 119에는 \"건물 2층에서 검은 연기가 보이고 폭발음이 들렸다\"는 신고가 접수됐습니다. 사망자의 신원이 아직 확인되지 않았습니다. 같은 장소에서 방화 용의자도 숨진 채 발견됐습니다. 불이 나자 건물 3층에 있던 사람들은 4층 등 건물 위층으로, 일부는 건물 밖에 설치된 비상계단을 통해 옥상으로 대피하기도 했습니다. 화재 현장에 있었던 목격자의 말 들어보시겠습니다. [현장 목격자] \"어느 순간 폭발음이 팡 터지면서 유리창 깨지는 소리가 계속 나고 제가 너무 놀라서 상담실에서 뛰쳐 나와서 문을 열려고 하니 이미 뜨거웠어요. 그래서 몸으로 문을 밀쳐서 열고…\" 소방당국은 화재 진압 과정에서 급격히 연소가 확대돼 인명 피해 규모가 커졌다고 설명했습니다. 당국은 브리핑에서 \"화재 건물 지하층에만 스프링클러가 있고 지상층에는 스프링클러가 설치돼 있지 않다\"고 밝혔습니다. 화재가 발생한 빌딩은 법원 뒤쪽에 위치해 변호사 사무실이 밀집한 곳입니다. 경찰은 50대 방화 용의자가 CCTV상 주거지에서 뭔가를 들고 나오는 장면을 확인하고 자세한 화재 경위를 조사하고 있는데요. 경찰은 불이 난 변호사 사무실에 의뢰된 송사 사건의 상대인 용의자가 사무실에 불을 낸 것으로 보고, 수사전담팀을 편성해 사건 발생 경위 등을 집중 조사할 방침입니다. 지금까지 대구에서 연합뉴스TV 정지훈입니다. #대구_변호사_사무실 #폭발 #방화 연합뉴스TV 기사문의 및 제보 : 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": "oVzTD-Qy5HM"
}
| 2
|
[
"The image shows a group of individuals, some wearing blue uniforms and masks, engaged in an outdoor activity. A person in the foreground is holding a radio or phone to their ear, suggesting communication or coordination. In the background, there is a fire truck and other people, some wearing helmets with \"KCS\" written on them. The scene appears to be a response to an emergency situation, possibly involving the police or emergency services. The text at the bottom mentions a \"40-year memorial participation incident,\" with details about an investigation. The setting suggests an ongoing situation that requires attention and response.",
"The image shows a man in a white shirt and glasses speaking into a microphone, presumably giving a report or statement. He is wearing a mask and has a lanyard with an ID badge around his neck. In the background, there are several individuals, some wearing blue uniforms and masks, indicating the presence of security or law enforcement personnel. The setting appears to be outside a building, with some trees and a sign visible in the background. The text at the bottom of the screen mentions a \"16:50 new report on the incident,\" suggesting that the man is providing updates on an ongoing situation. The overall atmosphere suggests that the event is being covered by the media, and the presence of uniformed personnel indicates a serious or official nature of the event."
] |
oVzTD-Qy5HM
|
An emergency situation is unfolding, with a group of individuals, including those in blue uniforms and masks, responding to an incident. The scene involves a fire truck and personnel with "KCS" on their helmets, indicating a coordinated response effort. A person is communicating via radio or phone, suggesting a need for real-time coordination. Later, a man in a white shirt gives a report or statement into a microphone, providing updates on the incident, which is being covered by the media. The event is serious enough to warrant an official response and media attention, with the man's statement suggesting an ongoing investigation into a significant incident, potentially related to a "40-year memorial participation incident" mentioned earlier. The overall context implies a solemn and official tone, with law enforcement and emergency services personnel involved in managing and responding to the situation.
|
On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.
|
[
"A person setting fire to the office building in Daegu, South Korea on 9 June 2022",
"A person setting fire to the office building during the arson attack in Daegu, South Korea on 9 June 2022",
"Flames engulfing a building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing the building during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating the office building in a state of panic due to a fire in Daegu, South Korea on 9 June 2022",
"People evacuating the office building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Firefighters arriving at the scene of a fire in Daegu, South Korea on 9 June 2022 to extinguish the blaze",
"Firefighters arriving at the scene to extinguish the fire during the arson attack in Daegu, South Korea on June 9, 2022",
"Paramedics treating injured people outside the building after fire in Daegu, South Korea on 9 June 2022",
"Paramedics treating injured people outside the building after arson attack in Daegu, South Korea on June 9, 2022"
] |
[
"Firefighters battling the blaze at the office building in Daegu, South Korea on June 9, 2022",
"Firefighters battling the blaze at the office building in Daegu, South Korea after alleged arson attack on 9 June 2022",
"People evacuating a building in a state of panic due to a fire in Daegu, South Korea on June 9, 2022",
"People evacuating the building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Emergency responders providing medical aid to injured victims of the June 9, 2022 fire in Daegu, South Korea",
"Emergency responders providing medical aid to injured victims of the June 9 2022 arson attack in Daegu, South Korea",
"Flames engulfing parts of the office building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing parts of the office building in Daegu, South Korea during the arson attack on 9 June 2022",
"Rescue teams searching for survivors in the building damaged by the fire in Daegu, South Korea on 9 June 2022",
"Rescue teams searching for survivors in the damaged building after the arson attack in Daegu, South Korea on 9 June 2022"
] |
[
"Flames engulfing the office building in Daegu, South Korea on 9 June 2022 fire incident",
"Flames engulfing the office building in Daegu, South Korea due to arson attack on 9 June 2022",
"Firefighters arriving at the scene and battling the blaze in Daegu, South Korea on 9 June 2022 during a large fire incident",
"Firefighters arriving at the scene and battling the blaze during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating building after fire in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"People evacuating building after arson attack in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"Emergency medical personnel treating injured individuals outside the building after fire in Daegu, South Korea on 9 June 2022",
"Emergency medical personnel treating injured individuals outside the building after the arson attack in Daegu, South Korea on June 9, 2022",
"Damage to the office building in Daegu, South Korea after the fire on 9 June 2022 has been extinguished",
"Damage to the office building in Daegu, South Korea after the arson attack fire was extinguished on 9 June 2022"
] |
{
"article_url": "https://namu.wiki/w/%EB%8C%80%EA%B5%AC%20%EB%B3%80%ED%98%B8%EC%82%AC%20%EC%82%AC%EB%AC%B4%EC%8B%A4%20%EB%B0%A9%ED%99%94%20%EC%82%AC%EA%B1%B4",
"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: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: To extract events from the given query, it makes sense to focus on the concrete and visual aspects of the fire and its aftermath, considering what could be reasonably captured in a video. This includes the fire itself, the response of emergency services, and the impact on the building and its occupants.\n\nEVENTS:\n1. Flames engulfing the office building in Daegu\n2. Firefighters arriving at the scene and battling the blaze\n3. People evacuating the building, some injured and covered in soot\n4. Emergency medical personnel treating injured individuals outside the building\n5. Damage to the office building after the fire has been extinguished",
"en_article_excerpt": "On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.",
"en_article_url": "https://en.wikipedia.org/wiki/Daegu_office_fire",
"event_category": "disasters",
"event_name": "daegu_office_fire",
"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: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the actions and consequences leading up to and resulting from the arson attack, such as the fire breaking out, people evacuating, and emergency responders arriving. These events are concrete, visual, and likely to be captured in a video related to the incident.\n\nEVENTS:\n1. A person setting fire to the office building\n2. Flames engulfing the building\n3. People evacuating the office building in a state of panic\n4. Firefighters arriving at the scene to extinguish the fire\n5. Paramedics treating injured people outside the building",
"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: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a fire at an office building in Daegu, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage to the building, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the office building\n2. People evacuating the building in a state of panic\n3. Emergency responders providing medical aid to injured victims\n4. Flames engulfing parts of the office building\n5. Rescue teams searching for survivors in the damaged building",
"video_URL": "http://twitter.com/i/status/1534839444830044161",
"video_description": "대구 변호사 사무실 화재",
"video_id": "1534839444830044161"
}
| 2
|
[
"The image shows a news broadcast with several workers wearing safety vests and helmets working on a rooftop. They are positioned near a ladder, possibly installing or repairing something. The scene is captured in black and white, and text in Korean is displayed on the screen, indicating that this is related to a 'Glass Residual' incident, with one person having fallen off the building's surface. The image includes a news channel logo and contact information.",
"The image shows a news broadcast featuring a female reporter standing outside a building. She is wearing a white face mask and holding a microphone with the \"KBS\" logo. The reporter appears to be delivering a report or update on a topic. The background shows a building and a person in a safety vest and helmet, suggesting a work or construction site nearby. The text on the screen is in Korean, and there is a news channel logo at the bottom right corner."
] |
1534839444830044161
|
A news broadcast is reporting on a 'Glass Residual' incident where a person fell off a building's surface during construction or repair work. The incident occurred on a rooftop where workers in safety vests and helmets were present, near a ladder, possibly installing or repairing something. A female reporter from KBS news channel is providing live updates from the scene, standing outside the building, wearing a face mask and holding a microphone, with a construction site visible in the background.
|
On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.
|
[
"A person setting fire to the office building in Daegu, South Korea on 9 June 2022",
"A person setting fire to the office building during the arson attack in Daegu, South Korea on 9 June 2022",
"Flames engulfing a building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing the building during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating the office building in a state of panic due to a fire in Daegu, South Korea on 9 June 2022",
"People evacuating the office building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Firefighters arriving at the scene of a fire in Daegu, South Korea on 9 June 2022 to extinguish the blaze",
"Firefighters arriving at the scene to extinguish the fire during the arson attack in Daegu, South Korea on June 9, 2022",
"Paramedics treating injured people outside the building after fire in Daegu, South Korea on 9 June 2022",
"Paramedics treating injured people outside the building after arson attack in Daegu, South Korea on June 9, 2022"
] |
[
"Firefighters battling the blaze at the office building in Daegu, South Korea on June 9, 2022",
"Firefighters battling the blaze at the office building in Daegu, South Korea after alleged arson attack on 9 June 2022",
"People evacuating a building in a state of panic due to a fire in Daegu, South Korea on June 9, 2022",
"People evacuating the building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Emergency responders providing medical aid to injured victims of the June 9, 2022 fire in Daegu, South Korea",
"Emergency responders providing medical aid to injured victims of the June 9 2022 arson attack in Daegu, South Korea",
"Flames engulfing parts of the office building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing parts of the office building in Daegu, South Korea during the arson attack on 9 June 2022",
"Rescue teams searching for survivors in the building damaged by the fire in Daegu, South Korea on 9 June 2022",
"Rescue teams searching for survivors in the damaged building after the arson attack in Daegu, South Korea on 9 June 2022"
] |
[
"Flames engulfing the office building in Daegu, South Korea on 9 June 2022 fire incident",
"Flames engulfing the office building in Daegu, South Korea due to arson attack on 9 June 2022",
"Firefighters arriving at the scene and battling the blaze in Daegu, South Korea on 9 June 2022 during a large fire incident",
"Firefighters arriving at the scene and battling the blaze during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating building after fire in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"People evacuating building after arson attack in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"Emergency medical personnel treating injured individuals outside the building after fire in Daegu, South Korea on 9 June 2022",
"Emergency medical personnel treating injured individuals outside the building after the arson attack in Daegu, South Korea on June 9, 2022",
"Damage to the office building in Daegu, South Korea after the fire on 9 June 2022 has been extinguished",
"Damage to the office building in Daegu, South Korea after the arson attack fire was extinguished on 9 June 2022"
] |
{
"article_url": "https://namu.wiki/w/%EB%8C%80%EA%B5%AC%20%EB%B3%80%ED%98%B8%EC%82%AC%20%EC%82%AC%EB%AC%B4%EC%8B%A4%20%EB%B0%A9%ED%99%94%20%EC%82%AC%EA%B1%B4",
"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: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: To extract events from the given query, it makes sense to focus on the concrete and visual aspects of the fire and its aftermath, considering what could be reasonably captured in a video. This includes the fire itself, the response of emergency services, and the impact on the building and its occupants.\n\nEVENTS:\n1. Flames engulfing the office building in Daegu\n2. Firefighters arriving at the scene and battling the blaze\n3. People evacuating the building, some injured and covered in soot\n4. Emergency medical personnel treating injured individuals outside the building\n5. Damage to the office building after the fire has been extinguished",
"en_article_excerpt": "On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.",
"en_article_url": "https://en.wikipedia.org/wiki/Daegu_office_fire",
"event_category": "disasters",
"event_name": "daegu_office_fire",
"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: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the actions and consequences leading up to and resulting from the arson attack, such as the fire breaking out, people evacuating, and emergency responders arriving. These events are concrete, visual, and likely to be captured in a video related to the incident.\n\nEVENTS:\n1. A person setting fire to the office building\n2. Flames engulfing the building\n3. People evacuating the office building in a state of panic\n4. Firefighters arriving at the scene to extinguish the fire\n5. Paramedics treating injured people outside the building",
"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: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a fire at an office building in Daegu, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage to the building, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the office building\n2. People evacuating the building in a state of panic\n3. Emergency responders providing medical aid to injured victims\n4. Flames engulfing parts of the office building\n5. Rescue teams searching for survivors in the damaged building",
"video_URL": "http://twitter.com/i/status/1534851387024359424",
"video_description": "흰 천 덮은 물건 든 방화 용의자…CCTV로 본 화재 순간 (출처 : JTBC) http://naver.me/xtqfdWvA 대구 방화 용의자 현장에서 숨져...\"재판 결과에 \\’앙심\\’” / YTN https://youtu.be/Msh294y6bO8 재개발투자 8억 반환소송 패소…2심 앞두고 범행",
"video_id": "1534851387024359424"
}
| 2
|
[
"The image shows a man standing in front of a group of people, likely emergency responders, under a blue tent. The text on the image mentions a traffic accident in Jeongneung, where a person was caught on CCTV throwing something from a window. The man in the image appears to be speaking or giving a statement.",
"The current frame shows a close-up view of a building's facade with two large holes in the glass, indicating damage or an impact, possibly related to the event described in the previous frame. The reflection of the building and other structures can be seen on the glass surface. The YTN logo is visible in the top right corner, suggesting this footage is from a news broadcast."
] |
1534851387024359424
|
A traffic accident occurred in Jeongneung, where a person was caught on CCTV throwing something from a window, causing damage to a building with two large holes in the glass. Emergency responders are present at the scene, and a man, possibly a witness or individual involved, is giving a statement under a tent. The event is being reported on by news outlet YTN, indicating its significance and public interest.
|
On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.
|
[
"A person setting fire to the office building in Daegu, South Korea on 9 June 2022",
"A person setting fire to the office building during the arson attack in Daegu, South Korea on 9 June 2022",
"Flames engulfing a building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing the building during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating the office building in a state of panic due to a fire in Daegu, South Korea on 9 June 2022",
"People evacuating the office building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Firefighters arriving at the scene of a fire in Daegu, South Korea on 9 June 2022 to extinguish the blaze",
"Firefighters arriving at the scene to extinguish the fire during the arson attack in Daegu, South Korea on June 9, 2022",
"Paramedics treating injured people outside the building after fire in Daegu, South Korea on 9 June 2022",
"Paramedics treating injured people outside the building after arson attack in Daegu, South Korea on June 9, 2022"
] |
[
"Firefighters battling the blaze at the office building in Daegu, South Korea on June 9, 2022",
"Firefighters battling the blaze at the office building in Daegu, South Korea after alleged arson attack on 9 June 2022",
"People evacuating a building in a state of panic due to a fire in Daegu, South Korea on June 9, 2022",
"People evacuating the building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Emergency responders providing medical aid to injured victims of the June 9, 2022 fire in Daegu, South Korea",
"Emergency responders providing medical aid to injured victims of the June 9 2022 arson attack in Daegu, South Korea",
"Flames engulfing parts of the office building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing parts of the office building in Daegu, South Korea during the arson attack on 9 June 2022",
"Rescue teams searching for survivors in the building damaged by the fire in Daegu, South Korea on 9 June 2022",
"Rescue teams searching for survivors in the damaged building after the arson attack in Daegu, South Korea on 9 June 2022"
] |
[
"Flames engulfing the office building in Daegu, South Korea on 9 June 2022 fire incident",
"Flames engulfing the office building in Daegu, South Korea due to arson attack on 9 June 2022",
"Firefighters arriving at the scene and battling the blaze in Daegu, South Korea on 9 June 2022 during a large fire incident",
"Firefighters arriving at the scene and battling the blaze during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating building after fire in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"People evacuating building after arson attack in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"Emergency medical personnel treating injured individuals outside the building after fire in Daegu, South Korea on 9 June 2022",
"Emergency medical personnel treating injured individuals outside the building after the arson attack in Daegu, South Korea on June 9, 2022",
"Damage to the office building in Daegu, South Korea after the fire on 9 June 2022 has been extinguished",
"Damage to the office building in Daegu, South Korea after the arson attack fire was extinguished on 9 June 2022"
] |
{
"article_url": "https://namu.wiki/w/%EB%8C%80%EA%B5%AC%20%EB%B3%80%ED%98%B8%EC%82%AC%20%EC%82%AC%EB%AC%B4%EC%8B%A4%20%EB%B0%A9%ED%99%94%20%EC%82%AC%EA%B1%B4",
"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: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: To extract events from the given query, it makes sense to focus on the concrete and visual aspects of the fire and its aftermath, considering what could be reasonably captured in a video. This includes the fire itself, the response of emergency services, and the impact on the building and its occupants.\n\nEVENTS:\n1. Flames engulfing the office building in Daegu\n2. Firefighters arriving at the scene and battling the blaze\n3. People evacuating the building, some injured and covered in soot\n4. Emergency medical personnel treating injured individuals outside the building\n5. Damage to the office building after the fire has been extinguished",
"en_article_excerpt": "On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.",
"en_article_url": "https://en.wikipedia.org/wiki/Daegu_office_fire",
"event_category": "disasters",
"event_name": "daegu_office_fire",
"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: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the actions and consequences leading up to and resulting from the arson attack, such as the fire breaking out, people evacuating, and emergency responders arriving. These events are concrete, visual, and likely to be captured in a video related to the incident.\n\nEVENTS:\n1. A person setting fire to the office building\n2. Flames engulfing the building\n3. People evacuating the office building in a state of panic\n4. Firefighters arriving at the scene to extinguish the fire\n5. Paramedics treating injured people outside the building",
"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: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a fire at an office building in Daegu, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage to the building, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the office building\n2. People evacuating the building in a state of panic\n3. Emergency responders providing medical aid to injured victims\n4. Flames engulfing parts of the office building\n5. Rescue teams searching for survivors in the damaged building",
"video_URL": "http://youtube.com/watch?v=rzyM4QtZNNU",
"video_description": "오늘(9일) 대구광역시 수성구 범어동 대구지방법원 인근 변호사 사무실 빌딩에서 방화로 추정되는 불이 나 7명이 숨지고 49명이 다쳤습니다. 건물 CCTV를 보면 오전 10시 53분 마스크를 쓰고 빌딩에 들어서는 남성이 확인됩니다. 한 손에는 흰 천으로 덮은 확인되지 않은 물체를 든 상태로, 경찰은 천에 덮인 물체가 인화 물질이었을 것으로 보고 있습니다. 이 남성이 해당 변호사 사무실에 들어간 지 23초 만에 불길이 일어나는 모습이 확인됩니다. ▣ KBS 기사 원문보기 : http://news.kbs.co.kr/news/view.do?ncd=5482165 ▣ 제보 하기 ◇ 카카오톡 : 'KBS제보' 검색 ◇ 전화 : 02-781-1234 ◇ 홈페이지 : https://goo.gl/4bWbkG ◇ 이메일 : kbs1234@kbs.co.kr #대구화재 #방화용의자 #CCTV",
"video_id": "rzyM4QtZNNU"
}
| 2
|
[
"The image shows a surveillance camera view of a stairway and a person, possibly a man, walking towards the stairs. The person appears to be carrying an object, possibly a box or package, with both hands. The scene is indoors, and the setting seems to be a hallway or lobby area. The image has a text overlay in Korean, which reads \"속보 영상\" (Breaking news video) in the top left corner, and there's another text at the bottom that appears to be a timestamp or other related information, but it's not clear enough to read accurately.",
"The current frame displays a graphic with the logo \"KBS NEWS\" on a blue background, suggesting a transition to a news segment or the end of a news report. The Korean text \"구독하기\" (Subscribe) indicates a prompt for viewers to subscribe, likely to the KBS News channel or service. This frame serves as a conclusion to the previous content, directing audience engagement towards subscribing for more updates."
] |
rzyM4QtZNNU
|
A man is seen walking towards a stairway in an indoor hallway or lobby area, carrying a box or package, captured by a surveillance camera. The scene is presented as a breaking news video. The footage is then followed by a news graphic from KBS NEWS, prompting viewers to subscribe, marking the end of the report.
|
On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.
|
[
"A person setting fire to the office building in Daegu, South Korea on 9 June 2022",
"A person setting fire to the office building during the arson attack in Daegu, South Korea on 9 June 2022",
"Flames engulfing a building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing the building during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating the office building in a state of panic due to a fire in Daegu, South Korea on 9 June 2022",
"People evacuating the office building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Firefighters arriving at the scene of a fire in Daegu, South Korea on 9 June 2022 to extinguish the blaze",
"Firefighters arriving at the scene to extinguish the fire during the arson attack in Daegu, South Korea on June 9, 2022",
"Paramedics treating injured people outside the building after fire in Daegu, South Korea on 9 June 2022",
"Paramedics treating injured people outside the building after arson attack in Daegu, South Korea on June 9, 2022"
] |
[
"Firefighters battling the blaze at the office building in Daegu, South Korea on June 9, 2022",
"Firefighters battling the blaze at the office building in Daegu, South Korea after alleged arson attack on 9 June 2022",
"People evacuating a building in a state of panic due to a fire in Daegu, South Korea on June 9, 2022",
"People evacuating the building in a state of panic during the arson attack in Daegu, South Korea on June 9, 2022",
"Emergency responders providing medical aid to injured victims of the June 9, 2022 fire in Daegu, South Korea",
"Emergency responders providing medical aid to injured victims of the June 9 2022 arson attack in Daegu, South Korea",
"Flames engulfing parts of the office building in Daegu, South Korea during the fire on 9 June 2022",
"Flames engulfing parts of the office building in Daegu, South Korea during the arson attack on 9 June 2022",
"Rescue teams searching for survivors in the building damaged by the fire in Daegu, South Korea on 9 June 2022",
"Rescue teams searching for survivors in the damaged building after the arson attack in Daegu, South Korea on 9 June 2022"
] |
[
"Flames engulfing the office building in Daegu, South Korea on 9 June 2022 fire incident",
"Flames engulfing the office building in Daegu, South Korea due to arson attack on 9 June 2022",
"Firefighters arriving at the scene and battling the blaze in Daegu, South Korea on 9 June 2022 during a large fire incident",
"Firefighters arriving at the scene and battling the blaze during the arson attack in Daegu, South Korea on June 9, 2022",
"People evacuating building after fire in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"People evacuating building after arson attack in Daegu, South Korea on June 9, 2022, with some injured and covered in soot",
"Emergency medical personnel treating injured individuals outside the building after fire in Daegu, South Korea on 9 June 2022",
"Emergency medical personnel treating injured individuals outside the building after the arson attack in Daegu, South Korea on June 9, 2022",
"Damage to the office building in Daegu, South Korea after the fire on 9 June 2022 has been extinguished",
"Damage to the office building in Daegu, South Korea after the arson attack fire was extinguished on 9 June 2022"
] |
{
"article_url": "https://namu.wiki/w/%EB%8C%80%EA%B5%AC%20%EB%B3%80%ED%98%B8%EC%82%AC%20%EC%82%AC%EB%AC%B4%EC%8B%A4%20%EB%B0%A9%ED%99%94%20%EC%82%AC%EA%B1%B4",
"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: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: To extract events from the given query, it makes sense to focus on the concrete and visual aspects of the fire and its aftermath, considering what could be reasonably captured in a video. This includes the fire itself, the response of emergency services, and the impact on the building and its occupants.\n\nEVENTS:\n1. Flames engulfing the office building in Daegu\n2. Firefighters arriving at the scene and battling the blaze\n3. People evacuating the building, some injured and covered in soot\n4. Emergency medical personnel treating injured individuals outside the building\n5. Damage to the office building after the fire has been extinguished",
"en_article_excerpt": "On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.",
"en_article_url": "https://en.wikipedia.org/wiki/Daegu_office_fire",
"event_category": "disasters",
"event_name": "daegu_office_fire",
"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: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the query, it makes sense to consider the actions and consequences leading up to and resulting from the arson attack, such as the fire breaking out, people evacuating, and emergency responders arriving. These events are concrete, visual, and likely to be captured in a video related to the incident.\n\nEVENTS:\n1. A person setting fire to the office building\n2. Flames engulfing the building\n3. People evacuating the office building in a state of panic\n4. Firefighters arriving at the scene to extinguish the fire\n5. Paramedics treating injured people outside the building",
"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: On 9 June 2022, a fire caused by a suspected arson attack broke out at an office building in Daegu, South Korea, killing seven people and injuring 49 others.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a fire at an office building in Daegu, South Korea, it makes sense to extract events that are directly related to the fire and its aftermath, such as rescue efforts, damage to the building, and emergency responses. These events are likely to be visualized in a video associated with the query, providing a concrete representation of the incident.\n\nEVENTS:\n1. Firefighters battling the blaze at the office building\n2. People evacuating the building in a state of panic\n3. Emergency responders providing medical aid to injured victims\n4. Flames engulfing parts of the office building\n5. Rescue teams searching for survivors in the damaged building",
"video_URL": "http://youtube.com/watch?v=5xiV1Z2MDX4",
"video_description": "대구 변호사 사무실 빌딩 화재…7명 사망·46명 부상 오늘(9일) 오전 11시쯤 대구시 수성구 범어동 대구지방법원 인근 7층짜리 변호사 사무실 빌딩 2층에서 불이 나 7명이 숨지고 46명이 연기를 마시는 등 부상을 입었습니다. 또 안에 있던 수십 명이 긴급 대피했습니다. 사망자는 남성 5명, 여성 2명인 것으로 알려졌습니다. 당시 119에는 \"2층에서 검은 연기가 보이고 폭발음이 들렸다\"는 신고가 접수됐습니다. 불이 나자 소방차 50대와 소방인력 160명이 동원돼 불을 끄고 입주자들을 구조했습니다. 불은 20여 분만에 진화됐습니다. 경찰은 화재 발생 당시 의뢰인이 불만을 제기한 정황이 있었다는 점 등으로 미뤄 방화 여부를 조사하고 있습니다. #사무실_빌딩_화재 #사망 #연기 #대구_범어동 연합뉴스TV 기사문의 및 제보 : 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": "5xiV1Z2MDX4"
}
| 2
|
[
"The image shows a large building with a damaged section where a section of the glass facade appears to have broken away, exposing the interior. A ladder is positioned against the building, suggesting repair or rescue efforts. The text on the image is in Korean and indicates a serious incident involving a building collapse or accident. The text references 7 fatalities and 46 injuries.",
"The video shows a scene outside a damaged building with a group of people, including one in an orange vest, gathered around. A ladder is still positioned against the building, indicating ongoing rescue or repair efforts. The text on the image, in Korean, highlights the serious incident with 7 fatalities and 46 injuries. A large flag is partially visible in the foreground, and there's a sense of ongoing emergency response and investigation."
