task
stringclasses 1
value | source
stringclasses 1
value | video
stringlengths 37
38
| duration
int64 120
150
| tgt
listlengths 1
24
| conversations
listlengths 2
2
|
|---|---|---|---|---|---|
tvg
|
qvhighlights
|
qvh/videos/dESCAL2IP2o_210.0_360.0.mp4
| 150 |
[
[
46,
60
],
[
74,
94
],
[
96,
104
],
[
114,
124
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A woman with red hair and and pink top sings during a concert' in the video, and output the start and end timestamps in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/dESCAL2IP2o_360.0_510.0.mp4
| 150 |
[
[
30,
64
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A girl group preforms on stage together under purple light', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/dESCAL2IP2o_60.0_210.0.mp4
| 150 |
[
[
10,
48
],
[
98,
144
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'Stage performance of girls singing and dancing'.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/dESCAL2IP2o_510.0_660.0.mp4
| 150 |
[
[
0,
6
],
[
8,
12
],
[
54,
80
],
[
90,
92
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'A fan holds up a \"Rose\" and \"Lisa\" sign during a BlackPink concert'.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/ZZvkUjrPsvo_210.0_360.0.mp4
| 150 |
[
[
104,
120
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'Waves are crashing against several boulders in the sand' and determine its start and end seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/ZZvkUjrPsvo_360.0_510.0.mp4
| 150 |
[
[
88,
124
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A woman rides in a car on a scenic drive from South Goa to North Goa' within the video using timestamps.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/ZZvkUjrPsvo_60.0_210.