] |
5xiV1Z2MDX4
|
A serious incident occurred at a large building, resulting in a partial collapse of its glass facade, with 7 fatalities and 46 injuries reported. Emergency responders, including someone in an orange vest, are on the scene, with a ladder positioned against the building, indicating ongoing rescue or repair efforts. The incident is under investigation, with a sense of emergency response still present, as evidenced by the activities of the people gathered outside the damaged building.
|
Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.
|
[
"Strong winds from typhoon knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Heavy rainfall from typhoons causing flooding in Taiwan, the Philippines, and other affected East Asian countries such as Japan, South Korea, and possibly Russia",
"Typhoon storm surges hitting coastal communities in Russia's eastern regions and other affected areas such as Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to shelters and safe zones in Japan, South Korea, Taiwan, Philippines, and Russia during typhoon events",
"Debris and damage to buildings and infrastructure in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
[
"Strong winds from typhoons knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Flooding in coastal cities and low-lying areas due to typhoons in Japan, South Korea, Taiwan, Philippines, and Russia",
"People evacuating to emergency shelters during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Debris-filled streets and damaged buildings after typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Emergency responders rescuing people from flooded areas during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia"
] |
[
"Typhoon causing strong winds and knocking down trees and power lines in Japan and South Korea",
"Typhoon causing heavy rainfall and flooding in the Philippines and Taiwan",
"Typhoon storm surges hitting coastal communities in Russia and other affected areas like Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to emergency shelters in Japan, South Korea, Taiwan, Philippines, and Russia due to typhoon",
"Debris and damaged buildings in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%ED%9E%8C%EB%82%A8%EB%85%B8",
"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: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Hinnamnor, it makes sense to extract events that are commonly associated with a powerful tropical cyclone, such as strong winds, heavy rainfall, and storm surges, as these events are likely to be visualized in a video. The events extracted should be specific to the regions affected, including Japan, South Korea, Taiwan, the Philippines, and Russia, taking into account the typical consequences of a typhoon in these areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in the Philippines and Taiwan\n3. Storm surges hitting coastal communities in Russia\n4. Residents evacuating to emergency shelters in affected areas\n5. Debris and damaged buildings in the aftermath of the typhoon",
"en_article_excerpt": "Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Hinnamnor",
"event_category": "disasters",
"event_name": "typhoon_hinnamno",
"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: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, as these are likely to be visualized in a video associated with the query. The events should be specific to the affected regions, considering the geographical characteristics and common typhoon impacts in those areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in Taiwan and the Philippines\n3. Storm surges hitting coastal communities in Russia's eastern regions\n4. Residents evacuating to shelters and safe zones in affected areas\n5. Debris and damage to buildings and infrastructure in the aftermath of the typhoon",
"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: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the impact of a powerful typhoon, such as damage to infrastructure, evacuations, and extreme weather conditions, as these are likely to be visualized in a video associated with the query. The events should be specific to the regions affected by the typhoon, including Japan, South Korea, Taiwan, the Philippines, and Russia.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. People evacuating to emergency shelters\n4. Debris-filled streets and damaged buildings\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1566887846916792320",
"video_description": "이게맞나.. #태풍 #힌남노 #포항 #역대급태풍",
"video_id": "1566887846916792320"
}
| 2
|
[
"The image shows a nighttime street scene, possibly in a residential area. It appears to be raining heavily, with the street and surroundings shrouded in mist. A vehicle with its headlights and red taillights is moving on the street. There are a few people standing by a gate, possibly taking shelter from the rain. The area is illuminated by streetlights, and trees line the street.",
"The image depicts a nighttime street scene in a residential area, with heavy rain continuing to obscure visibility. The street is still misty, and a vehicle with its headlights and red taillights is visible, moving through the rain. A few people remain standing by a gate, seeking shelter from the downpour. The scene is illuminated by streetlights, and trees continue to line the street, swaying in the wind due to the strong rainstorm."
] |
1566887846916792320
|
A vehicle drives down a residential street at night during a heavy rainstorm, while a group of people take shelter from the rain by a gate, illuminated by streetlights amidst the misty and windy conditions.
|
Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.
|
[
"Strong winds from typhoon knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Heavy rainfall from typhoons causing flooding in Taiwan, the Philippines, and other affected East Asian countries such as Japan, South Korea, and possibly Russia",
"Typhoon storm surges hitting coastal communities in Russia's eastern regions and other affected areas such as Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to shelters and safe zones in Japan, South Korea, Taiwan, Philippines, and Russia during typhoon events",
"Debris and damage to buildings and infrastructure in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
[
"Strong winds from typhoons knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Flooding in coastal cities and low-lying areas due to typhoons in Japan, South Korea, Taiwan, Philippines, and Russia",
"People evacuating to emergency shelters during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Debris-filled streets and damaged buildings after typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Emergency responders rescuing people from flooded areas during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia"
] |
[
"Typhoon causing strong winds and knocking down trees and power lines in Japan and South Korea",
"Typhoon causing heavy rainfall and flooding in the Philippines and Taiwan",
"Typhoon storm surges hitting coastal communities in Russia and other affected areas like Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to emergency shelters in Japan, South Korea, Taiwan, Philippines, and Russia due to typhoon",
"Debris and damaged buildings in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%ED%9E%8C%EB%82%A8%EB%85%B8",
"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: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Hinnamnor, it makes sense to extract events that are commonly associated with a powerful tropical cyclone, such as strong winds, heavy rainfall, and storm surges, as these events are likely to be visualized in a video. The events extracted should be specific to the regions affected, including Japan, South Korea, Taiwan, the Philippines, and Russia, taking into account the typical consequences of a typhoon in these areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in the Philippines and Taiwan\n3. Storm surges hitting coastal communities in Russia\n4. Residents evacuating to emergency shelters in affected areas\n5. Debris and damaged buildings in the aftermath of the typhoon",
"en_article_excerpt": "Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Hinnamnor",
"event_category": "disasters",
"event_name": "typhoon_hinnamno",
"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: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, as these are likely to be visualized in a video associated with the query. The events should be specific to the affected regions, considering the geographical characteristics and common typhoon impacts in those areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in Taiwan and the Philippines\n3. Storm surges hitting coastal communities in Russia's eastern regions\n4. Residents evacuating to shelters and safe zones in affected areas\n5. Debris and damage to buildings and infrastructure in the aftermath of the typhoon",
"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: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the impact of a powerful typhoon, such as damage to infrastructure, evacuations, and extreme weather conditions, as these are likely to be visualized in a video associated with the query. The events should be specific to the regions affected by the typhoon, including Japan, South Korea, Taiwan, the Philippines, and Russia.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. People evacuating to emergency shelters\n4. Debris-filled streets and damaged buildings\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1566774984525025281",
"video_description": "다들... 이번 태풍 힌남노 조심하세요... 현재 제주... 저희 집 나무가 90도로 순간적으로 휘어진 거 처음 봐요 바람 장난아니고 비도 장난아니니까 집에... 콕... 박혀있기",
"video_id": "1566774984525025281"
}
| 2
|
[
"The image is very dark, and details are not clearly visible. It appears to show silhouettes of trees against a night sky with power lines running horizontally across the top. There are no discernible actions, participants, or contextual elements evident due to the low visibility.",
"The image continues to be very dark, maintaining low visibility. It still depicts silhouettes of trees against the night sky, with power lines running horizontally across the top. There are no discernible actions, participants, or additional contextual elements evident, continuing the sense of stillness from the previous frame."
] |
1566774984525025281
|
The video appears to depict a nighttime scene with silhouettes of trees against the night sky and power lines visible at the top. The scene is very dark, with low visibility, and there are no discernible actions or participants evident throughout the observed frames, suggesting a static and serene environment with no notable events or activities occurring.
|
Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.
|
[
"Strong winds from typhoon knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Heavy rainfall from typhoons causing flooding in Taiwan, the Philippines, and other affected East Asian countries such as Japan, South Korea, and possibly Russia",
"Typhoon storm surges hitting coastal communities in Russia's eastern regions and other affected areas such as Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to shelters and safe zones in Japan, South Korea, Taiwan, Philippines, and Russia during typhoon events",
"Debris and damage to buildings and infrastructure in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
[
"Strong winds from typhoons knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Flooding in coastal cities and low-lying areas due to typhoons in Japan, South Korea, Taiwan, Philippines, and Russia",
"People evacuating to emergency shelters during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Debris-filled streets and damaged buildings after typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Emergency responders rescuing people from flooded areas during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia"
] |
[
"Typhoon causing strong winds and knocking down trees and power lines in Japan and South Korea",
"Typhoon causing heavy rainfall and flooding in the Philippines and Taiwan",
"Typhoon storm surges hitting coastal communities in Russia and other affected areas like Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to emergency shelters in Japan, South Korea, Taiwan, Philippines, and Russia due to typhoon",
"Debris and damaged buildings in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%ED%9E%8C%EB%82%A8%EB%85%B8",
"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: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Hinnamnor, it makes sense to extract events that are commonly associated with a powerful tropical cyclone, such as strong winds, heavy rainfall, and storm surges, as these events are likely to be visualized in a video. The events extracted should be specific to the regions affected, including Japan, South Korea, Taiwan, the Philippines, and Russia, taking into account the typical consequences of a typhoon in these areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in the Philippines and Taiwan\n3. Storm surges hitting coastal communities in Russia\n4. Residents evacuating to emergency shelters in affected areas\n5. Debris and damaged buildings in the aftermath of the typhoon",
"en_article_excerpt": "Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Hinnamnor",
"event_category": "disasters",
"event_name": "typhoon_hinnamno",
"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: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, as these are likely to be visualized in a video associated with the query. The events should be specific to the affected regions, considering the geographical characteristics and common typhoon impacts in those areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in Taiwan and the Philippines\n3. Storm surges hitting coastal communities in Russia's eastern regions\n4. Residents evacuating to shelters and safe zones in affected areas\n5. Debris and damage to buildings and infrastructure in the aftermath of the typhoon",
"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: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the impact of a powerful typhoon, such as damage to infrastructure, evacuations, and extreme weather conditions, as these are likely to be visualized in a video associated with the query. The events should be specific to the regions affected by the typhoon, including Japan, South Korea, Taiwan, the Philippines, and Russia.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. People evacuating to emergency shelters\n4. Debris-filled streets and damaged buildings\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1567139282846089217",
"video_description": "제11호 태풍 힌남노로 인한 자연재해 피해가 속출했는데요. 포항 아파트 지하주차장 침수로 인한 대규모 실종자가 발생을 했습니다. 포항 우방신세계아파트라는 곳에서 침수로 인해 실종자가 발생했고 9월 6일 20시 40분경 실종자1명(39세 남성)을 구조했고, 21시 50분 실종자1명(여성) 구조.",
"video_id": "1567139282846089217"
}
| 2
|
[
"The current frame depicts a group of people in a flooded area. The water appears to be rising, and the individuals are wading through it. Some people are carrying belongings or assisting others, likely trying to navigate through the floodwaters. The setting seems to be an urban area, possibly a street or a basement, with the flood causing significant disruption.",
"In the current frame, the group of people continues to navigate through the flooded area. The water level remains high, and individuals are seen wading carefully. One person is carrying an object, likely a personal belonging or a rescue item. The environment appears to be an urban setting, possibly a street or a basement, where the floodwaters have caused considerable disruption. The people are focused on moving through the water, possibly seeking higher ground or safety."
] |
1567139282846089217
|
A group of people are navigating through a flooded urban area, likely a street or basement, where rising water levels have caused significant disruption. The individuals are wading through the water, carrying belongings and assisting each other in an effort to move to safety or higher ground, amidst the challenging and potentially dangerous flood conditions.
|
Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.
|
[
"Strong winds from typhoon knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Heavy rainfall from typhoons causing flooding in Taiwan, the Philippines, and other affected East Asian countries such as Japan, South Korea, and possibly Russia",
"Typhoon storm surges hitting coastal communities in Russia's eastern regions and other affected areas such as Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to shelters and safe zones in Japan, South Korea, Taiwan, Philippines, and Russia during typhoon events",
"Debris and damage to buildings and infrastructure in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
[
"Strong winds from typhoons knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Flooding in coastal cities and low-lying areas due to typhoons in Japan, South Korea, Taiwan, Philippines, and Russia",
"People evacuating to emergency shelters during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Debris-filled streets and damaged buildings after typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Emergency responders rescuing people from flooded areas during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia"
] |
[
"Typhoon causing strong winds and knocking down trees and power lines in Japan and South Korea",
"Typhoon causing heavy rainfall and flooding in the Philippines and Taiwan",
"Typhoon storm surges hitting coastal communities in Russia and other affected areas like Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to emergency shelters in Japan, South Korea, Taiwan, Philippines, and Russia due to typhoon",
"Debris and damaged buildings in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%ED%9E%8C%EB%82%A8%EB%85%B8",
"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: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Hinnamnor, it makes sense to extract events that are commonly associated with a powerful tropical cyclone, such as strong winds, heavy rainfall, and storm surges, as these events are likely to be visualized in a video. The events extracted should be specific to the regions affected, including Japan, South Korea, Taiwan, the Philippines, and Russia, taking into account the typical consequences of a typhoon in these areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in the Philippines and Taiwan\n3. Storm surges hitting coastal communities in Russia\n4. Residents evacuating to emergency shelters in affected areas\n5. Debris and damaged buildings in the aftermath of the typhoon",
"en_article_excerpt": "Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Hinnamnor",
"event_category": "disasters",
"event_name": "typhoon_hinnamno",
"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: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, as these are likely to be visualized in a video associated with the query. The events should be specific to the affected regions, considering the geographical characteristics and common typhoon impacts in those areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in Taiwan and the Philippines\n3. Storm surges hitting coastal communities in Russia's eastern regions\n4. Residents evacuating to shelters and safe zones in affected areas\n5. Debris and damage to buildings and infrastructure in the aftermath of the typhoon",
"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: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the impact of a powerful typhoon, such as damage to infrastructure, evacuations, and extreme weather conditions, as these are likely to be visualized in a video associated with the query. The events should be specific to the regions affected by the typhoon, including Japan, South Korea, Taiwan, the Philippines, and Russia.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. People evacuating to emergency shelters\n4. Debris-filled streets and damaged buildings\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1566015450982494209",
"video_description": "얘들아… 초속 54미터 이상이면 건물도 붕괴될 정도의 바람이라는데 이번 힌남노는 매미보다 중심 기압이 낮은 더 강력한 태풍이라 제주/남부해안지역엔 초속 60미터까지도 예상된대.. 영동 쪽은 초속 3~40미터 수도권은 초속 15미터 예상… 다들 진짜 조심하자 대비할 수 있는 부분은 꼭 하고ㅜ",
"video_id": "1566015450982494209"
}
| 2
|
[
"A weather presenter and a news anchor are on a television screen, discussing a weather map that shows wind speeds across a region, with a focus on a severe weather event from 2003. The map uses colors to indicate wind speed categories, ranging from 15 m/s to over 50 m/s. The weather presenter is providing details about the wind speed variation, while the news anchor gestures to emphasize points.",
"The weather presenter and news anchor continue their discussion, now focusing on a nighttime urban scene illuminated by streetlights. They discuss a severe weather event from 2003, as indicated by the text overlay mentioning '2003년 태풍 '매미'로 폭풍해일 발생...인명 피해 발생' (In 2003, Typhoon Maemi caused a storm surge... leading to loss of life). The presenter provides details about the event, while the news anchor continues to engage with the audience, likely explaining the impact of the storm surge."
] |
1566015450982494209
|
A news segment featuring a weather presenter and a news anchor discussing a severe weather event from 2003, specifically Typhoon Maemi, which caused a storm surge and resulted in loss of life. The presenters analyze wind speed maps and show footage of a nighttime urban scene, explaining the details of the event and its impact, with the news anchor emphasizing key points to the audience.
|
Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.
|
[
"Strong winds from typhoon knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Heavy rainfall from typhoons causing flooding in Taiwan, the Philippines, and other affected East Asian countries such as Japan, South Korea, and possibly Russia",
"Typhoon storm surges hitting coastal communities in Russia's eastern regions and other affected areas such as Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to shelters and safe zones in Japan, South Korea, Taiwan, Philippines, and Russia during typhoon events",
"Debris and damage to buildings and infrastructure in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
[
"Strong winds from typhoons knocking down trees and power lines in Japan, South Korea, Taiwan, Philippines, and Russia",
"Flooding in coastal cities and low-lying areas due to typhoons in Japan, South Korea, Taiwan, Philippines, and Russia",
"People evacuating to emergency shelters during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Debris-filled streets and damaged buildings after typhoon in Japan, South Korea, Taiwan, Philippines, and Russia",
"Emergency responders rescuing people from flooded areas during typhoon in Japan, South Korea, Taiwan, Philippines, and Russia"
] |
[
"Typhoon causing strong winds and knocking down trees and power lines in Japan and South Korea",
"Typhoon causing heavy rainfall and flooding in the Philippines and Taiwan",
"Typhoon storm surges hitting coastal communities in Russia and other affected areas like Japan, South Korea, Taiwan, and the Philippines",
"Residents evacuating to emergency shelters in Japan, South Korea, Taiwan, Philippines, and Russia due to typhoon",
"Debris and damaged buildings in Japan, South Korea, Taiwan, Philippines, and Russia in the aftermath of the typhoon"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%ED%9E%8C%EB%82%A8%EB%85%B8",
"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: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Hinnamnor, it makes sense to extract events that are commonly associated with a powerful tropical cyclone, such as strong winds, heavy rainfall, and storm surges, as these events are likely to be visualized in a video. The events extracted should be specific to the regions affected, including Japan, South Korea, Taiwan, the Philippines, and Russia, taking into account the typical consequences of a typhoon in these areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in the Philippines and Taiwan\n3. Storm surges hitting coastal communities in Russia\n4. Residents evacuating to emergency shelters in affected areas\n5. Debris and damaged buildings in the aftermath of the typhoon",
"en_article_excerpt": "Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Hinnamnor",
"event_category": "disasters",
"event_name": "typhoon_hinnamno",
"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: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typical of a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, as these are likely to be visualized in a video associated with the query. The events should be specific to the affected regions, considering the geographical characteristics and common typhoon impacts in those areas.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines in Japan and South Korea\n2. Heavy rainfall causing flooding in Taiwan and the Philippines\n3. Storm surges hitting coastal communities in Russia's eastern regions\n4. Residents evacuating to shelters and safe zones in affected areas\n5. Debris and damage to buildings and infrastructure in the aftermath of the typhoon",
"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: Typhoon Hinnamnor, known in the Philippines as Super Typhoon Henry, was a very large and powerful tropical cyclone that impacted Japan, South Korea, Taiwan, the Philippines, and Russia.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events related to the impact of a powerful typhoon, such as damage to infrastructure, evacuations, and extreme weather conditions, as these are likely to be visualized in a video associated with the query. The events should be specific to the regions affected by the typhoon, including Japan, South Korea, Taiwan, the Philippines, and Russia.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal cities and low-lying areas\n3. People evacuating to emergency shelters\n4. Debris-filled streets and damaged buildings\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1566948535899041792",
"video_description": "칭구가 보내준 집앞 영상 괜찮아??? 응 근데 나도 안괜찮아 다들 괜찮으시길 #태풍_힌남노_저리가",
"video_id": "1566948535899041792"
}
| 2
|
[
"The image depicts a large landslide with a significant amount of earth and debris that has been displaced, creating a wide, deep gash in the hillside. The landslide is situated near a modern building with a flat roof, and there are trees and vegetation on either side of the slope. In the background, there are multiple high-rise buildings indicating an urban environment. A car is parked close to the landslide, suggesting the area is still accessible. The overcast sky implies recent or ongoing inclement weather, possibly contributing to the landslide.",
"The current frame continues to show the aftermath of the landslide with the displaced earth and debris still prominent, emphasizing the extent of the damage. The modern building with a flat roof remains in the foreground, and the vegetation on either side of the slope appears slightly disturbed but still in place. The high-rise buildings in the background are still visible, reinforcing the urban setting. The car is still parked near the landslide, indicating no immediate evacuation or change in access. The overcast sky persists, suggesting that the weather conditions that likely caused the landslide are still present."
] |
1566948535899041792
|
A landslide occurred in an urban area, near a modern building and high-rise structures, causing significant displacement of earth and debris on a hillside. The incident appears to have been influenced by inclement weather, as indicated by the overcast sky. The area remains accessible, with a car parked nearby, suggesting that the landslide has not immediately prompted evacuation or restricted access. The urban setting and the presence of nearby buildings and vegetation provide context to the scale and potential impact of the landslide.
|
Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges causing coastal erosion and damage during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to safer areas or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Debris and destroyed buildings scattered in the aftermath of the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Buildings and houses destroyed by strong winds from Typhoon in Philippines, China, and Korea in 2019",
"Flooding in coastal areas and low-lying regions during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to higher ground or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Trees and power lines uprooted or knocked down during Typhoon in Philippines, China, and Korea in 2019",
"Rescue teams providing aid to affected communities during the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Strong winds from Typhoon knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges caused by typhoons in the Philippines, China, and Korea in 2019 resulting in coastal erosion and damage",
"People evacuating to safer areas during Typhoon in the Philippines, China, and Korea in 2019",
"Debris and wreckage scattered on roads and buildings after Typhoon in Philippines, China, and Korea in 2019"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%A7%81%EB%A7%81_(2019%EB%85%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: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are commonly associated with a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to have occurred in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas\n5. Debris and wreckage scattered on roads and buildings",
"en_article_excerpt": "Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Lingling_(2019)",
"event_category": "disasters",
"event_name": "typhoon_lingling",
"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: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to occur in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas or shelters\n5. Debris and destroyed buildings scattered in the typhoon's aftermath",
"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: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typically associated with the aftermath or impact of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Lingling. The events extracted should be specific to the regions affected by the typhoon, including the Philippines, China, and Korea.\n\nEVENTS:\n1. Buildings and houses destroyed by strong winds\n2. Flooding in coastal areas and low-lying regions\n3. People evacuating to higher ground or shelters\n4. Trees and power lines uprooted or knocked down\n5. Rescue teams providing aid to affected communities",
"video_URL": "http://youtube.com/watch?v=QJY4XlSNVf8",
"video_description": "#태풍 #링링 #제13호 #13호 #중국 (서울=연합뉴스) 제13호 태풍 '링링'이 세력을 키우며 한반도를 향해 북상하고 있습니다. 5일 기상청에 따르면 '링링'은 이날 오전 9시 현재 일본 오키나와 남서쪽 약 370㎞ 해상에서 시속 19㎞로 북상 중입니다. 발생 초기 강도가 '약'이던 '링링'은 수온이 높은 해역을 지나며 이날 현재 '강'으로 세력이 강해진 상태입니다. 한국과 미국, 일본 기상청 모두 '링링'이 토요일인 7일 수도권을 강타할 것으로 예보해 철저한 대비가 필요합니다. 중국 저장성과 하이난성에서는 지난 2일 이후 '링링'과 제14호 태풍 '가지키'의 영향으로 폭우 피해가 잇따랐는데요. 영상으로 보시죠. ◆ 연합뉴스 홈페이지→ http://www.yna.co.kr/ ◆ 이 시각 많이 본 기사 → https://goo.gl/VQTsSZ ◆ 오늘의 핫뉴스 → https://goo.gl/WyGXpG ◆ 현장영상 → https://goo.gl/5aZcx8 ◆ 카드뉴스 →https://goo.gl/QKfDTH ◆연합뉴스 공식 SNS◆ ◇페이스북→ https://www.facebook.com/yonhap/ ▣ 연합뉴스 유튜브 채널 구독 : https://goo.gl/pL7TmT ▣ 연합뉴스 인스타 : https://goo.gl/UbqiQb",
"video_id": "QJY4XlSNVf8"
}
| 2
|
[
"The current frame shows a river with rapidly flowing water and a noticeable spray, indicating a strong current. The surrounding area is green and covered with trees. Korean text is visible, mentioning the rapid movement of water.",
"The current frame shows a river with water flowing vigorously, creating a significant spray and mist. The surrounding area remains green with dense trees. The Korean text mentions the rapid movement of water, emphasizing the strong current."
] |
QJY4XlSNVf8
|
A river with a strong current is depicted, surrounded by a lush, green, and densely treed area. The water flows rapidly, creating a significant spray and mist, emphasizing the powerful movement of the river.
|
Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges causing coastal erosion and damage during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to safer areas or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Debris and destroyed buildings scattered in the aftermath of the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Buildings and houses destroyed by strong winds from Typhoon in Philippines, China, and Korea in 2019",
"Flooding in coastal areas and low-lying regions during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to higher ground or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Trees and power lines uprooted or knocked down during Typhoon in Philippines, China, and Korea in 2019",
"Rescue teams providing aid to affected communities during the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Strong winds from Typhoon knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges caused by typhoons in the Philippines, China, and Korea in 2019 resulting in coastal erosion and damage",
"People evacuating to safer areas during Typhoon in the Philippines, China, and Korea in 2019",
"Debris and wreckage scattered on roads and buildings after Typhoon in Philippines, China, and Korea in 2019"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%A7%81%EB%A7%81_(2019%EB%85%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: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are commonly associated with a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to have occurred in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas\n5. Debris and wreckage scattered on roads and buildings",
"en_article_excerpt": "Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Lingling_(2019)",
"event_category": "disasters",
"event_name": "typhoon_lingling",
"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: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to occur in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas or shelters\n5. Debris and destroyed buildings scattered in the typhoon's aftermath",
"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: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typically associated with the aftermath or impact of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Lingling. The events extracted should be specific to the regions affected by the typhoon, including the Philippines, China, and Korea.\n\nEVENTS:\n1. Buildings and houses destroyed by strong winds\n2. Flooding in coastal areas and low-lying regions\n3. People evacuating to higher ground or shelters\n4. Trees and power lines uprooted or knocked down\n5. Rescue teams providing aid to affected communities",
"video_URL": "http://youtube.com/watch?v=ZFR-SBQwtTw",
"video_description": "태풍 '링링' 발생…주후반 한반도 영향 가능성 오늘 오전 9시쯤 필리핀 동쪽 해상에서 13호 태풍 '링링'이 발생했습니다. 강풍반경 200km의 소형 태풍인 '링링'은 계속 북상해서 수요일쯤 타이완 동쪽 해상에 접근하겠습니다. 태풍 '링링'은 금요일 오전쯤 제주도 서귀포 남서쪽 390km 해상까지 진출하겠고 이후 서해상을 향할 것으로 보입니다. 기상청은 태풍 발생 초기라 경로가 유동적이지만 주 후반부터 한반도 부근으로 북상할 가능성이 크다고 내다봤습니다. 연합뉴스TV 기사문의 및 제보 : 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": "ZFR-SBQwtTw"
}
| 2
|
[
"The image depicts a scene on a road during a storm. Two individuals are sitting on the back of a truck with the words \"CITY ENGINEERS OFFICE\" on the side, and another truck is visible in the background. The scene appears to be under heavy rainfall, as evidenced by the wet road and the rain-covered surroundings. There are trees along the side of the road, and the visibility is reduced due to the weather conditions. The text on the screen mentions \"태풍 '링링' 발생...주후반 한반도도 영향 가능성이,\" which translates to \"Typhoon 'Ringling' occurs...Impact possible on the Korean Peninsula later in the week.\"",
"The scene continues on the road during the storm with the same two individuals sitting on the back of the \"CITY ENGINEERS OFFICE\" truck. The background still shows another truck and the rain-covered surroundings, with reduced visibility due to heavy rainfall. Trees line the road, and the text remains unchanged, indicating ongoing news coverage of Typhoon 'Ringling' and its potential impact on the Korean Peninsula."
] |
ZFR-SBQwtTw
|
A video shows a scene of two individuals sitting on the back of a truck belonging to the "CITY ENGINEERS OFFICE" on a road during a storm, with another truck visible in the background. The scene is set amidst heavy rainfall, with reduced visibility and trees lining the road. The context suggests that the video is related to news coverage of Typhoon 'Ringling' and its potential impact on the Korean Peninsula later in the week.
|
Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges causing coastal erosion and damage during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to safer areas or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Debris and destroyed buildings scattered in the aftermath of the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Buildings and houses destroyed by strong winds from Typhoon in Philippines, China, and Korea in 2019",
"Flooding in coastal areas and low-lying regions during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to higher ground or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Trees and power lines uprooted or knocked down during Typhoon in Philippines, China, and Korea in 2019",
"Rescue teams providing aid to affected communities during the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Strong winds from Typhoon knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges caused by typhoons in the Philippines, China, and Korea in 2019 resulting in coastal erosion and damage",
"People evacuating to safer areas during Typhoon in the Philippines, China, and Korea in 2019",
"Debris and wreckage scattered on roads and buildings after Typhoon in Philippines, China, and Korea in 2019"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%A7%81%EB%A7%81_(2019%EB%85%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: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are commonly associated with a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to have occurred in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas\n5. Debris and wreckage scattered on roads and buildings",
"en_article_excerpt": "Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Lingling_(2019)",
"event_category": "disasters",
"event_name": "typhoon_lingling",
"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: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to occur in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas or shelters\n5. Debris and destroyed buildings scattered in the typhoon's aftermath",
"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: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typically associated with the aftermath or impact of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Lingling. The events extracted should be specific to the regions affected by the typhoon, including the Philippines, China, and Korea.\n\nEVENTS:\n1. Buildings and houses destroyed by strong winds\n2. Flooding in coastal areas and low-lying regions\n3. People evacuating to higher ground or shelters\n4. Trees and power lines uprooted or knocked down\n5. Rescue teams providing aid to affected communities",
"video_URL": "http://youtube.com/watch?v=8-DXe4qYo2E",
"video_description": "#태풍 #링링 (서울=연합뉴스) 제13호 태풍 '링링'이 필리핀 동부에서 발생했습니다. 이 태풍의 중심기압은 1천hPa(헥토파스칼), 중심 부근 최대 풍속은 초속 18ｍ(시속 65㎞)이며, 강풍 반경은 200㎞입니다. 한반도에 접근할 무렵 지금보다 크고 강해질 것으로 전망돼 대비가 필요한데요. 자세한 내용은 영상으로 보시죠. ◆ 연합뉴스 홈페이지→ http://www.yna.co.kr/ ◆ 이 시각 많이 본 기사 → https://goo.gl/VQTsSZ ◆ 오늘의 핫뉴스 → https://goo.gl/WyGXpG ◆ 현장영상 → https://goo.gl/5aZcx8 ◆ 카드뉴스 →https://goo.gl/QKfDTH ◆연합뉴스 공식 SNS◆ ◇페이스북→ https://www.facebook.com/yonhap/ ▣ 연합뉴스 유튜브 채널 구독 : https://goo.gl/pL7TmT ▣ 연합뉴스 인스타 : https://goo.gl/UbqiQb",
"video_id": "8-DXe4qYo2E"
}
| 2
|
[
"The image shows a scene of strong waves crashing against a concrete barrier on a coastal road. There is heavy rain, making the visibility low. Korean text in the image provides information about a typhoon that is located approximately 390 km from the southeastern coast of Jeju Island as of 9 AM on the 6th.",
"The image continues to depict the impact of a typhoon, showing strong waves crashing against a concrete barrier on a coastal road. The heavy rain persists, further reducing visibility. The Korean text reinforces the information that the typhoon is located approximately 390 km from the southeastern coast of Jeju Island as of 9 AM on the 6th."
] |
8-DXe4qYo2E
|
A typhoon is impacting the southeastern coast of Jeju Island, causing strong waves to crash against a coastal road's concrete barrier amidst heavy rain that significantly reduces visibility, as reported at 9 AM on the 6th, with the typhoon located approximately 390 km away.
|
Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges causing coastal erosion and damage during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to safer areas or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Debris and destroyed buildings scattered in the aftermath of the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Buildings and houses destroyed by strong winds from Typhoon in Philippines, China, and Korea in 2019",
"Flooding in coastal areas and low-lying regions during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to higher ground or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Trees and power lines uprooted or knocked down during Typhoon in Philippines, China, and Korea in 2019",
"Rescue teams providing aid to affected communities during the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Strong winds from Typhoon knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges caused by typhoons in the Philippines, China, and Korea in 2019 resulting in coastal erosion and damage",
"People evacuating to safer areas during Typhoon in the Philippines, China, and Korea in 2019",
"Debris and wreckage scattered on roads and buildings after Typhoon in Philippines, China, and Korea in 2019"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%A7%81%EB%A7%81_(2019%EB%85%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: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are commonly associated with a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to have occurred in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas\n5. Debris and wreckage scattered on roads and buildings",
"en_article_excerpt": "Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Lingling_(2019)",
"event_category": "disasters",
"event_name": "typhoon_lingling",
"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: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to occur in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas or shelters\n5. Debris and destroyed buildings scattered in the typhoon's aftermath",
"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: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typically associated with the aftermath or impact of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Lingling. The events extracted should be specific to the regions affected by the typhoon, including the Philippines, China, and Korea.\n\nEVENTS:\n1. Buildings and houses destroyed by strong winds\n2. Flooding in coastal areas and low-lying regions\n3. People evacuating to higher ground or shelters\n4. Trees and power lines uprooted or knocked down\n5. Rescue teams providing aid to affected communities",
"video_URL": "http://youtube.com/watch?v=taOktWIvk20",
"video_description": "#태풍 #링링 #서울태풍 #수도권태풍 #최근접 #초강력태풍 (서울=연합뉴스) 한반도를 강타할 초강력 제13호 태풍 '링링'이 왔습니다. 기상청에 따르면 태풍은 7일 새벽 서귀포 서쪽 약 150㎞ 해상을 통과, 오전 6시께 전남 목포 서쪽 약 140㎞ 해상을 지났습니다. 정오께 서울 서남서쪽 약 140㎞ 해상을 지날 것으로 보이는데요. 오후 2시께 태풍 중심이 서울에 제일 가까울 전망입니다. 영상으로 보시겠습니다. [영상 : 연합뉴스TV] ◆ 연합뉴스 홈페이지→ http://www.yna.co.kr/ ◆ 이 시각 많이 본 기사 → https://goo.gl/VQTsSZ ◆ 오늘의 핫뉴스 → https://goo.gl/WyGXpG ◆ 현장영상 → https://goo.gl/5aZcx8 ◆ 카드뉴스 →https://goo.gl/QKfDTH ◆연합뉴스 공식 SNS◆ ◇페이스북→ https://www.facebook.com/yonhap/ ▣ 연합뉴스 유튜브 채널 구독 : https://goo.gl/pL7TmT ▣ 연합뉴스 인스타 : https://goo.gl/UbqiQb",
"video_id": "taOktWIvk20"
}
| 2
|
[
"The image shows a harbor scene with several boats docked. There are bright lights illuminating the area, likely from dockside structures or boats. The text at the bottom of the image, written in Korean, mentions a distance of approximately 140 km. The text at the top right corner says '연합뉴스' which is the logo for Yonhap News Agency, suggesting that this is a news-related image.",
"The current frame displays a blue background with diagonal lines and the Yonhap News Agency logo in white, featuring both Korean and English text."
] |
taOktWIvk20
|
A news video by Yonhap News Agency depicting a harbor scene with docked boats, followed by a title or intro screen with the news agency's logo, suggesting the start of a news report, possibly related to an event or location approximately 140 km away from the harbor.
|
Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.
|
[
"Strong winds from typhoons knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges causing coastal erosion and damage during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to safer areas or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Debris and destroyed buildings scattered in the aftermath of the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Buildings and houses destroyed by strong winds from Typhoon in Philippines, China, and Korea in 2019",
"Flooding in coastal areas and low-lying regions during Typhoon in the Philippines, China, and Korea in 2019",
"People evacuating to higher ground or shelters during the 2019 typhoon in the Philippines, China, and Korea",
"Trees and power lines uprooted or knocked down during Typhoon in Philippines, China, and Korea in 2019",
"Rescue teams providing aid to affected communities during the 2019 typhoon in the Philippines, China, and Korea"
] |
[
"Strong winds from Typhoon knocking down trees and power lines in the Philippines, China, and Korea in 2019",
"Heavy rainfall and flooding from Typhoon in Philippines, China, and Korea in 2019",
"Storm surges caused by typhoons in the Philippines, China, and Korea in 2019 resulting in coastal erosion and damage",
"People evacuating to safer areas during Typhoon in the Philippines, China, and Korea in 2019",
"Debris and wreckage scattered on roads and buildings after Typhoon in Philippines, China, and Korea in 2019"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EB%A7%81%EB%A7%81_(2019%EB%85%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: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are commonly associated with a powerful typhoon, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to have occurred in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas\n5. Debris and wreckage scattered on roads and buildings",
"en_article_excerpt": "Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Lingling_(2019)",
"event_category": "disasters",
"event_name": "typhoon_lingling",
"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: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about Typhoon Lingling, it makes sense to extract events that are typical of a powerful typhoon's impact, such as strong winds, heavy rainfall, and storm surges, which could be visualized in a video. These events are likely to occur in the affected countries, including the Philippines, China, and Korea, and can be reasonably captioned in a video frame.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Storm surges causing coastal erosion and damage\n4. People evacuating to safer areas or shelters\n5. Debris and destroyed buildings scattered in the typhoon's aftermath",
"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: Typhoon Lingling, also known in the Philippines as Typhoon Liwayway, was a powerful typhoon that hit the Philippines, China, and Korea in 2019.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are typically associated with the aftermath or impact of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Lingling. The events extracted should be specific to the regions affected by the typhoon, including the Philippines, China, and Korea.\n\nEVENTS:\n1. Buildings and houses destroyed by strong winds\n2. Flooding in coastal areas and low-lying regions\n3. People evacuating to higher ground or shelters\n4. Trees and power lines uprooted or knocked down\n5. Rescue teams providing aid to affected communities",
"video_URL": "http://youtube.com/watch?v=t1uezBvD9U8",
"video_description": "태풍 '링링'이 서해안을 따라 빠르게 북상하면서 충북 지역 피해도 속출하고 있습니다. 충북 지역 피해 현장을 카메라에 담았습니다.",
"video_id": "t1uezBvD9U8"
}
| 2
|
[
"The image shows a partially torn gray wall next to a yellow metal shutter, possibly indicating some form of damage or vandalism. There is a sign in Korean on the right side, and a barrier tape in front of the wall. Yellow plastic components are scattered on the ground, and some wires are visible.",
"The scene continues to focus on the same area, showing the gray wall with a significant tear, exposing the inner structure. The yellow metal shutter remains partially visible. The Korean sign and barrier tape are still present, indicating the area remains restricted or under investigation. The yellow plastic components and wires scattered on the ground suggest that the damage or vandalism is still being examined."
] |
t1uezBvD9U8
|
A video depicting a scene of damage or vandalism, showing a partially torn gray wall next to a yellow metal shutter, with a Korean sign and barrier tape indicating a restricted area. The wall's inner structure is exposed, and scattered yellow plastic components and wires suggest an ongoing investigation into the incident.
|
Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.
|
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding in urban areas of the Korean Peninsula during Typhoon Soulik in 2012",
"Heavy rainfall causing flooding in urban areas of the Korean Peninsula during Typhoon Khanun in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Soulik in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Khanun in 2012"
] |
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities caused by Typhoon Soulik on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities due to Typhoon Khanun on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Soulik hit the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Khanun hit the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
[
"Strong winds from Typhoon Soulik blowing down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun blowing down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Soulik on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Khanun in the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Soulik on the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Khanun on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Soulik on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Khanun in the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EC%86%94%EB%A6%AD_(2018%EB%85%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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Soulik, it makes sense to extract events that are commonly associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and damage to infrastructure. These events are likely to be visualized in a video and are consistent with the characteristics of a powerful typhoon like Soulik.\n\nEVENTS:\n1. Strong winds blowing down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Debris flying through the air\n4. Roofs being torn off buildings\n5. Emergency responders evacuating people from flooded areas",
"en_article_excerpt": "Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Soulik_(2018)",
"event_category": "disasters",
"event_name": "typhoon_soulik",
"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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to Typhoon Soulik, it makes sense to consider the typical consequences and scenes associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and resulting damage. Given the typhoon's impact on the Korean Peninsula, events related to severe weather, destruction, and potential evacuation or rescue efforts are likely to be relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Residents evacuating their homes and seeking shelter\n4. Emergency responders rescuing people from flooded areas\n5. Debris and damaged buildings scattered across the affected regions",
"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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact and aftermath of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Soulik. Given the severity of the typhoon, events that depict its powerful effects on the Korean Peninsula are most relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal areas and cities\n3. People evacuating their homes and seeking shelter\n4. Debris and destroyed buildings scattered across streets\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1032900418777407489",
"video_description": "제주도 태풍 솔릭의 강풍의 무서움.. 오토바이도 날려버리는 태풍 솔릭.. ㄷㄷㄷ",
"video_id": "1032900418777407489"
}
| 2
|
[
"The frame depicts the interior of a vehicle, showing the windshield and dashboard. Outside the windshield, there is heavy rain, reducing visibility. The windshield wipers are active, attempting to clear the rain from the windshield. A person is visible outside, standing in the rain on the street, partially obscured by the wipers' motion. The scene suggests a rainy day, and the person outside appears to be waiting or walking in the rain.",
"The scene continues inside the vehicle, with the focus still on the windshield and dashboard. The heavy rain persists, maintaining low visibility. The windshield wipers are still actively clearing the rain, though they move more slowly than before. The person outside is less visible now, likely due to their movement or the wipers’ reduced speed. The rainy conditions prevail, suggesting the person outside is still navigating the wet street."
] |
1032900418777407489
|
A person is driving a vehicle on a heavily rainy day. The low visibility due to the rain is partially alleviated by the active windshield wipers. Meanwhile, another individual is outside, walking or waiting on the street, attempting to navigate through the rain. The scene captures a moment of everyday life during adverse weather conditions, focusing on the interaction between the driver's viewpoint and the pedestrian's actions outside the vehicle.
|
Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.
|
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding in urban areas of the Korean Peninsula during Typhoon Soulik in 2012",
"Heavy rainfall causing flooding in urban areas of the Korean Peninsula during Typhoon Khanun in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Soulik in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Khanun in 2012"
] |
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities caused by Typhoon Soulik on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities due to Typhoon Khanun on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Soulik hit the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Khanun hit the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
[
"Strong winds from Typhoon Soulik blowing down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun blowing down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Soulik on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Khanun in the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Soulik on the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Khanun on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Soulik on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Khanun in the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EC%86%94%EB%A6%AD_(2018%EB%85%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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Soulik, it makes sense to extract events that are commonly associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and damage to infrastructure. These events are likely to be visualized in a video and are consistent with the characteristics of a powerful typhoon like Soulik.\n\nEVENTS:\n1. Strong winds blowing down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Debris flying through the air\n4. Roofs being torn off buildings\n5. Emergency responders evacuating people from flooded areas",
"en_article_excerpt": "Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Soulik_(2018)",
"event_category": "disasters",
"event_name": "typhoon_soulik",
"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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to Typhoon Soulik, it makes sense to consider the typical consequences and scenes associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and resulting damage. Given the typhoon's impact on the Korean Peninsula, events related to severe weather, destruction, and potential evacuation or rescue efforts are likely to be relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Residents evacuating their homes and seeking shelter\n4. Emergency responders rescuing people from flooded areas\n5. Debris and damaged buildings scattered across the affected regions",
"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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact and aftermath of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Soulik. Given the severity of the typhoon, events that depict its powerful effects on the Korean Peninsula are most relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal areas and cities\n3. People evacuating their homes and seeking shelter\n4. Debris and destroyed buildings scattered across streets\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1032211760315420675",
"video_description": "실시간 제주도 서귀포 상황 태풍 솔릭...위험행..........조심하세요다들",
"video_id": "1032211760315420675"
}
| 2
|
[
"A car is driving on a street with a large pile of green and brown leaves or foliage on the left side of the road.",
"The car continues to drive down the street, with the pile of foliage now more centralized in the frame. The foliage appears to be being blown or moved, suggesting windy conditions."
] |
1032211760315420675
|
A car is driving down a street on a windy day, passing by a large pile of leaves or foliage that is being blown around.
|
Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.
|
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding in urban areas of the Korean Peninsula during Typhoon Soulik in 2012",
"Heavy rainfall causing flooding in urban areas of the Korean Peninsula during Typhoon Khanun in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Soulik in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Khanun in 2012"
] |
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities caused by Typhoon Soulik on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities due to Typhoon Khanun on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Soulik hit the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Khanun hit the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
[
"Strong winds from Typhoon Soulik blowing down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun blowing down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Soulik on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Khanun in the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Soulik on the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Khanun on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Soulik on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Khanun in the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EC%86%94%EB%A6%AD_(2018%EB%85%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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Soulik, it makes sense to extract events that are commonly associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and damage to infrastructure. These events are likely to be visualized in a video and are consistent with the characteristics of a powerful typhoon like Soulik.\n\nEVENTS:\n1. Strong winds blowing down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Debris flying through the air\n4. Roofs being torn off buildings\n5. Emergency responders evacuating people from flooded areas",
"en_article_excerpt": "Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Soulik_(2018)",
"event_category": "disasters",
"event_name": "typhoon_soulik",
"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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to Typhoon Soulik, it makes sense to consider the typical consequences and scenes associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and resulting damage. Given the typhoon's impact on the Korean Peninsula, events related to severe weather, destruction, and potential evacuation or rescue efforts are likely to be relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Residents evacuating their homes and seeking shelter\n4. Emergency responders rescuing people from flooded areas\n5. Debris and damaged buildings scattered across the affected regions",
"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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact and aftermath of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Soulik. Given the severity of the typhoon, events that depict its powerful effects on the Korean Peninsula are most relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal areas and cities\n3. People evacuating their homes and seeking shelter\n4. Debris and destroyed buildings scattered across streets\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1032540315515682816",
"video_description": "#태풍 #솔릭 예상 경로! 동쪽으로 방향 틀어",
"video_id": "1032540315515682816"
}
| 2
|
[
"The image is a weather map showing temperature distribution across regions including North Korea, South Korea, and parts of Russia and Japan. Various cities are labeled with their temperatures in degrees Celsius.",
"The image continues to depict a weather map, now focusing on temperature distribution across regions including North Korea, South Korea, and parts of Russia and Japan. Numerous cities are labeled with their respective temperatures in degrees Celsius, indicating a slight variation in temperatures across the regions."
] |
1032540315515682816
|
A weather forecast video displaying temperature distributions across North Korea, South Korea, parts of Russia, and Japan, showing variations in temperatures across different cities in the regions.
|
Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.
|
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding in urban areas of the Korean Peninsula during Typhoon Soulik in 2012",
"Heavy rainfall causing flooding in urban areas of the Korean Peninsula during Typhoon Khanun in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Soulik in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Khanun in 2012"
] |
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities caused by Typhoon Soulik on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities due to Typhoon Khanun on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Soulik hit the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Khanun hit the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
[
"Strong winds from Typhoon Soulik blowing down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun blowing down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Soulik on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Khanun in the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Soulik on the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Khanun on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Soulik on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Khanun in the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EC%86%94%EB%A6%AD_(2018%EB%85%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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Soulik, it makes sense to extract events that are commonly associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and damage to infrastructure. These events are likely to be visualized in a video and are consistent with the characteristics of a powerful typhoon like Soulik.\n\nEVENTS:\n1. Strong winds blowing down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Debris flying through the air\n4. Roofs being torn off buildings\n5. Emergency responders evacuating people from flooded areas",
"en_article_excerpt": "Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Soulik_(2018)",
"event_category": "disasters",
"event_name": "typhoon_soulik",
"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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to Typhoon Soulik, it makes sense to consider the typical consequences and scenes associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and resulting damage. Given the typhoon's impact on the Korean Peninsula, events related to severe weather, destruction, and potential evacuation or rescue efforts are likely to be relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Residents evacuating their homes and seeking shelter\n4. Emergency responders rescuing people from flooded areas\n5. Debris and damaged buildings scattered across the affected regions",
"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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact and aftermath of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Soulik. Given the severity of the typhoon, events that depict its powerful effects on the Korean Peninsula are most relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal areas and cities\n3. People evacuating their homes and seeking shelter\n4. Debris and destroyed buildings scattered across streets\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1032471495958618112",
"video_description": "어제 저녁부터 비바람이 거세지다 잠잠하다 하더니, 지금은 세차게 몰아치는 중입니다 ㅠㅠ #태풍솔릭 #제주도 #제주시",
"video_id": "1032471495958618112"
}
| 2
|
[
"The image shows a view of tall trees with dense foliage. The sky appears overcast, suggesting a cloudy or rainy day. The ground beneath the trees is covered with a mix of soil and fallen leaves.",
"The video continues to display a view of tall trees with dense foliage. The sky remains overcast, maintaining the impression of a cloudy or rainy day. The ground beneath the trees is still covered with a mix of soil and fallen leaves, reinforcing the natural, serene atmosphere established in the previous frames."
] |
1032471495958618112
|
The video depicts a static, natural scene of a forest on a cloudy or rainy day, characterized by tall trees with dense foliage and a ground covered in soil and fallen leaves, maintaining a serene atmosphere throughout.
|
Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.
|
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding in urban areas of the Korean Peninsula during Typhoon Soulik in 2012",
"Heavy rainfall causing flooding in urban areas of the Korean Peninsula during Typhoon Khanun in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Soulik in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Khanun in 2012"
] |
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities caused by Typhoon Soulik on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities due to Typhoon Khanun on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Soulik hit the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Khanun hit the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
[
"Strong winds from Typhoon Soulik blowing down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun blowing down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Soulik on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Khanun in the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Soulik on the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Khanun on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Soulik on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Khanun in the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EC%86%94%EB%A6%AD_(2018%EB%85%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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Soulik, it makes sense to extract events that are commonly associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and damage to infrastructure. These events are likely to be visualized in a video and are consistent with the characteristics of a powerful typhoon like Soulik.\n\nEVENTS:\n1. Strong winds blowing down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Debris flying through the air\n4. Roofs being torn off buildings\n5. Emergency responders evacuating people from flooded areas",
"en_article_excerpt": "Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Soulik_(2018)",
"event_category": "disasters",
"event_name": "typhoon_soulik",
"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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to Typhoon Soulik, it makes sense to consider the typical consequences and scenes associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and resulting damage. Given the typhoon's impact on the Korean Peninsula, events related to severe weather, destruction, and potential evacuation or rescue efforts are likely to be relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Residents evacuating their homes and seeking shelter\n4. Emergency responders rescuing people from flooded areas\n5. Debris and damaged buildings scattered across the affected regions",
"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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact and aftermath of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Soulik. Given the severity of the typhoon, events that depict its powerful effects on the Korean Peninsula are most relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal areas and cities\n3. People evacuating their homes and seeking shelter\n4. Debris and destroyed buildings scattered across streets\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://twitter.com/i/status/1032234901897015298",
"video_description": "일본 가고시마에 상륙한 태풍 솔릭 위력ㅠㅠㅠ 8월19일자",
"video_id": "1032234901897015298"
}
| 2
|
[
"The image shows a street scene in a heavy storm, with strong winds and rain obscuring visibility. A small yellow car is parked on the side of the road, and there are other vehicles visible in the background, including a black car. The text at the top indicates that the location is experiencing strong winds and heavy rain, with a severe warning about Typhoon 19. The scene conveys a sense of urgency and the impact of severe weather conditions on urban areas.",
"The current frame continues to depict the street scene in a heavy storm with strong winds and rain obscuring visibility. The small yellow car remains parked on the side of the road, and the black car is still visible in the background. The text at the top of the frame reiterates that the location is experiencing strong winds and heavy rain, with a severe warning about Typhoon 19. The scene maintains a sense of urgency and the impact of severe weather conditions on urban areas, consistent with the previous frame."
] |
1032234901897015298
|
A severe storm, identified as Typhoon 19, is affecting an urban area, causing strong winds and heavy rain that obscure visibility. The scene shows a street with vehicles, including a parked small yellow car and a black car in the background, emphasizing the impact of the typhoon on daily life and urban conditions, creating a sense of urgency due to the extreme weather.
|
Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.
|
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding in urban areas of the Korean Peninsula during Typhoon Soulik in 2012",
"Heavy rainfall causing flooding in urban areas of the Korean Peninsula during Typhoon Khanun in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Soulik in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Khanun in 2012"
] |
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities caused by Typhoon Soulik on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities due to Typhoon Khanun on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Soulik hit the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Khanun hit the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
[
"Strong winds from Typhoon Soulik blowing down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun blowing down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Soulik on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Khanun in the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Soulik on the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Khanun on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Soulik on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Khanun in the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EC%86%94%EB%A6%AD_(2018%EB%85%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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Soulik, it makes sense to extract events that are commonly associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and damage to infrastructure. These events are likely to be visualized in a video and are consistent with the characteristics of a powerful typhoon like Soulik.\n\nEVENTS:\n1. Strong winds blowing down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Debris flying through the air\n4. Roofs being torn off buildings\n5. Emergency responders evacuating people from flooded areas",
"en_article_excerpt": "Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Soulik_(2018)",
"event_category": "disasters",
"event_name": "typhoon_soulik",
"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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to Typhoon Soulik, it makes sense to consider the typical consequences and scenes associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and resulting damage. Given the typhoon's impact on the Korean Peninsula, events related to severe weather, destruction, and potential evacuation or rescue efforts are likely to be relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Residents evacuating their homes and seeking shelter\n4. Emergency responders rescuing people from flooded areas\n5. Debris and damaged buildings scattered across the affected regions",
"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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact and aftermath of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Soulik. Given the severity of the typhoon, events that depict its powerful effects on the Korean Peninsula are most relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal areas and cities\n3. People evacuating their homes and seeking shelter\n4. Debris and destroyed buildings scattered across streets\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://youtube.com/watch?v=_V6HiUPBShQ",
"video_description": "태풍 피해 전해드렸는데요, 이렇게 제주와 일부 내륙에 피해가 집중된 건 예보와 달리 솔릭의 위력이 급격히 떨어졌기 때문입니다. 시속 100km를 넘나드는 강풍과 비를 동반해 모두를 긴장시켰던 태풍이 왜 이렇게 빠르게 약해졌는지, 엄민재 기자가 전해드립니다. 뉴스 원문 기사 보기 https://news.sbs.co.kr/news/endPage.do?news_id=N1004904932 [태풍 '솔릭' 북상] 기사 더보기 https://news.sbs.co.kr/news/newsHotIssueList.do?tagId=10000046975 #SBS뉴스 #SBSNEWS #SBS_NEWS #에스비에스뉴스 #태풍_'솔릭'_북상 #8뉴스 ▶SBS 뉴스 채널 구독하기 : https://n.sbs.co.kr/youtube ▶SBS 뉴스 라이브 : https://n.sbs.co.kr/youtubeLive , https://n.sbs.co.kr/live ▶대한민국 뉴스리더 SBS◀ 홈페이지: https://n.sbs.co.kr 페이스북: https://www.facebook.com/sbs8news 트위터: https://www.twitter.com/sbs8news",
"video_id": "_V6HiUPBShQ"
}
| 2
|
[
"The frame shows several palm trees swaying in strong winds, indicating a windy or stormy environment. The sky is overcast, suggesting inclement weather. A caption in Korean at the top of the frame translates to \"Rapidly increasing humidity, why?\" The SBS News logo is visible, indicating the frame is from a news broadcast.",
"The current frame continues to show the palm trees swaying in strong winds, reinforcing the ongoing windy or stormy environment. The sky remains overcast, maintaining the inclement weather setting. The same Korean caption \"Rapidly increasing humidity, why?\" appears at the top, emphasizing the news segment's focus on the rapidly changing weather conditions. The SBS News logo is still visible, confirming the continuity of the news broadcast."
] |
_V6HiUPBShQ
|
A news broadcast by SBS News depicts a stormy environment with strong winds and overcast skies, focusing on the rapid increase in humidity, as indicated by a Korean caption "Rapidly increasing humidity, why?" that appears in consecutive frames, suggesting an investigation or report on the cause of the sudden weather change.
|
Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.
|
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding in urban areas of the Korean Peninsula during Typhoon Soulik in 2012",
"Heavy rainfall causing flooding in urban areas of the Korean Peninsula during Typhoon Khanun in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Soulik in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Khanun in 2012"
] |
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities caused by Typhoon Soulik on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities due to Typhoon Khanun on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Soulik hit the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Khanun hit the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
[
"Strong winds from Typhoon Soulik blowing down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun blowing down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Soulik on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Khanun in the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Soulik on the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Khanun on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Soulik on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Khanun in the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EC%86%94%EB%A6%AD_(2018%EB%85%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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Soulik, it makes sense to extract events that are commonly associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and damage to infrastructure. These events are likely to be visualized in a video and are consistent with the characteristics of a powerful typhoon like Soulik.\n\nEVENTS:\n1. Strong winds blowing down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Debris flying through the air\n4. Roofs being torn off buildings\n5. Emergency responders evacuating people from flooded areas",
"en_article_excerpt": "Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Soulik_(2018)",
"event_category": "disasters",
"event_name": "typhoon_soulik",
"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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to Typhoon Soulik, it makes sense to consider the typical consequences and scenes associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and resulting damage. Given the typhoon's impact on the Korean Peninsula, events related to severe weather, destruction, and potential evacuation or rescue efforts are likely to be relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Residents evacuating their homes and seeking shelter\n4. Emergency responders rescuing people from flooded areas\n5. Debris and damaged buildings scattered across the affected regions",
"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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact and aftermath of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Soulik. Given the severity of the typhoon, events that depict its powerful effects on the Korean Peninsula are most relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal areas and cities\n3. People evacuating their homes and seeking shelter\n4. Debris and destroyed buildings scattered across streets\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://youtube.com/watch?v=Aiq8I97bscw",
"video_description": "제19호 태풍 '솔릭'이 일본 남부 해상에서 한반도를 향해 북진하고 있습니다. '솔릭'은 강한 중형급 태풍으로 중심기압은 960hPa, 강풍 반경은 340㎞이라고 하는데요. 만일 태풍이 우리나라를 관통하면 2012년 9월 '산바' 이후 약 6년 만으로 큰 피해가 우려됩니다. 자세한 내용 영상으로 보시죠. ◆ 연합뉴스 홈페이지→ http://www.yna.co.kr/ ◆ 이 시각 많이 본 기사 → https://goo.gl/VQTsSZ ◆ 오늘의 핫뉴스 → https://goo.gl/WyGXpG ◆ 현장영상 → https://goo.gl/5aZcx8 ◆ 카드뉴스 →https://goo.gl/QKfDTH ◆연합뉴스 공식 SNS◆ ◇페이스북→ https://www.facebook.com/yonhap/ ▣ 연합뉴스 유튜브 채널 구독 : https://goo.gl/pL7TmT",
"video_id": "Aiq8I97bscw"
}
| 2
|
[
"The image shows a turbulent ocean scene with large, crashing waves. The text in the upper right corner reads \"연합뉴스\" (Yonhap News), indicating that this footage might be from a news broadcast. Below it, the text \"기상청 예보\" (Korea Meteorological Administration forecast) suggests that this is related to a weather forecast, specifically likely to be a warning or update on a storm or rough sea conditions.",
"The current frame shows a snowy, overcast landscape with fog or mist. The text \"YONHAP NEWS AGENCY\" is prominently displayed in the center, indicating this footage is from a Yonhap News broadcast. The absence of waves and the shift to a foggy, snowy environment suggest a transition from the stormy ocean scene to a discussion on broader weather conditions, possibly focusing on winter storms or hazardous conditions."
] |
Aiq8I97bscw
|
A news broadcast from Yonhap News is showing severe weather conditions, starting with a turbulent ocean scene featuring large, crashing waves, indicating rough sea conditions likely due to a storm. The scene then shifts to a snowy, overcast landscape with fog or mist, suggesting the broadcast is discussing winter storms or broader hazardous weather conditions, possibly as part of a forecast or warning from the Korea Meteorological Administration.
|
Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.
|
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding in urban areas of the Korean Peninsula during Typhoon Soulik in 2012",
"Heavy rainfall causing flooding in urban areas of the Korean Peninsula during Typhoon Khanun in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Soulik in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Khanun in 2012"
] |
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities caused by Typhoon Soulik on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities due to Typhoon Khanun on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Soulik hit the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Khanun hit the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
[
"Strong winds from Typhoon Soulik blowing down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun blowing down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Soulik on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Khanun in the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Soulik on the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Khanun on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Soulik on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Khanun in the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EC%86%94%EB%A6%AD_(2018%EB%85%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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Soulik, it makes sense to extract events that are commonly associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and damage to infrastructure. These events are likely to be visualized in a video and are consistent with the characteristics of a powerful typhoon like Soulik.\n\nEVENTS:\n1. Strong winds blowing down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Debris flying through the air\n4. Roofs being torn off buildings\n5. Emergency responders evacuating people from flooded areas",
"en_article_excerpt": "Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Soulik_(2018)",
"event_category": "disasters",
"event_name": "typhoon_soulik",
"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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to Typhoon Soulik, it makes sense to consider the typical consequences and scenes associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and resulting damage. Given the typhoon's impact on the Korean Peninsula, events related to severe weather, destruction, and potential evacuation or rescue efforts are likely to be relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Residents evacuating their homes and seeking shelter\n4. Emergency responders rescuing people from flooded areas\n5. Debris and damaged buildings scattered across the affected regions",
"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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact and aftermath of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Soulik. Given the severity of the typhoon, events that depict its powerful effects on the Korean Peninsula are most relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal areas and cities\n3. People evacuating their homes and seeking shelter\n4. Debris and destroyed buildings scattered across streets\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://youtube.com/watch?v=25LVZnXdx0A",
"video_description": "중부지방을 중심으로 연일 매섭게 비가 쏟아지고 있다. 긴급상황에 대비해야 할 소방서까지 침수된 모습이 SNS를 통해 전파되면서 불안이 가중되고 있다. 비도 이 정도면 재해 수준. 아무 일도 없다는 듯 태풍 솔릭은 지나갔지만, 오히려 비의 공포는 더해져만 가는데... 제작 : 박태호PD(ptho@ytnplus.co.kr) ▶ 기사 원문 : http://www.ytn.co.kr/_ln/0103_201808292100061801 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, 8585@ytn.co.kr, #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ [ 한국 뉴스 채널 와이티엔 / Korea News Channel YTN ]",
"video_id": "25LVZnXdx0A"
}
| 2
|
[
"The image shows a flooded room with water covering the floor. A person is standing in the doorway, wearing shorts and a dark top. The Korean text on the image reads \"침수 피해로 갑자기 물놀이 하행,\" which translates to \"Suddenly taking a water ride due to flood damage.\" The room has wooden walls and a door frame, and the water level reaches a significant height on the floor.",
"The image continues to depict a flooded room, with the water level still significantly high on the floor. A person is now seen standing further inside the room, wearing shorts and a dark top. The Korean text on the image repeats \"침수 피해로 갑자기 물놀이 하행,\" which translates to \"Suddenly taking a water ride due to flood damage.\" The room maintains its wooden walls and door frame, emphasizing the extent of the flooding and its impact on the individual within the space."
] |
25LVZnXdx0A
|
A person is standing in a flooded room with wooden walls and a door frame, wearing shorts and a dark top. The water level is significantly high, covering the floor, indicating severe flood damage. The individual appears to be wading through the water, having moved from the doorway further into the room, suggesting they are navigating the flooded space. The setting implies a residential or indoor area that has been suddenly and severely affected by flooding, with the person seemingly caught off guard and now dealing with the aftermath.
|
Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.
|
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding in urban areas of the Korean Peninsula during Typhoon Soulik in 2012",
"Heavy rainfall causing flooding in urban areas of the Korean Peninsula during Typhoon Khanun in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"Residents evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Soulik in 2012",
"Debris and damaged buildings scattered across the Korean Peninsula after Typhoon Khanun in 2012"
] |
[
"Strong winds from Typhoon Soulik knocking down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun knocking down trees and power lines on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities caused by Typhoon Soulik on the Korean Peninsula in 2012",
"Flooding in coastal areas and cities due to Typhoon Khanun on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Soulik on the Korean Peninsula in 2012",
"People evacuating their homes and seeking shelter during Typhoon Khanun on the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Soulik hit the Korean Peninsula in 2012",
"Debris and destroyed buildings scattered across streets after Typhoon Khanun hit the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders rescuing people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
[
"Strong winds from Typhoon Soulik blowing down trees and power lines on the Korean Peninsula in 2012",
"Strong winds from Typhoon Khanun blowing down trees and power lines on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Soulik on the Korean Peninsula in 2012",
"Heavy rainfall and flooding from Typhoon Khanun in the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Soulik on the Korean Peninsula in 2012",
"Debris flying through the air during Typhoon Khanun on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Soulik on the Korean Peninsula in 2012",
"Roofs being torn off buildings during Typhoon Khanun in the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Soulik on the Korean Peninsula in 2012",
"Emergency responders evacuating people from flooded areas during Typhoon Khanun on the Korean Peninsula in 2012"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%83%9C%ED%92%8D_%EC%86%94%EB%A6%AD_(2018%EB%85%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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about Typhoon Soulik, it makes sense to extract events that are commonly associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and damage to infrastructure. These events are likely to be visualized in a video and are consistent with the characteristics of a powerful typhoon like Soulik.\n\nEVENTS:\n1. Strong winds blowing down trees and power lines\n2. Heavy rainfall flooding streets and homes\n3. Debris flying through the air\n4. Roofs being torn off buildings\n5. Emergency responders evacuating people from flooded areas",
"en_article_excerpt": "Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.",
"en_article_url": "https://en.wikipedia.org/wiki/Typhoon_Soulik_(2018)",
"event_category": "disasters",
"event_name": "typhoon_soulik",
"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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to Typhoon Soulik, it makes sense to consider the typical consequences and scenes associated with a large and deadly typhoon, such as strong winds, heavy rainfall, and resulting damage. Given the typhoon's impact on the Korean Peninsula, events related to severe weather, destruction, and potential evacuation or rescue efforts are likely to be relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Heavy rainfall causing flooding in urban areas\n3. Residents evacuating their homes and seeking shelter\n4. Emergency responders rescuing people from flooded areas\n5. Debris and damaged buildings scattered across the affected regions",
"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: Typhoon Soulik was an unusually large, and the deadliest typhoon to strike the Korean Peninsula since Khanun in 2012.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact and aftermath of a typhoon, such as destruction, flooding, and evacuation efforts, as these events are likely to be visualized in a video about Typhoon Soulik. Given the severity of the typhoon, events that depict its powerful effects on the Korean Peninsula are most relevant.\n\nEVENTS:\n1. Strong winds knocking down trees and power lines\n2. Flooding in coastal areas and cities\n3. People evacuating their homes and seeking shelter\n4. Debris and destroyed buildings scattered across streets\n5. Emergency responders rescuing people from flooded areas",
"video_URL": "http://youtube.com/watch?v=BRxOTPDR0g4",
"video_description": "건물 공사 구조물이 무너지고 교회 첨탑과 호텔 지붕도 강풍에 날려 추락했습니다. 아름드리 가로수는 뿌리째 뽑혔습니다. 지난 2010년 태풍 곤파스가 몰고 온 강풍의 위력입니다. 전남 홍도에 초속 42.9m의 폭풍이 불었고 태안 38.1m, 군산 33.6m, 서울도 21.6m의 강풍이 기록됐습니다. 바람 태풍 곤파스로 6명이 숨지고 11명이 부상했으며, 1,673억 원의 재산 피해가 발생했습니다. 북상하는 19호 태풍 '솔릭'은 8년 전 '곤파스'와 비슷한 경로로 움직이고 있습니다. 내일 새벽, 제주도 서쪽을 거쳐 서해안을 따라 북상한 뒤 태안반도에 상륙해 수도권을 통과할 것으로 예상됩니다. 한반도 주변 수온이 28도 정도로 무척 높아, 곤파스보다 강한 세력을 유지한 채 북상할 가능성이 큽니다. 기상청은 태풍 '솔릭'으로 인해 목요일과 금요일 사이 전국에 최고 400mm의 폭우가 쏟아지고 초속 40m가 넘는 강풍이 불 것으로 전망했습니다. 취재기자 : 정혜윤 영상편집 : 연진영 자막뉴스 제작 : 육지혜 에디터 ▶ 기사 원문 : http://www.ytn.co.kr/_ln/0108_201808220940500446 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, 8585@ytn.co.kr, #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ [ 한국 뉴스 채널 와이티엔 / Korea News Channel YTN ]",
"video_id": "BRxOTPDR0g4"
}
| 2
|
[
"The frame shows a stormy ocean with large waves crashing against the shore. Water droplets are visible on the glass, indicating heavy rain or spray from the waves. The text in the image is in Korean and mentions a tropical storm and its comparison to a previous storm.",
"The video continues to depict a stormy ocean scene with large waves crashing against the shore. Water droplets are still visible on the glass, indicating ongoing heavy rain or spray from the waves. The text in the image is in Korean and mentions a tropical storm and its comparison to a previous storm, \"Sollict\" is described as being similar to \"Gonpas\" in terms of intensity."
] |
BRxOTPDR0g4
|
A tropical storm is intensifying over the ocean, with large waves crashing against the shore amidst heavy rain or spray. The storm is being compared to a previous one, known as "Gonpas", in terms of intensity, with the current storm, "Sollict", exhibiting similar strength. The video captures the powerful and turbulent scene of the storm's impact on the coastline.
|
The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.
|
[
"Strong winds blowing sand and dust across the Eastern Gobi desert steppe during the sandstorm on March 14, 2021",
"Reduced visibility on roads and highways due to heavy sand and dust in the air during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"People wearing masks and protective gear to shield themselves from the massive sandstorm that hit the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and other parts of East Asia on 14 March 2021",
"Sand and dust accumulating on buildings, streets, and vehicles during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"Flights and daily activities being disrupted due to a sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, and Korean Peninsula on March 14, 2021"
] |
[
"People wearing masks walking in low visibility conditions during a sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on 14 March 2021",
"Cars driving with headlights on during the day due to reduced visibility caused by the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on March 14, 2021",
"Sandstorm reducing visibility in urban areas of the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"Flights grounded or delayed due to sandstorm in East Asia on March 14, 2021",
"Residents sealing windows and doors to prevent sand entry during the 14 March 2021 sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia"
] |
[
"Sandstorm reducing visibility on roads and highways in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"People wearing masks to protect themselves from the sandstorm in East Asia on March 14, 2021",
"Trees and buildings covered in dust and sand during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on 14 March 2021",
"Cars and buses driving slowly due to low visibility during a sandstorm in the Eastern Gobi desert or East Asia on March 14 2021",
"Residents cleaning up sand and dust from streets and homes after the 14 March 2021 sandstorm in East Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%99%A9%EC%82%AC",
"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 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects and progression of the sandstorm, such as reduced visibility, dust in the air, and people protecting themselves from the storm. These events are likely to be visualized in a video associated with the query, given the geographical scope and impact of the sandstorm.\n\nEVENTS:\n1. Dust and sand reducing visibility on roads and highways\n2. People wearing masks to protect themselves from the sandstorm\n3. Trees and buildings covered in dust and sand\n4. Cars and buses driving slowly due to low visibility\n5. Residents cleaning up sand and dust from streets and homes",
"en_article_excerpt": "The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2021_East_Asia_sandstorm",
"event_category": "disasters",
"event_name": "2021_sandstorm",
"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 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the 2021 East Asia sandstorm, it makes sense to consider the typical visual consequences of a large-scale sandstorm, such as reduced visibility, strong winds, and massive amounts of dust and sand particles in the air. Events that could be visualized in a video would likely involve the storm's impact on the environment and daily life, rather than abstract or behind-the-scenes occurrences.\n\nEVENTS:\n1. Strong winds blowing sand and dust across the Eastern Gobi desert steppe\n2. Reduced visibility on roads and highways due to heavy sand and dust in the air\n3. People wearing masks and protective gear to shield themselves from the storm\n4. Sand and dust accumulating on buildings, streets, and vehicles\n5. Flights and daily activities being disrupted due to poor weather conditions",
"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 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2021 East Asia sandstorm, it makes sense to extract events that are directly related to the effects and progression of the sandstorm, such as reduced visibility, transportation disruptions, and daily life impacts. These events should be concrete and visual, allowing them to be reasonably captioned in a video frame associated with the query.\n\nEVENTS:\n1. People wearing masks walking in low visibility conditions\n2. Cars driving with headlights on during the day due to reduced visibility\n3. Sandstorm reducing visibility in urban areas\n4. Flights being grounded or delayed at airports\n5. Residents sealing windows and doors to prevent sand entry",
"video_URL": "http://youtube.com/watch?v=Yddr-IKR_KA",
"video_description": "중국 둔황에 초대형 모래폭풍이 불어닥치면서눈 깜짝할 사이에 도시 전체가 암흑으로 뒤덮었습니다. [Ch.19] 사실을 보고 진실을 말합니다. 👍🏻 공식 홈페이지 http://news.tvchosun.com/ 👍🏻 공식 페이스북 https://www.facebook.com/tvchosunnews/ 👍🏻 공식 트위터 https://twitter.com/TVChosunNews * 뉴스제보 : 이메일(tvchosun@chosun.com), 카카오톡(tv조선제보), 전화(1661-0190)",
"video_id": "Yddr-IKR_KA"
}
| 2
|
[
"The image shows a hazy or foggy scene with minimal visibility. At the top, there is a banner with text in Korean and the Chinese flag. The text appears to discuss a topic related to a \"forecast\" or \"prediction.\" The bottom of the image has a larger text banner in Korean, which seems to refer to the \"Chinese Communist Party\" and \"forecast.\" The context suggests a news segment or discussion about a forecast related to the Chinese Communist Party.",
"The image continues to depict a hazy or foggy scene with low visibility. The top banner, similar to the previous frame, includes text in Korean and the Chinese flag, indicating a news segment. The text at the top seems to be addressing a question about the forecast's prediction. The bottom text banner is in Korean and mentions '중도심 힘쓴 초대형 모래폭풍,' which translates to 'a massive sandstorm affecting the Chinese heartland.' This suggests that the news segment is discussing a significant weather event, specifically a large sandstorm impacting central China."
] |
Yddr-IKR_KA
|
A news segment discusses a forecast related to the Chinese Communist Party, focusing on a significant weather event, specifically a massive sandstorm affecting central China. The segment, presented with Korean text and the Chinese flag, explores the prediction and implications of this large sandstorm, providing updates and analysis on its impact on the region.
|
The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.
|
[
"Strong winds blowing sand and dust across the Eastern Gobi desert steppe during the sandstorm on March 14, 2021",
"Reduced visibility on roads and highways due to heavy sand and dust in the air during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"People wearing masks and protective gear to shield themselves from the massive sandstorm that hit the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and other parts of East Asia on 14 March 2021",
"Sand and dust accumulating on buildings, streets, and vehicles during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"Flights and daily activities being disrupted due to a sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, and Korean Peninsula on March 14, 2021"
] |
[
"People wearing masks walking in low visibility conditions during a sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on 14 March 2021",
"Cars driving with headlights on during the day due to reduced visibility caused by the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on March 14, 2021",
"Sandstorm reducing visibility in urban areas of the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"Flights grounded or delayed due to sandstorm in East Asia on March 14, 2021",
"Residents sealing windows and doors to prevent sand entry during the 14 March 2021 sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia"
] |
[
"Sandstorm reducing visibility on roads and highways in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"People wearing masks to protect themselves from the sandstorm in East Asia on March 14, 2021",
"Trees and buildings covered in dust and sand during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on 14 March 2021",
"Cars and buses driving slowly due to low visibility during a sandstorm in the Eastern Gobi desert or East Asia on March 14 2021",
"Residents cleaning up sand and dust from streets and homes after the 14 March 2021 sandstorm in East Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%99%A9%EC%82%AC",
"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 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects and progression of the sandstorm, such as reduced visibility, dust in the air, and people protecting themselves from the storm. These events are likely to be visualized in a video associated with the query, given the geographical scope and impact of the sandstorm.\n\nEVENTS:\n1. Dust and sand reducing visibility on roads and highways\n2. People wearing masks to protect themselves from the sandstorm\n3. Trees and buildings covered in dust and sand\n4. Cars and buses driving slowly due to low visibility\n5. Residents cleaning up sand and dust from streets and homes",
"en_article_excerpt": "The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2021_East_Asia_sandstorm",
"event_category": "disasters",
"event_name": "2021_sandstorm",
"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 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the 2021 East Asia sandstorm, it makes sense to consider the typical visual consequences of a large-scale sandstorm, such as reduced visibility, strong winds, and massive amounts of dust and sand particles in the air. Events that could be visualized in a video would likely involve the storm's impact on the environment and daily life, rather than abstract or behind-the-scenes occurrences.\n\nEVENTS:\n1. Strong winds blowing sand and dust across the Eastern Gobi desert steppe\n2. Reduced visibility on roads and highways due to heavy sand and dust in the air\n3. People wearing masks and protective gear to shield themselves from the storm\n4. Sand and dust accumulating on buildings, streets, and vehicles\n5. Flights and daily activities being disrupted due to poor weather conditions",
"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 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2021 East Asia sandstorm, it makes sense to extract events that are directly related to the effects and progression of the sandstorm, such as reduced visibility, transportation disruptions, and daily life impacts. These events should be concrete and visual, allowing them to be reasonably captioned in a video frame associated with the query.\n\nEVENTS:\n1. People wearing masks walking in low visibility conditions\n2. Cars driving with headlights on during the day due to reduced visibility\n3. Sandstorm reducing visibility in urban areas\n4. Flights being grounded or delayed at airports\n5. Residents sealing windows and doors to prevent sand entry",
"video_URL": "http://youtube.com/watch?v=3BbP2OHdePY",
"video_description": "뿌연 하루였습니다. 몽골에서 시작된 모래폭풍이 중국을 거쳐 한반도에 상륙한 건데, 내일은 전국에서 황사가루가 섞인 '흙비'까지 내릴 전망입니다. [Ch.19] 사실을 보고 진실을 말합니다. 👍🏻 공식 홈페이지 http://news.tvchosun.com/ 👍🏻 공식 페이스북 https://www.facebook.com/tvchosunnews/ 👍🏻 공식 트위터 https://twitter.com/TVChosunNews * 뉴스제보 : 이메일(tvchosun@chosun.com), 카카오톡(tv조선제보), 전화(1661-0190)",
"video_id": "3BbP2OHdePY"
}
| 2
|
[
"The frame shows a cityscape with buildings and a green dome structure in the foreground. The sky is overcast, indicating poor weather. A news ticker at the bottom reads \"중국발 황사, 벽령도 상륙한 뒤 서쪽 지역으로 확대\" which translates to \"Yellow dust from China spreads to the west after landing in Baekryeong-do.\"",
"The current frame continues to show the cityscape, maintaining the focus on the buildings and the green dome structure in the foreground. The sky remains overcast, consistent with the previous frame's indication of poor weather conditions. The news ticker at the bottom reads \"내일 황비 내린다,\" translating to \"Tomorrow, yellow dust will fall,\" suggesting an ongoing discussion about the environmental impact of the yellow dust."
] |
3BbP2OHdePY
|
The video appears to depict a cityscape under the threat of a yellow dust storm originating from China. The scene is set against a backdrop of overcast skies, indicating poor weather conditions. A green dome structure is prominently visible in the foreground, suggesting it might be a significant landmark or a relevant feature in the context of the storm. The news tickers at the bottom of the frames provide updates on the situation, warning of the yellow dust's spread to the west after landing in Baekryeong-do and predicting that it will fall the next day. The overall context suggests a news report or public service announcement regarding the environmental and possibly health impacts of the yellow dust storm on the city and its inhabitants.
|
The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.
|
[
"Strong winds blowing sand and dust across the Eastern Gobi desert steppe during the sandstorm on March 14, 2021",
"Reduced visibility on roads and highways due to heavy sand and dust in the air during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"People wearing masks and protective gear to shield themselves from the massive sandstorm that hit the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and other parts of East Asia on 14 March 2021",
"Sand and dust accumulating on buildings, streets, and vehicles during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"Flights and daily activities being disrupted due to a sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, and Korean Peninsula on March 14, 2021"
] |
[
"People wearing masks walking in low visibility conditions during a sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on 14 March 2021",
"Cars driving with headlights on during the day due to reduced visibility caused by the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on March 14, 2021",
"Sandstorm reducing visibility in urban areas of the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"Flights grounded or delayed due to sandstorm in East Asia on March 14, 2021",
"Residents sealing windows and doors to prevent sand entry during the 14 March 2021 sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia"
] |
[
"Sandstorm reducing visibility on roads and highways in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"People wearing masks to protect themselves from the sandstorm in East Asia on March 14, 2021",
"Trees and buildings covered in dust and sand during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on 14 March 2021",
"Cars and buses driving slowly due to low visibility during a sandstorm in the Eastern Gobi desert or East Asia on March 14 2021",
"Residents cleaning up sand and dust from streets and homes after the 14 March 2021 sandstorm in East Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%99%A9%EC%82%AC",
"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 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects and progression of the sandstorm, such as reduced visibility, dust in the air, and people protecting themselves from the storm. These events are likely to be visualized in a video associated with the query, given the geographical scope and impact of the sandstorm.\n\nEVENTS:\n1. Dust and sand reducing visibility on roads and highways\n2. People wearing masks to protect themselves from the sandstorm\n3. Trees and buildings covered in dust and sand\n4. Cars and buses driving slowly due to low visibility\n5. Residents cleaning up sand and dust from streets and homes",
"en_article_excerpt": "The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2021_East_Asia_sandstorm",
"event_category": "disasters",
"event_name": "2021_sandstorm",
"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 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the 2021 East Asia sandstorm, it makes sense to consider the typical visual consequences of a large-scale sandstorm, such as reduced visibility, strong winds, and massive amounts of dust and sand particles in the air. Events that could be visualized in a video would likely involve the storm's impact on the environment and daily life, rather than abstract or behind-the-scenes occurrences.\n\nEVENTS:\n1. Strong winds blowing sand and dust across the Eastern Gobi desert steppe\n2. Reduced visibility on roads and highways due to heavy sand and dust in the air\n3. People wearing masks and protective gear to shield themselves from the storm\n4. Sand and dust accumulating on buildings, streets, and vehicles\n5. Flights and daily activities being disrupted due to poor weather conditions",
"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 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2021 East Asia sandstorm, it makes sense to extract events that are directly related to the effects and progression of the sandstorm, such as reduced visibility, transportation disruptions, and daily life impacts. These events should be concrete and visual, allowing them to be reasonably captioned in a video frame associated with the query.\n\nEVENTS:\n1. People wearing masks walking in low visibility conditions\n2. Cars driving with headlights on during the day due to reduced visibility\n3. Sandstorm reducing visibility in urban areas\n4. Flights being grounded or delayed at airports\n5. Residents sealing windows and doors to prevent sand entry",
"video_URL": "http://youtube.com/watch?v=6sLn3wHQvCQ",
"video_description": "초대형 모래폭풍에 산사태까지…재난영화 방불케한 순간 포착 (서울=연합뉴스) 중국 북서부 간쑤성에서 초대형 모래폭풍이 도시를 집어삼키고 산사태로 엄청난 흙더미가 쓰나미처럼 쏟아져 내리는 등 흡사 재난 영화의 한 장면 같은 순간들이 카메라에 포착됐습니다. 지난 25일 간쑤성 과저우현에서는 높이 수십 미터에 달하는 거대한 모래폭풍이 도시를 덮쳤습니다. 모래폭풍은 마치 거대한 모래 장벽 같은 모습이었습니다. 모래폭풍이 시야를 가리고 해를 가리면서 일대는 오렌지색으로 물들었습니다. 가시거리가 50m 미만, 공기 질이 최악 수준으로 내려앉으면서 대기오염 최고단계인 황색경보가 발령됐습니다. 한편 같은 날 간쑤성 룽난시에서는 산사태가 발생했습니다. 산 중턱의 한 부분에서부터 흙더미와 나무가 쓰나미처럼 산 아래로 쏟아져 내리면서 도로에 있던 관광객 수십 명이 비명을 지르며 도망쳤습니다. 이날 산사태로 차량 한 대가 파손됐지만 인명 피해는 없었다고 합니다. 영상으로 보시죠. 제작 : 김건태·안창주 영상 : 로이터 #연합뉴스 #중국 #황사 ◆ 연합뉴스 유튜브 : https://www.youtube.com/yonhap ◆ 연합뉴스 홈페이지→ http://www.yna.co.kr/ ◆ 연합뉴스 페이스북→ https://www.facebook.com/yonhap/ ◆ 연합뉴스 인스타 : https://goo.gl/UbqiQb ◆ 연합뉴스 비디오메타 채널https://www.youtube.com/channel/UCTMCrbtHU0M0SR6TuBrL4Pw",
"video_id": "6sLn3wHQvCQ"
}
| 2
|
[
"The image shows a hazy urban area with tall buildings partially obscured by fog or smog. Text in the upper right corner reads \"연합뉴스\" (Yonhap News) and in the lower center, \"공기질은 최악\" (Air quality is the worst), indicating poor air quality in the depicted city.",
"The current frame features a cartoon character pointing upwards with a determined expression, accompanied by the text \"구독하기\" (Subscribe) in pink and \"구독 꼭-온\" (Subscribe definitely) in a speech bubble. The Yonhap News Agency logo is also visible."
] |
6sLn3wHQvCQ
|
A public service announcement video by Yonhap News highlights the issue of poor air quality in an urban area, transitioning into a call to action, encouraging viewers to subscribe to their channel, presumably to stay informed about environmental issues and other news.
|
The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.
|
[
"Strong winds blowing sand and dust across the Eastern Gobi desert steppe during the sandstorm on March 14, 2021",
"Reduced visibility on roads and highways due to heavy sand and dust in the air during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"People wearing masks and protective gear to shield themselves from the massive sandstorm that hit the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and other parts of East Asia on 14 March 2021",
"Sand and dust accumulating on buildings, streets, and vehicles during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"Flights and daily activities being disrupted due to a sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, and Korean Peninsula on March 14, 2021"
] |
[
"People wearing masks walking in low visibility conditions during a sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on 14 March 2021",
"Cars driving with headlights on during the day due to reduced visibility caused by the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on March 14, 2021",
"Sandstorm reducing visibility in urban areas of the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"Flights grounded or delayed due to sandstorm in East Asia on March 14, 2021",
"Residents sealing windows and doors to prevent sand entry during the 14 March 2021 sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia"
] |
[
"Sandstorm reducing visibility on roads and highways in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, and East Asia on 14 March 2021",
"People wearing masks to protect themselves from the sandstorm in East Asia on March 14, 2021",
"Trees and buildings covered in dust and sand during the sandstorm in the Eastern Gobi desert, Mongolian Plateau, Loess Plateau, North China Plain, Korean Peninsula, or East Asia on 14 March 2021",
"Cars and buses driving slowly due to low visibility during a sandstorm in the Eastern Gobi desert or East Asia on March 14 2021",
"Residents cleaning up sand and dust from streets and homes after the 14 March 2021 sandstorm in East Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/%ED%99%A9%EC%82%AC",
"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 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects and progression of the sandstorm, such as reduced visibility, dust in the air, and people protecting themselves from the storm. These events are likely to be visualized in a video associated with the query, given the geographical scope and impact of the sandstorm.\n\nEVENTS:\n1. Dust and sand reducing visibility on roads and highways\n2. People wearing masks to protect themselves from the sandstorm\n3. Trees and buildings covered in dust and sand\n4. Cars and buses driving slowly due to low visibility\n5. Residents cleaning up sand and dust from streets and homes",
"en_article_excerpt": "The 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2021_East_Asia_sandstorm",
"event_category": "disasters",
"event_name": "2021_sandstorm",
"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 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: To extract events related to the 2021 East Asia sandstorm, it makes sense to consider the typical visual consequences of a large-scale sandstorm, such as reduced visibility, strong winds, and massive amounts of dust and sand particles in the air. Events that could be visualized in a video would likely involve the storm's impact on the environment and daily life, rather than abstract or behind-the-scenes occurrences.\n\nEVENTS:\n1. Strong winds blowing sand and dust across the Eastern Gobi desert steppe\n2. Reduced visibility on roads and highways due to heavy sand and dust in the air\n3. People wearing masks and protective gear to shield themselves from the storm\n4. Sand and dust accumulating on buildings, streets, and vehicles\n5. Flights and daily activities being disrupted due to poor weather conditions",
"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 2021 East Asia sandstorm was a meteorological phenomenon that began in the Eastern Gobi desert steppe on March 14, and subsequently spread to the entire Mongolian Plateau South, the Loess Plateau, the North China Plain and the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about the 2021 East Asia sandstorm, it makes sense to extract events that are directly related to the effects and progression of the sandstorm, such as reduced visibility, transportation disruptions, and daily life impacts. These events should be concrete and visual, allowing them to be reasonably captioned in a video frame associated with the query.\n\nEVENTS:\n1. People wearing masks walking in low visibility conditions\n2. Cars driving with headlights on during the day due to reduced visibility\n3. Sandstorm reducing visibility in urban areas\n4. Flights being grounded or delayed at airports\n5. Residents sealing windows and doors to prevent sand entry",
"video_URL": "http://youtube.com/watch?v=qaan1wMGnN0",
"video_description": "거대한 '모래 폭풍'이 하늘을 뒤덮었습니다. 지난 주말 몽골의 건조한 초원에서 발원한 '황사 바람'입니다. 태풍급 강풍을 동반한 모래 먼지가 한적한 작은 마을을 집어삼킬 듯한 기세입니다. 초원은 물론이고 주변 도시들도 앞을 분간하기 어려운 먼지 속에 갇혔습니다. '황색 폭풍'의 습격으로 몽골 초원지대 유목민 약 600명이 한때 실종됐습니다. 다행히 대부분 살아서 돌아왔지만 5살 어린 아이 를 포함해 10여 명은 결국 숨졌습니다. 최고 풍속 초속 30m가 넘는 모래 폭풍에 10층 높이의 철탑도 맥없이 부러졌습니다. 인근 지역 주민들은 모래 바람의 공포 속에, 정전 까지 돼 암흑과 추위에 떨었습니다. 몽골 초원과 가까운 중국 북쪽 네이멍구에서는 모래가 섞인 눈보라가 몰아쳤습니다. 강풍에 밀려온 모래와 눈이 민가를 뒤덮으면서 집안에 갇히는 주민들도 속출했습니다. 경찰 대여섯 명이 삽과 수레로 눈 모래를 걷어낸 지 2시간 만에 71살 할머니가 구조되기도 했습니다. 이번 황사는 강한 바람이 모래 먼지를 멀리까지 실어나르면서 '10년 만의 황사'로 강해졌습니다. 특히 몽골 초원의 봄풀이 아직 자라기 전이어서 흙먼지가 많았다고 중국 기상 당국은 분석했습니다. 황사로 뒤덮였던 베이징에는 다시 맑은 날씨가 찾아왔습니다. 강한 바람 때문에 모래 먼지는 하루 만에 사라졌 는데, 이번 봄에 황사가 몇 차례 더 예보가 돼있는 상황입니다. 취재기자 : 강성웅 촬영편집 : 고광 자막뉴스 : 윤현경 ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0134_202103170936125411 ▶ 제보 하기 : https://mj.ytn.co.kr/mj/mj_write.php ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN & YTN plus 무단 전재 및 재배포금지",
"video_id": "qaan1wMGnN0"
}
| 2
|
[
"The image shows a foggy or smoggy road with limited visibility. A traffic light is visible, showing a red left-turn arrow and a red straight arrow, indicating that vehicles are not permitted to turn left or go straight. The text in Korean at the bottom reads: \"몽골 초원과 가까운 중국 북쪽 냐이명구에서는 모래가 섞인 눈보라가 몰아쳤습니다,\" which translates to \"In the northern region of China near the Mongolian grasslands, a snowstorm mixed with sand has hit.\"",
"The image shows a snowy road with limited visibility due to snowfall. The road appears to be in a rural or mountainous area, with snow-covered trees and a fence visible on the side. The text in Korean at the bottom reads: \"몽골 초원과 가까운 중국 북쪽 냐이명구에서는 모래가 섞인 눈보라가 몰아쳤습니다,\" which translates to \"In the northern region of China near the Mongolian grasslands, a snowstorm mixed with sand has hit.\""
] |
qaan1wMGnN0
|
A snowstorm mixed with sand has hit the northern region of China, near the Mongolian grasslands, causing limited visibility on the roads. The storm is affecting both urban and rural areas, with images showing a foggy road with a traffic light in one scene and a snowy road surrounded by snow-covered trees in another. The video depicts the severe weather conditions in the region, with reduced visibility due to the snowstorm.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|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 effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://youtube.com/watch?v=0ZROpcl5nUE",
"video_description": "열기가 식을 새도 없이 계속 쌓여만 가고 있습니다. 폭염 특보도 확대, 강화되고 있는데요. 오늘 오전 11시를 기해 경기 남부와 강원 영서 남부에도 폭염경보가 내려졌고, 전국 대부분 지역으로 폭염주의보가 확대됐습니다. 현재 경북 경주 기온이 36.6도로 전국에서 가장 뜨겁고요. 대구 36.4도, 서울도 32.9도까지 올라 올해 최고 기온을 기록할 것으로 보입니다. 밤에도 열기는 쉽게 식지 못하고 열대야로 이어지는 곳이 많겠는데요. 내일 서울의 아침 기온 24도, 대구 25도로 오늘 밤사이에도 더위로 잠 못 이루는 곳이 많겠고요. 낮에는 다시 서울 기온이 33도, 대구 37도까지 오르는 등 오늘과 비슷하겠습니다. 현재 전국에 맑은 하늘이 드러나 있는데요. 내일도 종일 쾌청한 하늘이 함께 하겠지만, 강한 자외선에는 주의하셔야겠습니다. 당분간 뚜렷한 비 소식 없이 낮에는 폭염이, 밤에는 열대야가 기승을 부리겠습니다. 지금까지 날씨 정보였습니다. ▶ 기사 원문 : http://www.ytn.co.kr/_ln/0108_201807151449122225 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, 8585@ytn.co.kr, #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ [ 한국 뉴스 채널 와이티엔 / Korea News Channel YTN ]",
"video_id": "0ZROpcl5nUE"
}
| 2
|
[
"In the current frame, a woman stands to the right, dressed in a light pink dress, presenting the weather forecast. A weather chart is displayed on the left, showing temperature highs and lows for Seoul and Daegu, with the text in Korean indicating the forecast for a specific date. The background features a blue sky with clouds, and the YTN logo is visible in the top right corner.",
"The woman in a light pink dress continues to present the weather forecast. The weather chart on the left now displays the forecast for Seoul, with temperatures and weather conditions for several days. The background shows a clear blue sky with green trees, and the YTN logo is still visible in the top right corner."
] |
0ZROpcl5nUE
|
A woman presents the weather forecast on a television news program, specifically for locations including Seoul and Daegu, with a background that appears to be a serene outdoor setting. The forecast includes temperature highs and lows for specific dates, as well as conditions over several days for Seoul. The YTN logo is visible throughout, indicating the broadcast is from YTN.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|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 effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://youtube.com/watch?v=-HJV2kcDUAA",
"video_description": "서울 기온이 39도를 넘어 관측 사상 최고 기록을 갈아치운 1일 오후 서울 지하철역에서는 전력에 과부하가 걸려 스크린도어에 이상이 생겼다. 서울교통공사에 따르면 이날 오후 2시 39분께 지하철 4호선 동작역에서 당고개 방향 승강장 안전문(스크린도어)이 작동하지 않는 현상이 발생했다. 공사 측은 \"가정에서 전력에 이상이 생기면 화재 등 사고를 예방하기 위해 두꺼비집(누전차단기)이 내려가듯이, 승강장 쪽 전력에서 같은 작용이 일어난 것\"이라고 설명했다. 동작역 스크린도어는 오후 5시 30분 현재도 열려있는 상태로, 승강장에는 안전요원이 배치돼 만일의 사고에 대비하고 있다. 스크린도어가 개방된 상태일 뿐, 열차 운행에는 지장이 없는 상황이다. 공사 관계자는 \"밤에 운행을 마친 뒤에 정확한 원인을 조사할 방침\"이라면서 \"고온으로 인해 일부 부품에 문제가 생겼을 가능성도 염두에 두고 있다\"고 말했다. 영상취재 - [연합뉴스TV 차영우] ◆ 연합뉴스 홈페이지→ http://www.yna.co.kr/ ◆ 이 시각 많이 본 기사 → https://goo.gl/VQTsSZ ◆ 오늘의 핫뉴스 → https://goo.gl/WyGXpG ◆ 현장영상 → https://goo.gl/5aZcx8 ◆ 카드뉴스 →https://goo.gl/QKfDTH ◆연합뉴스 공식 SNS◆ ◇페이스북→ https://www.facebook.com/yonhap/ ▣ 연합뉴스 유튜브 채널 구독 : https://goo.gl/pL7TmT",
"video_id": "-HJV2kcDUAA"
}
| 2
|
[
"The image shows a digital display board in a public transportation setting, likely a subway or train station. The text on the board is in Korean, displaying information about the next train. The board states \"이번 열차: 당고개행\" (This train: Danggo Line) and \"다음 열차: 당고개행\" (Next train: Danggo Line). The time shown is 17:33. Below the train information, there is a progress bar with text indicating different directions or destinations, such as \"사당,\" \"종신대학,\" and \"동작.\" In the background, there are blurred figures of people, likely passengers waiting at the station.",
"The image continues to display a digital display board at a subway or train station, confirming the same Korean text about the next train heading towards \"Danggo Line\" at 17:33. The progress bar still shows destinations like \"사당,\" \"종신대학,\" and \"동작.\" Passengers are visible in the background, suggesting the scene is a continuation of people waiting for the train, maintaining the setting of a busy station."
] |
-HJV2kcDUAA
|
The video appears to be a brief scene of a busy subway or train station in Korea. The digital display board shows information about the next train, which is headed towards the Danggo Line, with a scheduled time of 17:33. The board also displays a progress bar with various destinations. The scene shows passengers waiting in the background, indicating a typical commute scenario with people awaiting their train. The video seems to capture a mundane moment in a public transportation setting, with no notable events or actions occurring, simply depicting the everyday activity of people waiting for their train.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|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 effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://youtube.com/watch?v=MZR5vPcBcI4",
"video_description": "극한 폭염속에도 경남 밀양 얼음골에선 주먹만한 얼음 기둥이 관측됐습니다. 신기한 건 이례적인 더위 속에서도 이 얼음이 평년보다 더 오랫동안, 꽁꽁 얼어있다는건데요. 어떻게 된 일일까요. 최진석 기자가 소개합니다. [리포트] 경남 밀양 재약산 해발 600m. 불볕더위에 바깥 온도는 36도를 넘어섰지만 바위 사이로 시원한 바람이 나옵니다. 바위 안쪽 온도를 재보니 서늘한 가을 기온인 9.2도. 바위 틈엔 주먹만한 얼음 기둥까지 있습니다. 이 지역의 명소이자 천연기념물 224호인 얼음골입니다. 불볕더위에 지친 사람들은 시원한 바람이 신기하기만 합니다. [이미경/부산광역시 북구 : \"여기까지 올라오는데 참 많이 힘들었는데, 너무 선선한 바람이 부니까 너무 너무 좋아요.\"] 바위 틈에서는 에어컨을 틀어놓은 것처럼 차가운 자연 바람이 나오고 있습니다. 열화상카메라로 온도를 재보니 1도밖에 되지 않습니다. 이곳의 얼음은 보통 장마철인 6,7월이면 다 녹아 없어지지만 올해는 계속되는 폭염의 상황에도 더 꽁꽁 얼어붙은 채 남아있습니다. [변희룡/부경대 지구환경과학과 명예교수 : \"10여 년 관측했는데, 올해 얼음이 가장 오래 관측됐거든요. 장마철에 비가 많이 오면씻겨지는데 장마철에 비가 많이 안왔어요.\"] 기록적인 폭염 속에 더위를 식히려 지난달에만 2만 여명이 찾은 밀양 얼음골. 신비로운 비밀을 간직한 채 더위에 지친 이들의 색다른 피서지가 되고 있습니다. KBS 뉴스 최진석입니다.",
"video_id": "MZR5vPcBcI4"
}
| 2
|
[
"The image shows four people standing together outdoors, possibly at a scenic location. They are wearing casual clothing and hats, indicating they may be tourists or travelers. One person is holding a microphone with a \"KBS\" logo, suggesting that this is a scene from a television broadcast or interview. Text at the bottom of the image, written in Korean, mentions \"이미경 부산광역시 북구\" and includes a description of a place being very beautiful after some difficulties, which may be part of the broadcast content.",
"The scene continues to feature the same four people standing outdoors, likely at the same scenic location from the previous frame. They are still dressed casually and one individual remains holding the microphone with the \"KBS\" logo, reinforcing the setting as part of a television broadcast or interview. The text at the bottom of the image, written in Korean, repeats the mention of \"이미경 부산광역시 북구\" and discusses the beauty of a place after overcoming challenges, indicating a consistent theme of the broadcast content."
] |
MZR5vPcBcI4
|
A television broadcast or interview is being conducted outdoors at a scenic location, possibly in 부산광역시 북구, with four people involved, including one holding a KBS microphone. The discussion, led by 이미경, focuses on the beauty of the location after it has overcome difficulties, suggesting a theme of transformation or recovery.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|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 effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://youtube.com/watch?v=HCV2Hx8B0-c",
"video_description": "8월의 첫날인 오늘 최악의 폭염이 이어졌습니다. 오늘 얼마나 더웠는지 기온만 봐도 알 수가 있는데요. 강원도 홍천은 낮 기온 41도, 서울 39.6도까지 오르면서 기상 관측 이래 가장 높은 기온을 기록했습니다. 내일도 극심한 폭염은 계속됩니다. 해안가를 제외하고는 전국이 낮 기온 35도를 넘어서면서 뜨겁겠습니다. 서울과 춘천 39도, 대전과 대구는 38도까지 오르면서 오늘만큼 덥겠습니다. 토요일부터는 기온이 조금 내려가겠지만 낮 기온 35도 안팎으로 찜통더위는 이어집니다. 절기상 입추인 다음 주 화요일에도 낮 기온 35도로 무덥겠습니다. 현재 경기와 충남, 전북에는 오존주의보가 발효 중입니다. 내일도 전국이 맑겠고 자외선이 강해서 오존 농도가 높아질 수 있겠는데요. 중부와 전북 지역에서는 오존을 주의하셔야겠습니다. 아침 기온은 서울 29도로 밤 사이에도 무덥겠습니다. 한낮에는 광주 37도, 부산 35도로 오늘만큼 덥겠습니다. 바다의 물결은 제주해상에서 최고 4미터까지 거세게 일겠습니다. 더위가 밤낮을 가리지 않는 만큼 온열 질환에 걸리지 않도록 건강 관리를 잘해주시기 바랍니다. 날씨정보 전해드렸습니다.",
"video_id": "HCV2Hx8B0-c"
}
| 2
|
[
"The current frame shows a weather presenter standing in front of a cityscape background. To her left, there is a graph displaying temperature trends for a specific location, Seoul. The graph shows two lines: one in red indicating the low temperatures, which are decreasing, and one in orange indicating the high temperatures, which are also trending downward. The text at the top of the graph is in Korean, and the presenter appears to be delivering a weather report.",
"The video features a weather presenter standing in front of a cityscape background. She is dressed in a white sleeveless dress, and there is a large screen beside her showing temperature trends. The screen displays a graph with two lines, one in red indicating the low temperatures and one in orange indicating the high temperatures, both of which are trending downward. The presenter appears to be delivering a weather report, likely discussing the cooling trend in Seoul, as suggested by the text on the graph."
] |
HCV2Hx8B0-c
|
A weather presenter delivers a report in front of a cityscape background, discussing the temperature trends in Seoul. The graph beside her shows both low and high temperatures decreasing, indicating a cooling trend in the area.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|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 effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://youtube.com/watch?v=XYrtvA02lKc",
"video_description": "경기도 분당에서 폭염으로 수도 배관이 파열되면서 교량의 균열이 발생해 교통이 통제되고 있습니다. 어젯밤(29일) 10시쯤 경기도 성남시 분당구에 있는 길이 25m, 폭 20m인 야탑 10교에 설치된 수도 배관이 터지면서 물이 치솟았습니다. 이 사고로 교각이 왼쪽으로 15도 정도 기울었고 도로 일부에도 균열이 생겼습니다. 경찰은 사고가 나자 야탑교 사거리부터 탑골 사거리까지 440m 구간 차량 통행을 전면 통제했습니다. 사고 당시 다리 위를 지나던 차량이 많지 않아 별다른 피해는 없었습니다. 경기 분당경찰서는 노후화된 교각이 폭염 영향으로 팽창하면서 짓눌린 수도관이 터져 물이 치솟은 것으로 추정된다고 설명했습니다. 최기성 [choiks7@ytn.co.kr] ▶ 기사 원문 : http://www.ytn.co.kr/_ln/0103_201807300822376551 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, 8585@ytn.co.kr, #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ [ 한국 뉴스 채널 와이티엔 / Korea News Channel YTN ]",
"video_id": "XYrtvA02lKc"
}
| 2
|
[
"The image shows a street partially closed off with orange traffic cones and barriers. There is a sign overhead indicating directions to various places, with Korean text. A few people are visible near the barriers, and vehicles are seen in the background. The text at the bottom of the image, in Korean, translates to \"The 10th Battalion by train… 'Pongsan Station to Pongsan'.\"",
"The current frame continues to show the street partially closed off with orange traffic cones and barriers. The overhead sign with Korean text remains visible, directing traffic to various locations. A few people are still present near the barriers, and vehicles can be seen in the background. The text at the bottom of the image translates to \"The 10th Battalion by train… 'Pongsan Station to Pongsan'.\" This suggests that the event or activity depicted involves a military movement or operation, specifically the 10th Battalion, which appears to be traveling by train from Pongsan Station to Pongsan."
] |
XYrtvA02lKc
|
The video appears to depict a scene of a street closure in a Korean setting, with orange traffic cones and barriers restricting access. The presence of an overhead sign with Korean text and the mention of the "10th Battalion" suggests a military-related event or operation. The text at the bottom of the frames indicates that the 10th Battalion is traveling by train from Pongsan Station to Pongsan, implying a troop movement or deployment. The few people visible near the barriers and the vehicles in the background suggest a controlled and possibly secure environment. Overall, the video seems to be capturing a moment of military mobilization or logistics in a specific Korean location.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|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 effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://twitter.com/i/status/1038669934375493632",
"video_description": "재난수준 폭염에도 올 여름 전력부족 없었다 올여름 재난 수준의 폭염으로 냉방 전력수요가 급증했지만 전력이 부족한 날은 없었음 7월과 8월 두 달 동안 공급예비율은 7일간을 제외, 모두 두 자릿수 이상을 유지 전력부족도 없었고, 전기세도 감면해준 문재인 정부",
"video_id": "1038669934375493632"
}
| 2
|
[
"The image shows a computer screen displaying various data points in Korean. There are four columns of data with numbers next to them, possibly indicating measurements or statistics, with units such as \"만kW\" (ten thousand kW). A person is seen from the side, looking at the screen, and wearing glasses. The text on the screen appears to be related to energy or power measurements, with the time displayed as \"오후 2:04:36\". There is also a news ticker at the bottom with additional information in Korean.",
"The image shows a computer screen displaying energy or power measurements in Korean. The screen shows data such as \"전비단계\" (power demand stage) with values like \"10,018.0 만kW\" (100,180 kW). The time \"오후 2:04:36\" is displayed on the screen. A person is looking at the screen from the side, and the news ticker at the bottom has information in Korean, including \"재난수준 폭염에도 올 여름 전력부족 없었다\" (No power shortage this summer despite disaster-level heatwave)."
] |
1038669934375493632
|
A person, wearing glasses, is monitoring a computer screen displaying real-time energy or power measurements in Korean. The data on the screen includes statistics such as power demand stage and units of measurement in ten thousand kW, with a time stamp of 2:04:36 PM. The context suggests a setting where energy consumption and power supply are being closely watched, possibly in a control room or monitoring station. The news ticker at the bottom of the screen provides additional information, including a report about the absence of power shortages despite a disaster-level heatwave, indicating that the video is taking place during a period of high energy demand, likely in South Korea.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|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 effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://twitter.com/i/status/1026325665824403456",
"video_description": "\"너무 덥지? 잘 지내고 있어?\" 관심어린 안부 한 마디가 폭염의 열기를 식힐 수 있습니다. 더위가 기승을 부리는 요즘 부모님께 또 친구에게 안부 전화 하는 건 어떨까요? (출처 : 국민안전방송 안전한TV) #성남시 #폭염 #가마솥더위 #폭염대비",
"video_id": "1026325665824403456"
}
| 2
|
[
"The image shows a woman in a professional setting, likely an office, with a blurred bookshelf in the background. She has a contemplative expression and is wearing a light-colored blouse.",
"The woman in the professional setting maintains a contemplative expression, continuing her thoughtful demeanor from the previous frame. She is still wearing a light-colored blouse, and the blurred bookshelf in the background remains consistent with the office environment. The overall setting and her expression suggest she is deeply engaged in a serious or reflective moment."
] |
1026325665824403456
|
A woman in a professional office setting is deeply engaged in a serious or reflective moment, maintaining a contemplative expression as she sits in front of a bookshelf, suggesting she may be considering important information or making a decision.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|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 effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://youtube.com/watch?v=09W_DRDb9HQ",
"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": "09W_DRDb9HQ"
}
| 2
|
[
"The image shows a close-up of a piece of cheese with a wooden stick partially inserted into it. There is text at the top of the image in Korean, which reads \"대한민국이 펼쳐 폭염에 익어버린 달걀\" which translates to \"South Korea unfolds, eggs that have ripened in the heatwave.\"",
"The image continues to focus on a close-up of the piece of cheese with a wooden stick partially inserted into it. The cheese appears soft and creamy. The same Korean text remains at the top, still reading \"대한민국이 펼쳐 폭염에 익어버린 달걀\" which translates to \"South Korea unfolds, eggs that have ripened in the heatwave.\""
] |
09W_DRDb9HQ
|
A video depicting a close-up of a piece of soft and creamy cheese with a wooden stick partially inserted into it, accompanied by a Korean text overlay that reads "South Korea unfolds, eggs that have ripened in the heatwave", suggesting a possible metaphorical or poetic connection between the cheese, South Korea, and the effects of a heatwave, with the content remaining static over the first two frames.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|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 effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://youtube.com/watch?v=8wcKX0LCc08",
"video_description": "폭염 때문에 힘든 건 사람만이 아닙니다. 과육이 물러진 수박이 산지에서 폐기되는 등 제철 과일과 채소 피해도 잇따르고 있습니다.",
"video_id": "8wcKX0LCc08"
}
| 2
|
[
"The current frame shows a field with a large number of watermelons scattered on the ground. A person is kneeling in the field, with their hands clasped together, seemingly reporting or presenting information. The watermelons are of various sizes and some are cut open. In the background, there is a green field with watermelons growing. The image includes text overlays from a news broadcast, indicating the time as 07:18 and the location as Seoul. Additional text in Korean suggests the context might be related to agricultural news or an event related to watermelons.",
"The scene transitions to a news studio where a female presenter stands in front of a large screen displaying the Korean text \"뉴스투데이\" (News Today) and \"투데이한정\" (Today Special), indicating a news segment. The presenter is dressed in a bright orange suit and holds a piece of paper, likely reading from it. The screen in the background shows a visual of a coastal scene with a bridge, suggesting the topic may be related to a coastal or environmental issue. The time displayed is 07:19, and additional text at the bottom indicates news related to \"서울 용산 어린이 사무실...\" (Seoul Yongsan Children's Office...), suggesting the segment could be about an event or news story concerning the Children's Office in Seoul."
] |
8wcKX0LCc08
|
A news broadcast from Seoul, starting at 07:18, covers a story related to watermelons in a field, where a person is reporting or presenting information among scattered watermelons of various sizes. The scene then cuts to a news studio at 07:19, where a female presenter introduces a segment called "News Today" and "Today Special", potentially discussing a coastal or environmental issue, with a possible connection to an event or news story about the Children's Office in Seoul's Yongsan area.
|
Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.
|
[
"People sweating and fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Temperature readings on thermometers exceeding record highs during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens gathering at public water parks and pools to cool off during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"Ambulances rushing to treat heat stroke patients during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Farmers inspecting withered and dried-out crops due to the heat wave in Northeast Asia during July 2018"
] |
[
"People sweating and fanning themselves in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Temperature readings displayed on outdoor thermometers showing extremely high numbers during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queueing for water or other cooling supplies during the July 2018 heat wave in Japan, North Korea, South Korea, and China",
"Heat-related illnesses being treated at hospitals or medical tents during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Dried-up or wilted plants and crops due to the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia"
] |
[
"People fanning themselves on the streets during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Citizens queuing for water in public spaces during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia",
"thermometer screens displaying extremely high temperatures during the July 2018 heat wave in Japan, North Korea, South Korea, China, and Northeast Asia",
"Trees and plants wilting due to the heat wave in Japan, North Korea, South Korea, China, and Northeast Asia in July 2018",
"People wearing masks and hats to protect themselves from the sun during the July 2018 heat wave in Japan, North Korea, South Korea, China, and other parts of Northeast Asia"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2018%EB%85%84_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%8F%AD%EC%97%BC",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are commonly associated with extreme heat and its effects on people and the environment. These events should be visual and tangible, allowing them to be captured in a video, such as people trying to cool themselves, impacts on daily life, or consequences of the heat wave.\n\nEVENTS:\n1. People fanning themselves on the streets\n2. Citizens queuing for water in public spaces\n3. thermometer screens displaying extremely high temperatures\n4. Trees and plants wilting due to the heat\n5. People wearing masks and hats to protect themselves from the sun",
"en_article_excerpt": "Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.",
"en_article_url": "https://en.wikipedia.org/wiki/2018_Northeast_Asia_heat_wave",
"event_category": "disasters",
"event_name": "2018_northeast_asia_heat_wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|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 effects of a heat wave, such as extreme weather conditions, people trying to cool themselves, and potential consequences of the heat wave. These events should be concrete and visual, allowing them to be easily depicted in a video.\n\nEVENTS:\n1. People sweating and fanning themselves on the streets\n2. Temperature readings on thermometers exceeding record highs\n3. Citizens gathering at public water parks and pools to cool off\n4. Ambulances rushing to treat heat stroke patients\n5. Farmers inspecting withered and dried-out crops due to the heat wave",
"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: Throughout much of July 2018, a record-breaking heat wave affected large areas of Northeast Asia including Japan, North Korea, South Korea, China.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about a record-breaking heat wave in Northeast Asia in July 2018, it makes sense to extract events that are visually representative of extreme heat and its effects on daily life and the environment. These events should be common consequences of a heat wave and plausible to be captured in a video during that time in the mentioned regions.\n\nEVENTS:\n1. People sweating and fanning themselves in public spaces\n2. Temperature readings displayed on outdoor thermometers showing extremely high numbers\n3. Citizens queueing for water or other cooling supplies\n4. Heat-related illnesses being treated at hospitals or medical tents\n5. Dried-up or wilted plants and crops due to the heat wave",
"video_URL": "http://youtube.com/watch?v=g9CbgCp52qc",
"video_description": "연일 불볕더위가 기승을 부리는 가운데 서울시가 도로에 물을 뿌려 열을 식히는 작업을 강화합니다. 서울시는 낮 최고기온이 32℃ 이상으로 오르면 폭염에 노출될 가능성이 큰 정오부터 오후 4시까지 중앙버스전용차로를 중심으로 살수 차량 운행을 확대한다고 밝혔습니다. 서울시는 여름철 도로 물뿌리기로 미세먼지를 제거하는 동시에 온열질환 등 폭염으로 발생할 수 있는 안전사고도 방지할 수 있기를 기대하고 있습니다. ▶ 기사 원문 : http://www.ytn.co.kr/_ln/0115_201807181131189139 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, 8585@ytn.co.kr, #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ [ 한국 뉴스 채널 와이티엔 / Korea News Channel YTN ]",
"video_id": "g9CbgCp52qc"
}
| 2
|
[
"A man with a beard and long hair is looking off to the side with a serious expression. The background is blurred with bokeh lights, suggesting an urban setting.",
"A figure, seemingly made of or surrounded by flames, is running at high speed amidst an explosive, fiery scene. The background is dominated by bright, glowing orange and yellow hues, indicating a chaotic, possibly destructive environment."
] |
g9CbgCp52qc
|
A man with a beard and long hair is depicted in an urban setting, initially shown with a serious expression. The scene then shifts to a chaotic and destructive environment where a figure engulfed in flames is running at high speed, suggesting an intense and potentially dangerous situation. The contrast between the calm, serious demeanor of the man in the first frame and the explosive, fiery scene in the second frame implies a dramatic turn of events, possibly indicating the man's involvement or reaction to the catastrophic incident unfolding before him.
|
In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.
|
[
"People bundling up in heavy clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in heavy clothing to brave the cold during record cold temperatures in East Asia, Southeast Asia, and South Asia in late January 2016",
"People bundling up in heavy clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong, during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia during late January 2016 snowfall events",
"Frost or ice formation on car windshields, roads, and buildings during the cold wave in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings during snowfall in East Asia, Southeast Asia, and South Asia in late January 2016",
"Residents in East Asia, Southeast Asia, and South Asia shoveling snow or using umbrellas to navigate snowy streets during the late January 2016 cold wave",
"Residents in East and South Asia shoveling snow or using umbrellas to navigate snowy streets during record cold temperatures in late January 2016",
"Residents shoveling snow or using umbrellas to navigate snowy streets in East Asia, Southeast Asia, or South Asia in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia Southeast Asia and South Asia during late January 2016"
] |
[
"People bundling up in warm clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in warm clothing to brave the cold in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People bundling up in warm clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"Frozen lakes and rivers with people ice skating or playing in East Asia Southeast Asia or South Asia during late January 2016 cold wave",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia where people are ice skating or playing during the record cold temperatures of late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, or South Asia where people are ice skating or playing in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia during late January 2016 cold wave",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia after snowfall in late January 2016",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 cold wave",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off sidewalks and driveways in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
[
"People bundling up in winter clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in winter clothing to brave the cold in East and South Asia during late January 2016 record cold snap",
"People bundling up in winter clothing to brave the cold during late January 2016 snowfall in East, Southeast, and South Asia",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during the cold wave of late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia due to record cold temperatures in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia after snowfall in late January 2016",
"Trees and buildings covered in snow and ice during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off streets and sidewalks in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_1%EC%9B%94_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%95%9C%ED%8C%8C",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, and the consequences of the snowfall, as these events are likely to be visualized in a video. The extracted events should be specific to the regions mentioned and the time of year, taking into account the typical climate and scenery of East Asia, mainland Southeast Asia, and northern South Asia in late January.\n\nEVENTS:\n1. People bundling up in winter clothing to brave the cold\n2. Snow falling in cities and towns\n3. Frozen lakes and rivers\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off streets and sidewalks",
"en_article_excerpt": "In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.",
"en_article_url": "https://en.wikipedia.org/wiki/January_2016_East_Asia_cold_wave",
"event_category": "disasters",
"event_name": "2016_east_asia_cold_wave",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|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 effects of the cold wave, such as people experiencing the cold weather, disruptions to daily life, and unusual weather phenomena like snowfall in regions that rarely see it. These events would be visually representative of the cold wave's impact and could be reasonably captured in a video.\n\nEVENTS:\n1. People bundling up in heavy clothing to brave the cold\n2. Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong\n3. Frost or ice forming on surfaces like car windshields, roads, and buildings\n4. Residents shoveling snow or using umbrellas to navigate snowy streets\n5. Cars and buses driving slowly on icy or snow-covered roads",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a cold wave, such as people dealing with the cold and snow, and disruptions to daily life. These events should be visual and concrete, and could be reasonably captured in a video of the cold wave's impact.\n\nEVENTS:\n1. People bundling up in warm clothing to brave the cold\n2. Snowplows clearing roads and highways\n3. Frozen lakes and rivers with people ice skating or playing\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off sidewalks and driveways",
"video_URL": "http://twitter.com/i/status/1346958705632296961",
"video_description": "전국 눈 대단한 한파 다들 잘 이겨내요",
"video_id": "1346958705632296961"
}
| 2
|
[
"The video captures a scene of a person riding a bicycle down a sidewalk in a residential area. The person is wearing a helmet and is moving towards the right side of the image. The area is lined with tall apartment buildings, and there is a large landscaped area with trees and paths on the right side of the sidewalk. The scene appears to be in the early morning or late afternoon, given the soft lighting.",
"The scene continues in the residential area with the person riding the bicycle down the sidewalk. The individual is still moving towards the right side of the image, maintaining the same direction as before. The background remains consistent with tall apartment buildings and the large landscaped area with trees and paths on the right. The lighting still suggests it is either early morning or late afternoon, and the overall atmosphere remains calm and quiet."
] |
1346958705632296961
|
A person rides a bicycle down a sidewalk in a residential area, moving in a consistent direction, surrounded by tall apartment buildings and a large landscaped area with trees and paths, in a calm and quiet atmosphere, likely during the early morning or late afternoon.
|
In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.
|
[
"People bundling up in heavy clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in heavy clothing to brave the cold during record cold temperatures in East Asia, Southeast Asia, and South Asia in late January 2016",
"People bundling up in heavy clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong, during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia during late January 2016 snowfall events",
"Frost or ice formation on car windshields, roads, and buildings during the cold wave in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings during snowfall in East Asia, Southeast Asia, and South Asia in late January 2016",
"Residents in East Asia, Southeast Asia, and South Asia shoveling snow or using umbrellas to navigate snowy streets during the late January 2016 cold wave",
"Residents in East and South Asia shoveling snow or using umbrellas to navigate snowy streets during record cold temperatures in late January 2016",
"Residents shoveling snow or using umbrellas to navigate snowy streets in East Asia, Southeast Asia, or South Asia in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia Southeast Asia and South Asia during late January 2016"
] |
[
"People bundling up in warm clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in warm clothing to brave the cold in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People bundling up in warm clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"Frozen lakes and rivers with people ice skating or playing in East Asia Southeast Asia or South Asia during late January 2016 cold wave",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia where people are ice skating or playing during the record cold temperatures of late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, or South Asia where people are ice skating or playing in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia during late January 2016 cold wave",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia after snowfall in late January 2016",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 cold wave",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off sidewalks and driveways in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
[
"People bundling up in winter clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in winter clothing to brave the cold in East and South Asia during late January 2016 record cold snap",
"People bundling up in winter clothing to brave the cold during late January 2016 snowfall in East, Southeast, and South Asia",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during the cold wave of late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia due to record cold temperatures in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia after snowfall in late January 2016",
"Trees and buildings covered in snow and ice during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off streets and sidewalks in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_1%EC%9B%94_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%95%9C%ED%8C%8C",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, and the consequences of the snowfall, as these events are likely to be visualized in a video. The extracted events should be specific to the regions mentioned and the time of year, taking into account the typical climate and scenery of East Asia, mainland Southeast Asia, and northern South Asia in late January.\n\nEVENTS:\n1. People bundling up in winter clothing to brave the cold\n2. Snow falling in cities and towns\n3. Frozen lakes and rivers\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off streets and sidewalks",
"en_article_excerpt": "In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.",
"en_article_url": "https://en.wikipedia.org/wiki/January_2016_East_Asia_cold_wave",
"event_category": "disasters",
"event_name": "2016_east_asia_cold_wave",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|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 effects of the cold wave, such as people experiencing the cold weather, disruptions to daily life, and unusual weather phenomena like snowfall in regions that rarely see it. These events would be visually representative of the cold wave's impact and could be reasonably captured in a video.\n\nEVENTS:\n1. People bundling up in heavy clothing to brave the cold\n2. Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong\n3. Frost or ice forming on surfaces like car windshields, roads, and buildings\n4. Residents shoveling snow or using umbrellas to navigate snowy streets\n5. Cars and buses driving slowly on icy or snow-covered roads",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a cold wave, such as people dealing with the cold and snow, and disruptions to daily life. These events should be visual and concrete, and could be reasonably captured in a video of the cold wave's impact.\n\nEVENTS:\n1. People bundling up in warm clothing to brave the cold\n2. Snowplows clearing roads and highways\n3. Frozen lakes and rivers with people ice skating or playing\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off sidewalks and driveways",
"video_URL": "http://youtube.com/watch?v=2qCY0mBeZy4",
"video_description": "지난 연말부터 시작된 한파의 기세는 여전했습니다. 강원도 산간은 영하 20도, 철원 영하 15.9도, 서울도 영하 9.8도를 기록했습니다. 이번 한파는 풀리지 않고 다음 주까지 이어질 것으로 보입니다. 주말부터 다음 주 초반까지 기온이 조금 오르지만, 이후 다시 기온이 급강하하기 때문입니다. 특히 다음 주 후반에는 서울 기온이 영하 15도까지 떨어지는 강력한 한파가 맹위를 떨칠 전망입니다. 올겨울 들어 가장 강력한 추위입니다. [윤기한 / 기상청 통보관 : 한파가 누그러지지 않은 상황에서 2차로 한기가 추가로 내려오는 것입니다. 따라서 다음 주에는 추위 강도가 지금보다 훨씬 세질 것으로 보입니다.] 북극 한파가 새해 첫날부터 열흘 이상 이어지는 것입니다. 서해안의 눈도 잠시 약해졌다가 다음 주 중반 이후에는 눈 폭탄으로 쏟아질 것으로 우려됩니다. 기상청은 이번 한파와 폭설로 동파와 축사, 비닐하우스 붕괴 등 시설물 피해가 속출할 것이라며 사전 대비를 당부했습니다. 취재기자: 김진두 영상편집: 한경희 자막뉴스: 박해진 ▶ 기사 원문 : https://www.ytn.co.kr/replay/view.php?idx=29&key=202101020712296278 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, social@ytn.co.kr, #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN & YTN plus 무단 전재 및 재배포금지",
"video_id": "2qCY0mBeZy4"
}
| 2
|
[
"The image shows a person using a red hand pump to draw water from a blue container. There is snow on the ground, indicating a cold environment. The person is wearing gloves and is pumping the handle to extract water. In the upper left corner, there is an inset image of a man in glasses, with the text \"자막뉴스 SOCIAL\" in Korean, suggesting this might be a part of a news segment. At the bottom, the text reads \"울겨울 들어 가장 강력한 추위입니다,\" which translates to \"This is the most severe cold wave since early winter.\"",
"The image continues to depict the person using the red hand pump to draw water from the blue container. The snowy ground and cold environment remain consistent with the previous frame. The person, still wearing gloves, is pumping the handle to extract water. The inset image of the man in glasses and the text \"자막뉴스 SOCIAL\" in the upper left corner indicate this is part of a news segment. The text at the bottom reiterates \"울겨울 들어 가장 강력한 추위입니다,\" which translates to \"This is the most severe cold wave since early winter.\""
] |
2qCY0mBeZy4
|
A person is shown using a hand pump to draw water from a container in a cold, snowy environment, indicating a severe cold wave. The scene is part of a news segment, suggested by the inset image of a man and the Korean text "자막뉴스 SOCIAL". The repetition of the action and setting across frames emphasizes the challenges of accessing water during this extremely cold period, with the text at the bottom reinforcing that it is the most severe cold wave since early winter.
|
In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.
|
[
"People bundling up in heavy clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in heavy clothing to brave the cold during record cold temperatures in East Asia, Southeast Asia, and South Asia in late January 2016",
"People bundling up in heavy clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong, during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia during late January 2016 snowfall events",
"Frost or ice formation on car windshields, roads, and buildings during the cold wave in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings during snowfall in East Asia, Southeast Asia, and South Asia in late January 2016",
"Residents in East Asia, Southeast Asia, and South Asia shoveling snow or using umbrellas to navigate snowy streets during the late January 2016 cold wave",
"Residents in East and South Asia shoveling snow or using umbrellas to navigate snowy streets during record cold temperatures in late January 2016",
"Residents shoveling snow or using umbrellas to navigate snowy streets in East Asia, Southeast Asia, or South Asia in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia Southeast Asia and South Asia during late January 2016"
] |
[
"People bundling up in warm clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in warm clothing to brave the cold in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People bundling up in warm clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"Frozen lakes and rivers with people ice skating or playing in East Asia Southeast Asia or South Asia during late January 2016 cold wave",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia where people are ice skating or playing during the record cold temperatures of late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, or South Asia where people are ice skating or playing in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia during late January 2016 cold wave",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia after snowfall in late January 2016",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 cold wave",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off sidewalks and driveways in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
[
"People bundling up in winter clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in winter clothing to brave the cold in East and South Asia during late January 2016 record cold snap",
"People bundling up in winter clothing to brave the cold during late January 2016 snowfall in East, Southeast, and South Asia",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during the cold wave of late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia due to record cold temperatures in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia after snowfall in late January 2016",
"Trees and buildings covered in snow and ice during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off streets and sidewalks in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_1%EC%9B%94_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%95%9C%ED%8C%8C",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, and the consequences of the snowfall, as these events are likely to be visualized in a video. The extracted events should be specific to the regions mentioned and the time of year, taking into account the typical climate and scenery of East Asia, mainland Southeast Asia, and northern South Asia in late January.\n\nEVENTS:\n1. People bundling up in winter clothing to brave the cold\n2. Snow falling in cities and towns\n3. Frozen lakes and rivers\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off streets and sidewalks",
"en_article_excerpt": "In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.",
"en_article_url": "https://en.wikipedia.org/wiki/January_2016_East_Asia_cold_wave",
"event_category": "disasters",
"event_name": "2016_east_asia_cold_wave",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|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 effects of the cold wave, such as people experiencing the cold weather, disruptions to daily life, and unusual weather phenomena like snowfall in regions that rarely see it. These events would be visually representative of the cold wave's impact and could be reasonably captured in a video.\n\nEVENTS:\n1. People bundling up in heavy clothing to brave the cold\n2. Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong\n3. Frost or ice forming on surfaces like car windshields, roads, and buildings\n4. Residents shoveling snow or using umbrellas to navigate snowy streets\n5. Cars and buses driving slowly on icy or snow-covered roads",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a cold wave, such as people dealing with the cold and snow, and disruptions to daily life. These events should be visual and concrete, and could be reasonably captured in a video of the cold wave's impact.\n\nEVENTS:\n1. People bundling up in warm clothing to brave the cold\n2. Snowplows clearing roads and highways\n3. Frozen lakes and rivers with people ice skating or playing\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off sidewalks and driveways",
"video_URL": "http://youtube.com/watch?v=QmU3W9ffZeM",
"video_description": "기온이 마치 롤러코스터처럼 떨어질 모양입니다. 얼마나 추워질지 벌써부터 겁도 나는데요. 일단 내일 아침 서울 기온은 영하 11도까지 떨어지겠고요. 목요일부터는 찬바람이 더욱 강해지면서 아침 기온이 영하 15도로 전날 낮 대비 13도가량 기온이 급감하겠습니다. 한낮 기온도 영하 11도에 머물 텐데요. 다음 날 금요일 아침 기온은 영하 17도로 이번 한파의 절정이 되겠습니다. 한파 대비 미리 해주시는 게 좋겠습니다. 이에 따라서 오늘 밤 9시를 기해서는 경기 동부와 북부, 충청도, 경북 곳곳에 한파경보가 발효되겠고요. 서울 등 그 밖의 수도권과 충청도 전북 내륙 지역까지 한파주의보가 확대 발효되겠습니다. 눈구름도 함께 몰려오겠습니다. 내일 퇴근길 무렵에 서해 등 서쪽지역에 눈이 내리기 시작해 밤사이에 전국으로 확대될 텐데요. 특히 서해안 지역으로는 최대 30cm 이상, 제주 산지에는 최고 50cm 이상의 폭설이 우려됩니다. 충남 지역에는 금요일까지 호남과 제주도는 일요일까지 눈이 길게 이어지겠습니다. 날씨였습니다. https://imnews.imbc.com/replay/2021/nw1700/article/6048848_34922.html #날씨,#추위 #한파",
"video_id": "QmU3W9ffZeM"
}
| 2
|
[
"In the image, a woman is standing outdoors near a body of water with reeds in the background. She is dressed in a long-sleeved, high-neck, brown dress and is gesturing towards a weather map displayed on a screen. The map shows parts of South Korea highlighted in blue, indicating specific weather zones. The text \"기상특보\" is visible, which translates to \"weather alert\" or \"weather warning.\" The woman appears to be presenting or explaining the weather conditions in the indicated areas, likely as part of a weather forecast segment on a television broadcast. The scene suggests cold or rainy weather conditions based on the woman's attire and the overall setting.",
"The woman continues her presentation outdoors, maintaining the same background with reeds near the body of water. She points towards the weather map, which still displays specific weather zones in South Korea highlighted in blue. The text \"기상특보\" is still visible, emphasizing the ongoing weather alert. She appears to be explaining the weather conditions in detail, likely providing updates or further details on the weather alert for the highlighted areas."
] |
QmU3W9ffZeM
|
A woman, dressed in a brown dress, presents a weather forecast outdoors near a body of water with reeds in the background. She gestures towards a screen displaying a weather map of South Korea, highlighting specific areas with a "weather alert" or "weather warning" indicated by the text "기상특보". The woman provides detailed explanations of the weather conditions in the highlighted areas, likely updating viewers on cold or rainy weather conditions across South Korea as part of a television broadcast.
|
In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.
|
[
"People bundling up in heavy clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in heavy clothing to brave the cold during record cold temperatures in East Asia, Southeast Asia, and South Asia in late January 2016",
"People bundling up in heavy clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong, during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia during late January 2016 snowfall events",
"Frost or ice formation on car windshields, roads, and buildings during the cold wave in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings during snowfall in East Asia, Southeast Asia, and South Asia in late January 2016",
"Residents in East Asia, Southeast Asia, and South Asia shoveling snow or using umbrellas to navigate snowy streets during the late January 2016 cold wave",
"Residents in East and South Asia shoveling snow or using umbrellas to navigate snowy streets during record cold temperatures in late January 2016",
"Residents shoveling snow or using umbrellas to navigate snowy streets in East Asia, Southeast Asia, or South Asia in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia Southeast Asia and South Asia during late January 2016"
] |
[
"People bundling up in warm clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in warm clothing to brave the cold in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People bundling up in warm clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"Frozen lakes and rivers with people ice skating or playing in East Asia Southeast Asia or South Asia during late January 2016 cold wave",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia where people are ice skating or playing during the record cold temperatures of late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, or South Asia where people are ice skating or playing in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia during late January 2016 cold wave",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia after snowfall in late January 2016",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 cold wave",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off sidewalks and driveways in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
[
"People bundling up in winter clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in winter clothing to brave the cold in East and South Asia during late January 2016 record cold snap",
"People bundling up in winter clothing to brave the cold during late January 2016 snowfall in East, Southeast, and South Asia",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during the cold wave of late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia due to record cold temperatures in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia after snowfall in late January 2016",
"Trees and buildings covered in snow and ice during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off streets and sidewalks in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_1%EC%9B%94_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%95%9C%ED%8C%8C",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, and the consequences of the snowfall, as these events are likely to be visualized in a video. The extracted events should be specific to the regions mentioned and the time of year, taking into account the typical climate and scenery of East Asia, mainland Southeast Asia, and northern South Asia in late January.\n\nEVENTS:\n1. People bundling up in winter clothing to brave the cold\n2. Snow falling in cities and towns\n3. Frozen lakes and rivers\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off streets and sidewalks",
"en_article_excerpt": "In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.",
"en_article_url": "https://en.wikipedia.org/wiki/January_2016_East_Asia_cold_wave",
"event_category": "disasters",
"event_name": "2016_east_asia_cold_wave",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|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 effects of the cold wave, such as people experiencing the cold weather, disruptions to daily life, and unusual weather phenomena like snowfall in regions that rarely see it. These events would be visually representative of the cold wave's impact and could be reasonably captured in a video.\n\nEVENTS:\n1. People bundling up in heavy clothing to brave the cold\n2. Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong\n3. Frost or ice forming on surfaces like car windshields, roads, and buildings\n4. Residents shoveling snow or using umbrellas to navigate snowy streets\n5. Cars and buses driving slowly on icy or snow-covered roads",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a cold wave, such as people dealing with the cold and snow, and disruptions to daily life. These events should be visual and concrete, and could be reasonably captured in a video of the cold wave's impact.\n\nEVENTS:\n1. People bundling up in warm clothing to brave the cold\n2. Snowplows clearing roads and highways\n3. Frozen lakes and rivers with people ice skating or playing\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off sidewalks and driveways",
"video_URL": "http://youtube.com/watch?v=G7XGz4uL6mI",
"video_description": "기상정보 배혜지 기상캐스터 2021년 1월 12일 화요일 아침 시각 빙판길 골목길 언덕길 등 보행 조심하세요... 감기 걸리지 않도록 건강관리 잘하세요. 행복한 화요일 되세요.^^ #감기조심 #한파특보 #한파경보 #한파주의보 #건조경보 #화재예방 #산불조심 #코로나19 #COVID19 #기상정보 #날씨 #Weather #배혜지기상캐스터 #기상캐스터 #WeatherCaster #KBS뉴스광장 ============================================================== Uploaded by: 하안마음 (White Heart.rhythm7777777) Youtube: http://www.youtube.com/user/rhythmsgarden Twitter: https://twitter.com/rhythm700 Face Book: https://www.facebook.com/rhythm700 Instagram: https://www.instagram.com/rhythm7777777 헤일리 웨스튼라 Hayley Westenra Official Website: http://www.hayleywestenra.com Instagram: https://www.instagram.com/hayleywestenra Twitter: https://twitter.com/hayleywestenra FaceBook: https://www.facebook.com/hayleywestenra Youtube: https://www.youtube.com/channel/UCuA623UAgxrJuWcMcaI_kgg 헤일리 웨스튼라 코리아 Hayley Westenra Korea Fancafe: http://cafe.daum.net/HayleyWestenra Facebook: https://www.facebook.com/hayleywestenra Youtube: https://www.youtube.com/channel/UCBrwEte0dnl1JTWSpzGFVeA/videos Wikipedia: http://en.wikipedia.org/wiki/Hayley_Westenra",
"video_id": "G7XGz4uL6mI"
}
| 2
|
[
"The image shows a news anchor standing to the right side, gesturing toward a large screen displaying a map of South Korea. The map highlights certain regions in yellow and includes text in Korean. The anchor is dressed in a yellow dress and appears to be explaining something related to the highlighted regions. The background features a city skyline, and the text at the top right corner indicates the time as 07:47.",
"The news anchor, still wearing a yellow dress, stands to the right side, with her hands clasped in front of her. She is positioned in front of a screen showing a map of South Korea, divided into three time intervals with highlighted areas in blue and green. The background depicts a snowy landscape with trees and a road. The text at the top right corner indicates the time as 07:48. The anchor appears to be delivering the weather forecast for the upcoming times."
] |
G7XGz4uL6mI
|
A news anchor delivers a weather forecast, standing in front of a screen displaying a map of South Korea. The map highlights various regions and is divided into time intervals, indicating different weather conditions. The anchor explains the forecast, gesturing towards the map and providing information about the expected weather in different parts of the country. The background changes from a city skyline to a snowy landscape, but the anchor remains in the same position, continuing to present the weather forecast at 07:47 and 07:48.
|
In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.
|
[
"People bundling up in heavy clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in heavy clothing to brave the cold during record cold temperatures in East Asia, Southeast Asia, and South Asia in late January 2016",
"People bundling up in heavy clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong, during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia during late January 2016 snowfall events",
"Frost or ice formation on car windshields, roads, and buildings during the cold wave in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings during snowfall in East Asia, Southeast Asia, and South Asia in late January 2016",
"Residents in East Asia, Southeast Asia, and South Asia shoveling snow or using umbrellas to navigate snowy streets during the late January 2016 cold wave",
"Residents in East and South Asia shoveling snow or using umbrellas to navigate snowy streets during record cold temperatures in late January 2016",
"Residents shoveling snow or using umbrellas to navigate snowy streets in East Asia, Southeast Asia, or South Asia in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia Southeast Asia and South Asia during late January 2016"
] |
[
"People bundling up in warm clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in warm clothing to brave the cold in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People bundling up in warm clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"Frozen lakes and rivers with people ice skating or playing in East Asia Southeast Asia or South Asia during late January 2016 cold wave",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia where people are ice skating or playing during the record cold temperatures of late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, or South Asia where people are ice skating or playing in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia during late January 2016 cold wave",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia after snowfall in late January 2016",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 cold wave",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off sidewalks and driveways in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
[
"People bundling up in winter clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in winter clothing to brave the cold in East and South Asia during late January 2016 record cold snap",
"People bundling up in winter clothing to brave the cold during late January 2016 snowfall in East, Southeast, and South Asia",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during the cold wave of late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia due to record cold temperatures in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia after snowfall in late January 2016",
"Trees and buildings covered in snow and ice during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off streets and sidewalks in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_1%EC%9B%94_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%95%9C%ED%8C%8C",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, and the consequences of the snowfall, as these events are likely to be visualized in a video. The extracted events should be specific to the regions mentioned and the time of year, taking into account the typical climate and scenery of East Asia, mainland Southeast Asia, and northern South Asia in late January.\n\nEVENTS:\n1. People bundling up in winter clothing to brave the cold\n2. Snow falling in cities and towns\n3. Frozen lakes and rivers\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off streets and sidewalks",
"en_article_excerpt": "In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.",
"en_article_url": "https://en.wikipedia.org/wiki/January_2016_East_Asia_cold_wave",
"event_category": "disasters",
"event_name": "2016_east_asia_cold_wave",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|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 effects of the cold wave, such as people experiencing the cold weather, disruptions to daily life, and unusual weather phenomena like snowfall in regions that rarely see it. These events would be visually representative of the cold wave's impact and could be reasonably captured in a video.\n\nEVENTS:\n1. People bundling up in heavy clothing to brave the cold\n2. Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong\n3. Frost or ice forming on surfaces like car windshields, roads, and buildings\n4. Residents shoveling snow or using umbrellas to navigate snowy streets\n5. Cars and buses driving slowly on icy or snow-covered roads",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a cold wave, such as people dealing with the cold and snow, and disruptions to daily life. These events should be visual and concrete, and could be reasonably captured in a video of the cold wave's impact.\n\nEVENTS:\n1. People bundling up in warm clothing to brave the cold\n2. Snowplows clearing roads and highways\n3. Frozen lakes and rivers with people ice skating or playing\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off sidewalks and driveways",
"video_URL": "http://twitter.com/i/status/1346762056142188546",
"video_description": "눈보라 때문에 기절을 함",
"video_id": "1346762056142188546"
}
| 2
|
[
"A snowy night scene outside a building with illuminated signs for \"JUNO HAIR\" and \"三丁目\" (Santōmachi). The area is covered in snow, and the ground is blanketed with snow, indicating heavy snowfall. There are no visible people in the frame.",
"The snowy night scene continues with a person walking in the distance, heading towards the building with illuminated signs for \"JUNO HAIR\" and \"三丁目\" (Santōmachi). The heavy snowfall persists, covering the ground and creating a winter atmosphere."
] |
1346762056142188546
|
A person walks through a snowy night scene towards a building with signs for "JUNO HAIR" and "三丁目" (Santōmachi) on a heavily snow-covered ground, amidst persistent snowfall.
|
In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.
|
[
"People bundling up in heavy clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in heavy clothing to brave the cold during record cold temperatures in East Asia, Southeast Asia, and South Asia in late January 2016",
"People bundling up in heavy clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong, during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia during late January 2016 snowfall events",
"Frost or ice formation on car windshields, roads, and buildings during the cold wave in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings during snowfall in East Asia, Southeast Asia, and South Asia in late January 2016",
"Residents in East Asia, Southeast Asia, and South Asia shoveling snow or using umbrellas to navigate snowy streets during the late January 2016 cold wave",
"Residents in East and South Asia shoveling snow or using umbrellas to navigate snowy streets during record cold temperatures in late January 2016",
"Residents shoveling snow or using umbrellas to navigate snowy streets in East Asia, Southeast Asia, or South Asia in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia Southeast Asia and South Asia during late January 2016"
] |
[
"People bundling up in warm clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in warm clothing to brave the cold in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People bundling up in warm clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"Frozen lakes and rivers with people ice skating or playing in East Asia Southeast Asia or South Asia during late January 2016 cold wave",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia where people are ice skating or playing during the record cold temperatures of late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, or South Asia where people are ice skating or playing in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia during late January 2016 cold wave",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia after snowfall in late January 2016",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 cold wave",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off sidewalks and driveways in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
[
"People bundling up in winter clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in winter clothing to brave the cold in East and South Asia during late January 2016 record cold snap",
"People bundling up in winter clothing to brave the cold during late January 2016 snowfall in East, Southeast, and South Asia",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during the cold wave of late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia due to record cold temperatures in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia after snowfall in late January 2016",
"Trees and buildings covered in snow and ice during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off streets and sidewalks in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_1%EC%9B%94_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%95%9C%ED%8C%8C",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, and the consequences of the snowfall, as these events are likely to be visualized in a video. The extracted events should be specific to the regions mentioned and the time of year, taking into account the typical climate and scenery of East Asia, mainland Southeast Asia, and northern South Asia in late January.\n\nEVENTS:\n1. People bundling up in winter clothing to brave the cold\n2. Snow falling in cities and towns\n3. Frozen lakes and rivers\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off streets and sidewalks",
"en_article_excerpt": "In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.",
"en_article_url": "https://en.wikipedia.org/wiki/January_2016_East_Asia_cold_wave",
"event_category": "disasters",
"event_name": "2016_east_asia_cold_wave",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|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 effects of the cold wave, such as people experiencing the cold weather, disruptions to daily life, and unusual weather phenomena like snowfall in regions that rarely see it. These events would be visually representative of the cold wave's impact and could be reasonably captured in a video.\n\nEVENTS:\n1. People bundling up in heavy clothing to brave the cold\n2. Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong\n3. Frost or ice forming on surfaces like car windshields, roads, and buildings\n4. Residents shoveling snow or using umbrellas to navigate snowy streets\n5. Cars and buses driving slowly on icy or snow-covered roads",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a cold wave, such as people dealing with the cold and snow, and disruptions to daily life. These events should be visual and concrete, and could be reasonably captured in a video of the cold wave's impact.\n\nEVENTS:\n1. People bundling up in warm clothing to brave the cold\n2. Snowplows clearing roads and highways\n3. Frozen lakes and rivers with people ice skating or playing\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off sidewalks and driveways",
"video_URL": "http://twitter.com/i/status/1346961474866925570",
"video_description": "눈보라가 휘날리는 바람 찬 부산 시청 #풍산",
"video_id": "1346961474866925570"
}
| 2
|
[
"The image shows a group of people standing on a sidewalk near a street, holding yellow signs. They appear to be engaged in a peaceful protest or demonstration. Some individuals are wearing black jackets and masks. The setting is an urban area with tall buildings and bare trees, indicating it might be winter. The signs have Korean text, and the context suggests they are advocating for a cause, although the specific message is not clear from the image alone.",
"The current frame depicts a street scene in an urban area, likely during winter, given the presence of bare trees. The focus is on a silver van parked on the side of the road with its back doors open, revealing various items inside. The van is positioned near a pedestrian crosswalk, and traffic cones are set up on the road, possibly indicating a controlled area or directing traffic. The setting is consistent with a city environment, with tall buildings in the background and a few individuals visible, including one near the van. The atmosphere seems calm and orderly, with no visible signs of protest or demonstration from the previous frame."
] |
1346961474866925570
|
A group of people, some wearing black jackets and masks, are participating in a peaceful protest or demonstration on a sidewalk in an urban area, likely during winter, holding yellow signs with Korean text to advocate for a cause. Nearby, a silver van is parked with its back doors open, possibly related to the event, and traffic cones are set up to control the area, maintaining a calm and orderly atmosphere.
|
In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.
|
[
"People bundling up in heavy clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in heavy clothing to brave the cold during record cold temperatures in East Asia, Southeast Asia, and South Asia in late January 2016",
"People bundling up in heavy clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong, during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snowflakes falling in cities like Bangkok or Hong Kong in East Asia during late January 2016 snowfall events",
"Frost or ice formation on car windshields, roads, and buildings during the cold wave in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Frost or ice forming on surfaces like car windshields, roads, and buildings during snowfall in East Asia, Southeast Asia, and South Asia in late January 2016",
"Residents in East Asia, Southeast Asia, and South Asia shoveling snow or using umbrellas to navigate snowy streets during the late January 2016 cold wave",
"Residents in East and South Asia shoveling snow or using umbrellas to navigate snowy streets during record cold temperatures in late January 2016",
"Residents shoveling snow or using umbrellas to navigate snowy streets in East Asia, Southeast Asia, or South Asia in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Cars and buses driving slowly on icy or snow-covered roads in East Asia Southeast Asia and South Asia during late January 2016"
] |
[
"People bundling up in warm clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in warm clothing to brave the cold in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People bundling up in warm clothing to brave the cold during late January 2016 snowfall in East Asia, Southeast Asia, and South Asia",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"Snowplows clearing roads and highways in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"Frozen lakes and rivers with people ice skating or playing in East Asia Southeast Asia or South Asia during late January 2016 cold wave",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia where people are ice skating or playing during the record cold temperatures of late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, or South Asia where people are ice skating or playing in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia during late January 2016 cold wave",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia Southeast Asia and South Asia after snowfall in late January 2016",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 cold wave",
"People shoveling snow off sidewalks and driveways in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off sidewalks and driveways in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
[
"People bundling up in winter clothing to brave the cold during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"People bundling up in winter clothing to brave the cold in East and South Asia during late January 2016 record cold snap",
"People bundling up in winter clothing to brave the cold during late January 2016 snowfall in East, Southeast, and South Asia",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during the cold wave of late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Snow falling in cities and towns in East Asia, Southeast Asia, and South Asia in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia due to record cold temperatures in late January 2016",
"Frozen lakes and rivers in East Asia, Southeast Asia, and South Asia after snowfall in late January 2016",
"Trees and buildings covered in snow and ice during the late January 2016 cold wave in East Asia, Southeast Asia, and South Asia",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during record cold temperatures in late January 2016",
"Trees and buildings covered in snow and ice in East Asia, Southeast Asia, and South Asia during late January 2016 snowfall",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during the cold wave in late January 2016",
"People shoveling snow off streets and sidewalks in East Asia, Southeast Asia, and South Asia during late January 2016 record cold temperatures",
"People shoveling snow off streets and sidewalks in East Asia Southeast Asia and South Asia during late January 2016 snowfall"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2016%EB%85%84_1%EC%9B%94_%EB%8F%99%EC%95%84%EC%8B%9C%EC%95%84_%ED%95%9C%ED%8C%8C",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of the cold wave, such as people experiencing the cold weather, and the consequences of the snowfall, as these events are likely to be visualized in a video. The extracted events should be specific to the regions mentioned and the time of year, taking into account the typical climate and scenery of East Asia, mainland Southeast Asia, and northern South Asia in late January.\n\nEVENTS:\n1. People bundling up in winter clothing to brave the cold\n2. Snow falling in cities and towns\n3. Frozen lakes and rivers\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off streets and sidewalks",
"en_article_excerpt": "In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.",
"en_article_url": "https://en.wikipedia.org/wiki/January_2016_East_Asia_cold_wave",
"event_category": "disasters",
"event_name": "2016_east_asia_cold_wave",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|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 effects of the cold wave, such as people experiencing the cold weather, disruptions to daily life, and unusual weather phenomena like snowfall in regions that rarely see it. These events would be visually representative of the cold wave's impact and could be reasonably captured in a video.\n\nEVENTS:\n1. People bundling up in heavy clothing to brave the cold\n2. Snowflakes falling in cities that rarely see snow, such as Bangkok or Hong Kong\n3. Frost or ice forming on surfaces like car windshields, roads, and buildings\n4. Residents shoveling snow or using umbrellas to navigate snowy streets\n5. Cars and buses driving slowly on icy or snow-covered roads",
"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: In late January 2016, a cold wave struck much of East Asia, parts of mainland Southeast Asia and parts of northern South Asia, bringing record cold temperatures and snowfall to many regions.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the effects of a cold wave, such as people dealing with the cold and snow, and disruptions to daily life. These events should be visual and concrete, and could be reasonably captured in a video of the cold wave's impact.\n\nEVENTS:\n1. People bundling up in warm clothing to brave the cold\n2. Snowplows clearing roads and highways\n3. Frozen lakes and rivers with people ice skating or playing\n4. Trees and buildings covered in snow and ice\n5. People shoveling snow off sidewalks and driveways",
"video_URL": "http://youtube.com/watch?v=PxIbNGPQYw8",
"video_description": "지난주 부터 계속되는 한파에 SNS 등에서는 순간포착 영상인 이른바 '얼었어' 시리즈가 유행하고 있다고 합니다. https://imnews.imbc.com/replay/2021/nwtoday/article/6054105_34943.html #한파, #SNS, #얼었어시리즈",
"video_id": "PxIbNGPQYw8"
}
| 2
|
[
"The image shows a news segment featuring various products. On the left, a person is holding a package of baby wipes, and the text indicates a news headline about them. In the middle, a person is holding a small bottle, possibly a beverage, with a screen in the background showing the name \"Jacquie.\" On the right, there's a bottle of Coca-Cola Zero Sugar. The main headline at the bottom of the image suggests a news story about price differences in certain products in Korea. The overall context appears to be a news report on consumer products and their prices.",
"The image continues with a news segment focusing on consumer products and their prices in Korea. On the left, a hand is opening a package of baby wipes, with the text suggesting a news headline related to them. In the center, a hand holds a small bottle of water, with a screen in the background still showing \"Jacquie,\" indicating a price comparison. On the right, the Coca-Cola Zero Sugar bottle remains visible, and the main headline at the bottom repeats the theme of price differences in Korea. The overall context remains a news report analyzing consumer product prices."
] |
PxIbNGPQYw8
|
A news segment is being reported, focusing on the price differences of various consumer products in Korea. The products featured include baby wipes, a beverage, and Coca-Cola Zero Sugar. The report appears to be comparing prices, with on-screen text and visuals highlighting the differences. A person, possibly a news anchor or reporter, is presenting the information, with hands shown opening packages and holding products for demonstration. The context suggests an informative news story aimed at consumers, analyzing and discussing the pricing of everyday products in the Korean market.
|
Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.
|
[
"Heavy rains and floods in the southern Korean Peninsula during summer 2020",
"Heavy rains pouring down in southern South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North and South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during the summer floods of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during heavy rains in summer 2020",
"Rescue teams navigating boats through flooded streets to reach stranded residents during the summer floods of 2020 in North and South Korea",
"Rescue teams navigating boats through flooded streets to reach stranded residents in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after floods in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after heavy rains in North and South Korea during the summer of 2020"
] |
[
"People evacuating flooded homes and buildings in the Korean Peninsula during the summer rainy season of 2020",
"People evacuating flooded homes and buildings in the Korean Peninsula during summer 2020 heavy rains",
"Cars and buildings submerged in floodwater in North Korea and South Korea during the summer floods of 2020",
"Cars and buildings submerged in floodwater during heavy rains in the Korean Peninsula in summer 2020",
"Emergency responders rescuing people from flooded areas in North Korea and South Korea during the summer rainy season of 2020",
"Emergency responders rescuing people from flooded areas in North and South Korea during heavy rains in the summer of 2020",
"Debris and wreckage from destroyed buildings and infrastructure due to floods in North and South Korea during the summer 2020 rainy season",
"Debris and wreckage from destroyed buildings and infrastructure in North Korea, South Korea, and the Korean Peninsula after heavy rains during the summer rainy season of June-August 2020",
"Residents clearing mud and water from their homes and streets after floods in the Korean Peninsula during the summer 2020 rainy season",
"Residents clearing mud and water from their homes and streets in North and South Korea after heavy rains during the summer rainy season of 2020"
] |
[
"Floodwaters inundating homes and buildings in southern Korea, particularly in South Korea, during the summer rainy season of 2020",
"Floodwaters inundating homes and buildings in southern Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North and South Korea during heavy rains in summer 2020",
"Rescue workers helping those stranded by the floods in North Korea and South Korea during the summer rainy season of 2020",
"Rescue workers helping those stranded by floods in the Korean Peninsula during the summer rainy season of 2020",
"Cars and buildings submerged in water during floods in North and South Korea, Korean Peninsula, Summer 2020",
"Cars and buildings submerged in water in North and South Korea during heavy rains in summer 2020",
"Emergency responders distributing aid and supplies to communities affected by floods in North Korea and South Korea during the summer rainy season of June to August 2020",
"Emergency responders distributing aid and supplies to affected communities in North and South Korea during heavy rains in the summer of 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2020%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact of floods and heavy rains in Korea, such as scenes of flooding, damage, and rescue efforts, as these are likely to be visualized in a video about the event. The extracted events should be specific to the region and the time of year, taking into account the regional rainy season and the areas most affected by the floods.\n\nEVENTS:\n1. Floodwaters inundating homes and buildings in southern Korea\n2. People evacuating flooded areas by boat\n3. Rescue workers helping those stranded by the floods\n4. Cars and buildings submerged in water\n5. Emergency responders distributing aid and supplies to affected communities",
"en_article_excerpt": "Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Korean_floods",
"event_category": "disasters",
"event_name": "2020_korean_floods",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the cause and effects of the flooding, such as scenes of heavy rainfall, flooded areas, and rescue efforts. These events are likely to be visualized in a video documenting the floods and their impact on the region.\n\nEVENTS:\n1. Heavy rains pouring down in the southern parts of the Korean Peninsula\n2. Rivers overflowing and flooding nearby cities and towns\n3. People evacuating their homes and seeking higher ground\n4. Rescue teams navigating boats through flooded streets to reach stranded residents\n5. Cars and buildings submerged in water with debris scattered around",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the consequences of flooding and heavy rainfall, such as damage to infrastructure, evacuation efforts, and scenes of flooding. These events are likely to be visualized in a video capturing the impact of the floods on the region.\n\nEVENTS:\n1. People evacuating flooded homes and buildings\n2. Cars and buildings submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Debris and wreckage from destroyed buildings and infrastructure\n5. Residents clearing mud and water from their homes and streets",
"video_URL": "http://youtube.com/watch?v=SPZkwqJerMU",
"video_description": "2020년 홍수 피해 주민들에 1천483억원 보상 2020년 여름 기나긴 장마로 큰 홍수 피해를 당한 주민들이 총 1천480여억원의 보상금을 지급받게 됐습니다. 환경부 소속 중앙환경분쟁조정위원회는 홍수 피해를 본 주민들과 정부, 지자체 및 한국수자원공사 간 분쟁조정 절차가 최근 마무리됐다고 밝혔습니다. 조정위는 관계부처 원인 조사에서 댐·하천을 미흡하게 관리한 사실이 드러난 점 등을 고려했다고 밝혔습니다. 연합뉴스TV 기사문의 및 제보 : 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": "SPZkwqJerMU"
}
| 2
|
[
"The image shows a scene of debris and rubble, indicating destruction or a disaster. In the background, there are mountains, and the sky appears overcast. There is text in Korean on the image that provides additional context. The text at the top right reads \"연합뉴스TV\" and \"부산 24,707,\" which suggests that this footage is from a news broadcast and the location is Busan. The text at the bottom reads \"2020년 홍수 피해 주민들에게 1천483억원 보상,\" which translates to \"14.83 billion won compensation to flood victims in 2020.\" The scene appears to be related to the aftermath of a flood and the compensation being provided to the affected residents.",
"The scene continues to show the aftermath of a flood, with extensive debris and rubble scattered across the area. The text at the bottom of the image repeats the message about the \"14.83 billion won compensation to flood victims in 2020,\" reinforcing the focus on the financial support being offered to those affected by the disaster. The consistent presence of mountains in the background and the overcast sky suggests that the footage is still capturing the same location and conditions as previously described."
] |
SPZkwqJerMU
|
The video depicts the aftermath of a flood in Busan, showing a scene of destruction with debris and rubble scattered across the area, set against the backdrop of mountains and an overcast sky. The footage, from a 2020 news broadcast, highlights the compensation being provided to flood victims, with a total of 14.83 billion won allocated for this purpose. The consistent imagery and text overlays emphasize the focus on the disaster's impact and the financial support being offered to affected residents.
|
Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.
|
[
"Heavy rains and floods in the southern Korean Peninsula during summer 2020",
"Heavy rains pouring down in southern South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North and South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during the summer floods of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during heavy rains in summer 2020",
"Rescue teams navigating boats through flooded streets to reach stranded residents during the summer floods of 2020 in North and South Korea",
"Rescue teams navigating boats through flooded streets to reach stranded residents in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after floods in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after heavy rains in North and South Korea during the summer of 2020"
] |
[
"People evacuating flooded homes and buildings in the Korean Peninsula during the summer rainy season of 2020",
"People evacuating flooded homes and buildings in the Korean Peninsula during summer 2020 heavy rains",
"Cars and buildings submerged in floodwater in North Korea and South Korea during the summer floods of 2020",
"Cars and buildings submerged in floodwater during heavy rains in the Korean Peninsula in summer 2020",
"Emergency responders rescuing people from flooded areas in North Korea and South Korea during the summer rainy season of 2020",
"Emergency responders rescuing people from flooded areas in North and South Korea during heavy rains in the summer of 2020",
"Debris and wreckage from destroyed buildings and infrastructure due to floods in North and South Korea during the summer 2020 rainy season",
"Debris and wreckage from destroyed buildings and infrastructure in North Korea, South Korea, and the Korean Peninsula after heavy rains during the summer rainy season of June-August 2020",
"Residents clearing mud and water from their homes and streets after floods in the Korean Peninsula during the summer 2020 rainy season",
"Residents clearing mud and water from their homes and streets in North and South Korea after heavy rains during the summer rainy season of 2020"
] |
[
"Floodwaters inundating homes and buildings in southern Korea, particularly in South Korea, during the summer rainy season of 2020",
"Floodwaters inundating homes and buildings in southern Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North and South Korea during heavy rains in summer 2020",
"Rescue workers helping those stranded by the floods in North Korea and South Korea during the summer rainy season of 2020",
"Rescue workers helping those stranded by floods in the Korean Peninsula during the summer rainy season of 2020",
"Cars and buildings submerged in water during floods in North and South Korea, Korean Peninsula, Summer 2020",
"Cars and buildings submerged in water in North and South Korea during heavy rains in summer 2020",
"Emergency responders distributing aid and supplies to communities affected by floods in North Korea and South Korea during the summer rainy season of June to August 2020",
"Emergency responders distributing aid and supplies to affected communities in North and South Korea during heavy rains in the summer of 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2020%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact of floods and heavy rains in Korea, such as scenes of flooding, damage, and rescue efforts, as these are likely to be visualized in a video about the event. The extracted events should be specific to the region and the time of year, taking into account the regional rainy season and the areas most affected by the floods.\n\nEVENTS:\n1. Floodwaters inundating homes and buildings in southern Korea\n2. People evacuating flooded areas by boat\n3. Rescue workers helping those stranded by the floods\n4. Cars and buildings submerged in water\n5. Emergency responders distributing aid and supplies to affected communities",
"en_article_excerpt": "Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Korean_floods",
"event_category": "disasters",
"event_name": "2020_korean_floods",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the cause and effects of the flooding, such as scenes of heavy rainfall, flooded areas, and rescue efforts. These events are likely to be visualized in a video documenting the floods and their impact on the region.\n\nEVENTS:\n1. Heavy rains pouring down in the southern parts of the Korean Peninsula\n2. Rivers overflowing and flooding nearby cities and towns\n3. People evacuating their homes and seeking higher ground\n4. Rescue teams navigating boats through flooded streets to reach stranded residents\n5. Cars and buildings submerged in water with debris scattered around",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the consequences of flooding and heavy rainfall, such as damage to infrastructure, evacuation efforts, and scenes of flooding. These events are likely to be visualized in a video capturing the impact of the floods on the region.\n\nEVENTS:\n1. People evacuating flooded homes and buildings\n2. Cars and buildings submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Debris and wreckage from destroyed buildings and infrastructure\n5. Residents clearing mud and water from their homes and streets",
"video_URL": "http://youtube.com/watch?v=mtt7-wXFwxI",
"video_description": "(서울=뉴스1) 김연수 기자 = 지난 1일부터 전국을 강타하고 있는 집중호우로 전국에서 피해가 속출하고 있습니다. 특히 큰 비가 내린 남부 지방을 중심으로 지난 7일 이후 1만1717건의 시설피해가 집계됐다. 섬진강댐 하류 제방이 붕괴돼 주민들이 긴급대피했고 화동군 화개장터가 32년 만에 침수됐습니다. 도로와 교량, 주택 등 1만7879건의 시설피해가 접수된 가운데 제5호 태풍 '장미'가 북상하면서 피해 규모가 더욱 커질 것으로 전망되는데요. 수마가 할퀴고 간 자리 영상으로 확인해보세요. #장마 #홍수피해 #홍수 #물폭탄",
"video_id": "mtt7-wXFwxI"
}
| 2
|
[
"The video shows a flooded river with muddy water, partially submerging some trees and vegetation. Several people are walking along a wet, paved path on the right side, using umbrellas to shield themselves from the rain. The background features tall buildings, suggesting an urban setting. The sky is overcast, and the overall atmosphere appears gloomy due to the weather.",
"The video displays a TV channel logo with the text \"뉴스TV\" in the center. Additional Korean text is visible at the bottom of the screen, reading \"영상 | 전남소방본부 등\" and \"제작 | 김연수.\" This suggests a transition to a news segment, possibly related to the previous scene, providing updates or information about the flooded river and the affected area. The text indicates involvement from the Jeonnam Fire Department and credits the producer, Kim Yeon-soo."
] |
mtt7-wXFwxI
|
The video depicts a flooded urban area, showing a river with muddy water submerging trees and vegetation, with people walking along a nearby path under umbrellas in the rain. The scene then transitions to a news segment on "뉴스TV", indicating a shift in focus to reporting and updates, likely related to the flood, involving the Jeonnam Fire Department, and produced by Kim Yeon-soo.
|
Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.
|
[
"Heavy rains and floods in the southern Korean Peninsula during summer 2020",
"Heavy rains pouring down in southern South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North and South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during the summer floods of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during heavy rains in summer 2020",
"Rescue teams navigating boats through flooded streets to reach stranded residents during the summer floods of 2020 in North and South Korea",
"Rescue teams navigating boats through flooded streets to reach stranded residents in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after floods in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after heavy rains in North and South Korea during the summer of 2020"
] |
[
"People evacuating flooded homes and buildings in the Korean Peninsula during the summer rainy season of 2020",
"People evacuating flooded homes and buildings in the Korean Peninsula during summer 2020 heavy rains",
"Cars and buildings submerged in floodwater in North Korea and South Korea during the summer floods of 2020",
"Cars and buildings submerged in floodwater during heavy rains in the Korean Peninsula in summer 2020",
"Emergency responders rescuing people from flooded areas in North Korea and South Korea during the summer rainy season of 2020",
"Emergency responders rescuing people from flooded areas in North and South Korea during heavy rains in the summer of 2020",
"Debris and wreckage from destroyed buildings and infrastructure due to floods in North and South Korea during the summer 2020 rainy season",
"Debris and wreckage from destroyed buildings and infrastructure in North Korea, South Korea, and the Korean Peninsula after heavy rains during the summer rainy season of June-August 2020",
"Residents clearing mud and water from their homes and streets after floods in the Korean Peninsula during the summer 2020 rainy season",
"Residents clearing mud and water from their homes and streets in North and South Korea after heavy rains during the summer rainy season of 2020"
] |
[
"Floodwaters inundating homes and buildings in southern Korea, particularly in South Korea, during the summer rainy season of 2020",
"Floodwaters inundating homes and buildings in southern Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North and South Korea during heavy rains in summer 2020",
"Rescue workers helping those stranded by the floods in North Korea and South Korea during the summer rainy season of 2020",
"Rescue workers helping those stranded by floods in the Korean Peninsula during the summer rainy season of 2020",
"Cars and buildings submerged in water during floods in North and South Korea, Korean Peninsula, Summer 2020",
"Cars and buildings submerged in water in North and South Korea during heavy rains in summer 2020",
"Emergency responders distributing aid and supplies to communities affected by floods in North Korea and South Korea during the summer rainy season of June to August 2020",
"Emergency responders distributing aid and supplies to affected communities in North and South Korea during heavy rains in the summer of 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2020%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact of floods and heavy rains in Korea, such as scenes of flooding, damage, and rescue efforts, as these are likely to be visualized in a video about the event. The extracted events should be specific to the region and the time of year, taking into account the regional rainy season and the areas most affected by the floods.\n\nEVENTS:\n1. Floodwaters inundating homes and buildings in southern Korea\n2. People evacuating flooded areas by boat\n3. Rescue workers helping those stranded by the floods\n4. Cars and buildings submerged in water\n5. Emergency responders distributing aid and supplies to affected communities",
"en_article_excerpt": "Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Korean_floods",
"event_category": "disasters",
"event_name": "2020_korean_floods",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the cause and effects of the flooding, such as scenes of heavy rainfall, flooded areas, and rescue efforts. These events are likely to be visualized in a video documenting the floods and their impact on the region.\n\nEVENTS:\n1. Heavy rains pouring down in the southern parts of the Korean Peninsula\n2. Rivers overflowing and flooding nearby cities and towns\n3. People evacuating their homes and seeking higher ground\n4. Rescue teams navigating boats through flooded streets to reach stranded residents\n5. Cars and buildings submerged in water with debris scattered around",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the consequences of flooding and heavy rainfall, such as damage to infrastructure, evacuation efforts, and scenes of flooding. These events are likely to be visualized in a video capturing the impact of the floods on the region.\n\nEVENTS:\n1. People evacuating flooded homes and buildings\n2. Cars and buildings submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Debris and wreckage from destroyed buildings and infrastructure\n5. Residents clearing mud and water from their homes and streets",
"video_URL": "http://youtube.com/watch?v=5j_NI2eL3HA",
"video_description": "북한에서 집중 호우로 일어난 홍수에 22명이 숨지고 4명이 실종됐습니다. 국제적십자사연맹은 미국의소리 방송에 보낸 이메일에서 \"북한 조선 적십자회와 국가 비상 재해 위원회에 따르면 심각한 홍수로 인해 22명이 사망하고 4명이 실종됐다\"고 밝혔습니다. https://imnews.imbc.com/replay/2020/nwtoday/article/5873504_32531.html #북한 #집중호우 #홍수",
"video_id": "5j_NI2eL3HA"
}
| 2
|
[
"The image shows a bulldozer moving through a flooded area with water reaching up to its tires. The bulldozer is carrying a load of rocks in its bucket. The environment around the bulldozer appears to be a rural or semi-rural area with trees and grass visible. The sky is overcast, suggesting recent or ongoing rain. Text in Korean at the bottom of the image mentions \"국제적참여연맹 '북, 홍수로 22명 사망·4명 실종'\" which translates to \"International Federation of Human Rights 'North Korea, 22 people dead and 4 missing due to flooding'\".",
"The current frame depicts a bulldozer continuing its movement through the floodwaters, still carrying a load of rocks. The water level remains high, reaching up to the bulldozer's tires, indicating that the flooding situation is ongoing. The surrounding environment is consistent with the previous frame, showing a rural or semi-rural setting with trees and grass visible. The sky is still overcast, reinforcing the conditions of recent or ongoing rain. The text at the bottom of the image, \"국제적참여연맹 '북, 홍수로 22명 사망·4명 실종'\" (International Federation of Human Rights 'North Korea, 22 people dead and 4 missing due to flooding'), remains present, emphasizing the severity of the flooding disaster."
] |
5j_NI2eL3HA
|
A bulldozer is navigating through a flooded rural or semi-rural area in North Korea, carrying a load of rocks in its bucket. The flooding is severe, with water reaching up to the bulldozer's tires, and is a result of recent or ongoing rain. The situation is dire, with reports of 22 people dead and 4 missing due to the flooding, as indicated by text from the International Federation of Human Rights. The bulldozer's actions suggest efforts to mitigate the flood's impact or assist in recovery, highlighting the ongoing response to the natural disaster.
|
Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.
|
[
"Heavy rains and floods in the southern Korean Peninsula during summer 2020",
"Heavy rains pouring down in southern South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North and South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during the summer floods of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during heavy rains in summer 2020",
"Rescue teams navigating boats through flooded streets to reach stranded residents during the summer floods of 2020 in North and South Korea",
"Rescue teams navigating boats through flooded streets to reach stranded residents in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after floods in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after heavy rains in North and South Korea during the summer of 2020"
] |
[
"People evacuating flooded homes and buildings in the Korean Peninsula during the summer rainy season of 2020",
"People evacuating flooded homes and buildings in the Korean Peninsula during summer 2020 heavy rains",
"Cars and buildings submerged in floodwater in North Korea and South Korea during the summer floods of 2020",
"Cars and buildings submerged in floodwater during heavy rains in the Korean Peninsula in summer 2020",
"Emergency responders rescuing people from flooded areas in North Korea and South Korea during the summer rainy season of 2020",
"Emergency responders rescuing people from flooded areas in North and South Korea during heavy rains in the summer of 2020",
"Debris and wreckage from destroyed buildings and infrastructure due to floods in North and South Korea during the summer 2020 rainy season",
"Debris and wreckage from destroyed buildings and infrastructure in North Korea, South Korea, and the Korean Peninsula after heavy rains during the summer rainy season of June-August 2020",
"Residents clearing mud and water from their homes and streets after floods in the Korean Peninsula during the summer 2020 rainy season",
"Residents clearing mud and water from their homes and streets in North and South Korea after heavy rains during the summer rainy season of 2020"
] |
[
"Floodwaters inundating homes and buildings in southern Korea, particularly in South Korea, during the summer rainy season of 2020",
"Floodwaters inundating homes and buildings in southern Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North and South Korea during heavy rains in summer 2020",
"Rescue workers helping those stranded by the floods in North Korea and South Korea during the summer rainy season of 2020",
"Rescue workers helping those stranded by floods in the Korean Peninsula during the summer rainy season of 2020",
"Cars and buildings submerged in water during floods in North and South Korea, Korean Peninsula, Summer 2020",
"Cars and buildings submerged in water in North and South Korea during heavy rains in summer 2020",
"Emergency responders distributing aid and supplies to communities affected by floods in North Korea and South Korea during the summer rainy season of June to August 2020",
"Emergency responders distributing aid and supplies to affected communities in North and South Korea during heavy rains in the summer of 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2020%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact of floods and heavy rains in Korea, such as scenes of flooding, damage, and rescue efforts, as these are likely to be visualized in a video about the event. The extracted events should be specific to the region and the time of year, taking into account the regional rainy season and the areas most affected by the floods.\n\nEVENTS:\n1. Floodwaters inundating homes and buildings in southern Korea\n2. People evacuating flooded areas by boat\n3. Rescue workers helping those stranded by the floods\n4. Cars and buildings submerged in water\n5. Emergency responders distributing aid and supplies to affected communities",
"en_article_excerpt": "Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Korean_floods",
"event_category": "disasters",
"event_name": "2020_korean_floods",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the cause and effects of the flooding, such as scenes of heavy rainfall, flooded areas, and rescue efforts. These events are likely to be visualized in a video documenting the floods and their impact on the region.\n\nEVENTS:\n1. Heavy rains pouring down in the southern parts of the Korean Peninsula\n2. Rivers overflowing and flooding nearby cities and towns\n3. People evacuating their homes and seeking higher ground\n4. Rescue teams navigating boats through flooded streets to reach stranded residents\n5. Cars and buildings submerged in water with debris scattered around",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the consequences of flooding and heavy rainfall, such as damage to infrastructure, evacuation efforts, and scenes of flooding. These events are likely to be visualized in a video capturing the impact of the floods on the region.\n\nEVENTS:\n1. People evacuating flooded homes and buildings\n2. Cars and buildings submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Debris and wreckage from destroyed buildings and infrastructure\n5. Residents clearing mud and water from their homes and streets",
"video_URL": "http://youtube.com/watch?v=nR08Eart4vo",
"video_description": "댐 관리를 담당하는 한국수자원공사가 이번 수해와 관련해 댐 수위 조절에는 문제가 없었다고 밝혔습니다. 수자원공사는 댐관리규정 등에 따라 홍수기 기상변화와 댐 상·하류 상황, 댐 안전과 민원 등을 고려해 홍수 대응이 가능하도록 댐 수위를 관리했다고 설명했습니다. 섬진강댐은 집중호우 전부터 홍수기제한수위보다 3m 낮게 유지했고, 용담댐이나 합천댐도 제한 수위를 지켜 전혀 이상이 없었다고 강조했습니다. 다만, 유례없는 최장 기간의 장마로 제방이 무너지고 물이 넘치는 등 복합적인 요인 탓에 홍수 피해가 난 것으로 보인다고 덧붙였습니다. 이에 관련 기관과 함께 원인 조사를 한 뒤 대책 수립에 적극 협조하고, 복구 지원에 노력하겠다고 전했습니다. ※ '당신의 제보가 뉴스가 됩니다' YTN은 여러분의 소중한 제보를 기다립니다. [카카오톡] YTN을 검색해 채널 추가 [전화] 02-398-8585 [메일] social@ytn.co.kr [온라인 제보] www.ytn.co.kr ▶ 기사 원문 : https://www.ytn.co.kr/_ln/0103_202008121704378843 ▶ 제보 안내 : http://goo.gl/gEvsAL, 모바일앱, social@ytn.co.kr, #2424 ▣ YTN 유튜브 채널 구독 : http://goo.gl/Ytb5SZ ⓒ YTN & YTN PLUS 무단 전재 및 재배포금지",
"video_id": "nR08Eart4vo"
}
| 2
|
[
"The image shows an aerial view of a flooded area with extensive water coverage over fields and buildings. The water appears muddy and is inundating the landscape, affecting various structures. The text in the image is in Korean, mentioning a flood caused by heavy rainfall and resulting in damage. There are no visible people or animals, and the overall setting suggests a severe natural disaster affecting the region.",
"In the current frame, a group of workers wearing orange safety vests and hard hats are actively engaged in cleanup efforts amidst a scene of debris and damaged structures. They are seen removing and clearing the wreckage, which includes twisted metal and collapsed roofing materials, likely from the flood damage. The workers appear focused on their task, with some bending over to pick up debris and others using tools to aid in the cleanup. The environment is littered with the aftermath of the flood, indicating a post-disaster recovery operation."
] |
nR08Eart4vo
|
A severe flood, caused by heavy rainfall, has devastated a region, inundating fields and buildings with muddy water. The disaster has resulted in significant damage to structures, prompting a cleanup operation. A group of workers, dressed in orange safety vests and hard hats, are actively engaged in removing debris and wreckage, including twisted metal and collapsed roofing materials, in an effort to recover from the flood's aftermath.
|
Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.
|
[
"Heavy rains and floods in the southern Korean Peninsula during summer 2020",
"Heavy rains pouring down in southern South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North and South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during the summer floods of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during heavy rains in summer 2020",
"Rescue teams navigating boats through flooded streets to reach stranded residents during the summer floods of 2020 in North and South Korea",
"Rescue teams navigating boats through flooded streets to reach stranded residents in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after floods in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after heavy rains in North and South Korea during the summer of 2020"
] |
[
"People evacuating flooded homes and buildings in the Korean Peninsula during the summer rainy season of 2020",
"People evacuating flooded homes and buildings in the Korean Peninsula during summer 2020 heavy rains",
"Cars and buildings submerged in floodwater in North Korea and South Korea during the summer floods of 2020",
"Cars and buildings submerged in floodwater during heavy rains in the Korean Peninsula in summer 2020",
"Emergency responders rescuing people from flooded areas in North Korea and South Korea during the summer rainy season of 2020",
"Emergency responders rescuing people from flooded areas in North and South Korea during heavy rains in the summer of 2020",
"Debris and wreckage from destroyed buildings and infrastructure due to floods in North and South Korea during the summer 2020 rainy season",
"Debris and wreckage from destroyed buildings and infrastructure in North Korea, South Korea, and the Korean Peninsula after heavy rains during the summer rainy season of June-August 2020",
"Residents clearing mud and water from their homes and streets after floods in the Korean Peninsula during the summer 2020 rainy season",
"Residents clearing mud and water from their homes and streets in North and South Korea after heavy rains during the summer rainy season of 2020"
] |
[
"Floodwaters inundating homes and buildings in southern Korea, particularly in South Korea, during the summer rainy season of 2020",
"Floodwaters inundating homes and buildings in southern Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North and South Korea during heavy rains in summer 2020",
"Rescue workers helping those stranded by the floods in North Korea and South Korea during the summer rainy season of 2020",
"Rescue workers helping those stranded by floods in the Korean Peninsula during the summer rainy season of 2020",
"Cars and buildings submerged in water during floods in North and South Korea, Korean Peninsula, Summer 2020",
"Cars and buildings submerged in water in North and South Korea during heavy rains in summer 2020",
"Emergency responders distributing aid and supplies to communities affected by floods in North Korea and South Korea during the summer rainy season of June to August 2020",
"Emergency responders distributing aid and supplies to affected communities in North and South Korea during heavy rains in the summer of 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2020%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact of floods and heavy rains in Korea, such as scenes of flooding, damage, and rescue efforts, as these are likely to be visualized in a video about the event. The extracted events should be specific to the region and the time of year, taking into account the regional rainy season and the areas most affected by the floods.\n\nEVENTS:\n1. Floodwaters inundating homes and buildings in southern Korea\n2. People evacuating flooded areas by boat\n3. Rescue workers helping those stranded by the floods\n4. Cars and buildings submerged in water\n5. Emergency responders distributing aid and supplies to affected communities",
"en_article_excerpt": "Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Korean_floods",
"event_category": "disasters",
"event_name": "2020_korean_floods",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the cause and effects of the flooding, such as scenes of heavy rainfall, flooded areas, and rescue efforts. These events are likely to be visualized in a video documenting the floods and their impact on the region.\n\nEVENTS:\n1. Heavy rains pouring down in the southern parts of the Korean Peninsula\n2. Rivers overflowing and flooding nearby cities and towns\n3. People evacuating their homes and seeking higher ground\n4. Rescue teams navigating boats through flooded streets to reach stranded residents\n5. Cars and buildings submerged in water with debris scattered around",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the consequences of flooding and heavy rainfall, such as damage to infrastructure, evacuation efforts, and scenes of flooding. These events are likely to be visualized in a video capturing the impact of the floods on the region.\n\nEVENTS:\n1. People evacuating flooded homes and buildings\n2. Cars and buildings submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Debris and wreckage from destroyed buildings and infrastructure\n5. Residents clearing mud and water from their homes and streets",
"video_URL": "http://youtube.com/watch?v=GwY9HYVEQIk",
"video_description": "전국 하천 홍수특보 전부 해제…상수도 93곳 피해 중부지방 집중호우가 소강상태에 접어든 가운데 전국 하천 주요 지점의 홍수특보가 전부 해제됐습니다. 환경부는 낙동강이 흐르는 경남 밀양시 삼랑진교에 내려졌던 홍수주의보가 오늘(12일) 오후 5시30분 해제된 것을 끝으로 전국 하천 주요지점에 내려진 홍수특보가 모두 해제됐다고 밝혔습니다. 한강과 임진강 비룡대교·영평교, 왕숙천 진관교 등지에 발령됐던 홍수주의보와 섬진강 하동군 읍내리 지점의 홍수주의보는 각각 지난 11일 오후 6시와 오후 5시 해제됐습니다. 이번 호우로 27개 시·군의 상수도 시설 93곳에서 피해가 발생했습니다. 연합뉴스TV 기사문의 및 제보 : 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": "GwY9HYVEQIk"
}
| 2
|
[
"The image shows a river with high water levels flooding over the bridge supports. The text indicates flooding in Hachon, South Korea, with 93 households affected and significant damage to infrastructure.",
"The image shows a flooded basement with water reaching up to the pumps and pipes, causing significant damage. The text indicates flooding in Hachon, South Korea, with 95 households affected and severe damage to infrastructure."
] |
GwY9HYVEQIk
|
A severe flood is affecting the area of Hachon, South Korea, with water levels overflowing the river and causing significant damage to infrastructure, including homes and bridges. The flood has impacted at least 95 households, with water also flooding basements and reaching critical equipment such as pumps and pipes, resulting in substantial destruction.
|
Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.
|
[
"Heavy rains and floods in the southern Korean Peninsula during summer 2020",
"Heavy rains pouring down in southern South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North and South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during the summer floods of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during heavy rains in summer 2020",
"Rescue teams navigating boats through flooded streets to reach stranded residents during the summer floods of 2020 in North and South Korea",
"Rescue teams navigating boats through flooded streets to reach stranded residents in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after floods in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after heavy rains in North and South Korea during the summer of 2020"
] |
[
"People evacuating flooded homes and buildings in the Korean Peninsula during the summer rainy season of 2020",
"People evacuating flooded homes and buildings in the Korean Peninsula during summer 2020 heavy rains",
"Cars and buildings submerged in floodwater in North Korea and South Korea during the summer floods of 2020",
"Cars and buildings submerged in floodwater during heavy rains in the Korean Peninsula in summer 2020",
"Emergency responders rescuing people from flooded areas in North Korea and South Korea during the summer rainy season of 2020",
"Emergency responders rescuing people from flooded areas in North and South Korea during heavy rains in the summer of 2020",
"Debris and wreckage from destroyed buildings and infrastructure due to floods in North and South Korea during the summer 2020 rainy season",
"Debris and wreckage from destroyed buildings and infrastructure in North Korea, South Korea, and the Korean Peninsula after heavy rains during the summer rainy season of June-August 2020",
"Residents clearing mud and water from their homes and streets after floods in the Korean Peninsula during the summer 2020 rainy season",
"Residents clearing mud and water from their homes and streets in North and South Korea after heavy rains during the summer rainy season of 2020"
] |
[
"Floodwaters inundating homes and buildings in southern Korea, particularly in South Korea, during the summer rainy season of 2020",
"Floodwaters inundating homes and buildings in southern Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North and South Korea during heavy rains in summer 2020",
"Rescue workers helping those stranded by the floods in North Korea and South Korea during the summer rainy season of 2020",
"Rescue workers helping those stranded by floods in the Korean Peninsula during the summer rainy season of 2020",
"Cars and buildings submerged in water during floods in North and South Korea, Korean Peninsula, Summer 2020",
"Cars and buildings submerged in water in North and South Korea during heavy rains in summer 2020",
"Emergency responders distributing aid and supplies to communities affected by floods in North Korea and South Korea during the summer rainy season of June to August 2020",
"Emergency responders distributing aid and supplies to affected communities in North and South Korea during heavy rains in the summer of 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2020%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact of floods and heavy rains in Korea, such as scenes of flooding, damage, and rescue efforts, as these are likely to be visualized in a video about the event. The extracted events should be specific to the region and the time of year, taking into account the regional rainy season and the areas most affected by the floods.\n\nEVENTS:\n1. Floodwaters inundating homes and buildings in southern Korea\n2. People evacuating flooded areas by boat\n3. Rescue workers helping those stranded by the floods\n4. Cars and buildings submerged in water\n5. Emergency responders distributing aid and supplies to affected communities",
"en_article_excerpt": "Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Korean_floods",
"event_category": "disasters",
"event_name": "2020_korean_floods",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the cause and effects of the flooding, such as scenes of heavy rainfall, flooded areas, and rescue efforts. These events are likely to be visualized in a video documenting the floods and their impact on the region.\n\nEVENTS:\n1. Heavy rains pouring down in the southern parts of the Korean Peninsula\n2. Rivers overflowing and flooding nearby cities and towns\n3. People evacuating their homes and seeking higher ground\n4. Rescue teams navigating boats through flooded streets to reach stranded residents\n5. Cars and buildings submerged in water with debris scattered around",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the consequences of flooding and heavy rainfall, such as damage to infrastructure, evacuation efforts, and scenes of flooding. These events are likely to be visualized in a video capturing the impact of the floods on the region.\n\nEVENTS:\n1. People evacuating flooded homes and buildings\n2. Cars and buildings submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Debris and wreckage from destroyed buildings and infrastructure\n5. Residents clearing mud and water from their homes and streets",
"video_URL": "http://youtube.com/watch?v=FG82wp__uZ8",
"video_description": "#홍수 #성금 ●BTN불교TV 유튜브 구독하기 https://bit.ly/3k5nt10 (링크 누르고 구독 버튼 클릭!) ●BTN불교TV는? BTN불교TV(주)는 25년의 시간 동안 부처님의 법음을 널리 홍포해온 한국을 대표하는 불교방송국입니다. 불자님들의 소중한 후원금과 광고수입은 더 나은 방송 포교와 불교문화 진흥, 다양한 컨텐츠를 제작하는데 사용되고 있습니다. BTN은 앞으로도 방송 포교사의 소임을 다하겠습니다. ●BTN불교TV 채널번호 안내 IPTV: KTolleh:233번, SK B TV:305번, LGU+TV:275번(전국공통) SKYLIFE: 181번(전국공통) 지역케이블: 케이블 가입자의 경우 BTN채널번호가 지역별로 달라서 아래 주소를 클릭하셔서 확인하시면 됩니다 https://blog.naver.com/btnii/221391809765 ●다양한 경로로 BTN불교TV를 만나보세요! 홈페이지:http://www.btn.co.kr/index.asp 유튜브:https://www.youtube.com/channel/UCOozqNhXDcb6gg6oaU7uImA?view_as=subscriber 페이스북:https://www.facebook.com/BTNkorea/ 블로그:https://blog.naver.com/btnii 카카오스토리:https://story.kakao.com/ch/btntv",
"video_id": "FG82wp__uZ8"
}
| 2
|
[
"The frame shows a flooded room with water covering the floor. There are several golden Buddha statues on a raised platform at the back. In front of the statues, there are traditional items and a broom leaning against the platform. Text in Korean is displayed in the center of the image.",
"The flooded room remains filled with water, submerging the floor and partially covering the golden Buddha statues on a raised platform. The traditional items and broom are still present in front of the statues. Korean text appears prominently in the center of the image, likely continuing the narrative from the previous frame."
] |
FG82wp__uZ8
|
A flooded room, apparently a place of worship or cultural significance, is shown with water covering the floor and partially submerging golden Buddha statues on a raised platform. Traditional items and a broom are positioned in front of the statues. The presence of Korean text in both frames suggests the video is either in Korean or intended for a Korean-speaking audience, and may be providing context or narration about the flooding or the significance of the room and its contents.
|
Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.
|
[
"Heavy rains and floods in the southern Korean Peninsula during summer 2020",
"Heavy rains pouring down in southern South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North and South Korea during the summer of 2020",
"Rivers overflowing and flooding nearby cities and towns in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during the summer floods of 2020",
"People evacuating their homes and seeking higher ground in North and South Korea during heavy rains in summer 2020",
"Rescue teams navigating boats through flooded streets to reach stranded residents during the summer floods of 2020 in North and South Korea",
"Rescue teams navigating boats through flooded streets to reach stranded residents in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after floods in North and South Korea during the summer rainy season of 2020",
"Cars and buildings submerged in water with debris scattered around after heavy rains in North and South Korea during the summer of 2020"
] |
[
"People evacuating flooded homes and buildings in the Korean Peninsula during the summer rainy season of 2020",
"People evacuating flooded homes and buildings in the Korean Peninsula during summer 2020 heavy rains",
"Cars and buildings submerged in floodwater in North Korea and South Korea during the summer floods of 2020",
"Cars and buildings submerged in floodwater during heavy rains in the Korean Peninsula in summer 2020",
"Emergency responders rescuing people from flooded areas in North Korea and South Korea during the summer rainy season of 2020",
"Emergency responders rescuing people from flooded areas in North and South Korea during heavy rains in the summer of 2020",
"Debris and wreckage from destroyed buildings and infrastructure due to floods in North and South Korea during the summer 2020 rainy season",
"Debris and wreckage from destroyed buildings and infrastructure in North Korea, South Korea, and the Korean Peninsula after heavy rains during the summer rainy season of June-August 2020",
"Residents clearing mud and water from their homes and streets after floods in the Korean Peninsula during the summer 2020 rainy season",
"Residents clearing mud and water from their homes and streets in North and South Korea after heavy rains during the summer rainy season of 2020"
] |
[
"Floodwaters inundating homes and buildings in southern Korea, particularly in South Korea, during the summer rainy season of 2020",
"Floodwaters inundating homes and buildings in southern Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North Korea and South Korea during the summer rainy season of 2020",
"People evacuating flooded areas by boat in North and South Korea during heavy rains in summer 2020",
"Rescue workers helping those stranded by the floods in North Korea and South Korea during the summer rainy season of 2020",
"Rescue workers helping those stranded by floods in the Korean Peninsula during the summer rainy season of 2020",
"Cars and buildings submerged in water during floods in North and South Korea, Korean Peninsula, Summer 2020",
"Cars and buildings submerged in water in North and South Korea during heavy rains in summer 2020",
"Emergency responders distributing aid and supplies to communities affected by floods in North Korea and South Korea during the summer rainy season of June to August 2020",
"Emergency responders distributing aid and supplies to affected communities in North and South Korea during heavy rains in the summer of 2020"
] |
{
"article_url": "https://ko.wikipedia.org/wiki/2020%EB%85%84_%ED%95%9C%EA%B5%AD_%EC%A7%91%EC%A4%91%ED%98%B8%EC%9A%B0",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"during_raw_generation": "EXPLANATION: It makes sense to extract events that are directly related to the impact of floods and heavy rains in Korea, such as scenes of flooding, damage, and rescue efforts, as these are likely to be visualized in a video about the event. The extracted events should be specific to the region and the time of year, taking into account the regional rainy season and the areas most affected by the floods.\n\nEVENTS:\n1. Floodwaters inundating homes and buildings in southern Korea\n2. People evacuating flooded areas by boat\n3. Rescue workers helping those stranded by the floods\n4. Cars and buildings submerged in water\n5. Emergency responders distributing aid and supplies to affected communities",
"en_article_excerpt": "Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.",
"en_article_url": "https://en.wikipedia.org/wiki/2020_Korean_floods",
"event_category": "disasters",
"event_name": "2020_korean_floods",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"prequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the cause and effects of the flooding, such as scenes of heavy rainfall, flooded areas, and rescue efforts. These events are likely to be visualized in a video documenting the floods and their impact on the region.\n\nEVENTS:\n1. Heavy rains pouring down in the southern parts of the Korean Peninsula\n2. Rivers overflowing and flooding nearby cities and towns\n3. People evacuating their homes and seeking higher ground\n4. Rescue teams navigating boats through flooded streets to reach stranded residents\n5. Cars and buildings submerged in water with debris scattered around",
"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: Between June and August 2020, floods severely impacted large areas of both North and South Korea due to heavy rains of the regional rainy season, primarily in the far southern parts of the Korean Peninsula.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"sequel_raw_generation": "EXPLANATION: Given the query about floods in North and South Korea due to heavy rains, it makes sense to extract events that are directly related to the consequences of flooding and heavy rainfall, such as damage to infrastructure, evacuation efforts, and scenes of flooding. These events are likely to be visualized in a video capturing the impact of the floods on the region.\n\nEVENTS:\n1. People evacuating flooded homes and buildings\n2. Cars and buildings submerged in floodwater\n3. Emergency responders rescuing people from flooded areas\n4. Debris and wreckage from destroyed buildings and infrastructure\n5. Residents clearing mud and water from their homes and streets",
"video_URL": "http://twitter.com/i/status/1291976724456992776",
"video_description": "섬진강이 난리네요 ㅠ#섬진강#유등면#섬진강 홍수",
"video_id": "1291976724456992776"
}
| 2
|
[
"The current frame depicts a flooded area with a large blue metal roof structure partially submerged in muddy water. The water level reaches halfway up the structure's pillars, indicating significant flooding. There are trees and debris scattered around, suggesting the impact of heavy rainfall or a flood.",
"The scene continues to show a flooded area with a large blue metal roof structure. The water level remains high, partially submerging the structure's pillars. The muddy water flows rapidly, carrying debris and creating a turbulent environment. The impact of heavy rainfall or a flood is evident from the scattered trees and debris, highlighting the severity of the flooding situation."
] |
1291976724456992776
|
A severe flood is depicted, with a large blue metal roof structure partially submerged in muddy water. The water level is high, reaching halfway up the structure's pillars, and is flowing rapidly, carrying debris and creating a turbulent environment. The surrounding area is scattered with trees and debris, indicating the significant impact of heavy rainfall or flooding.
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.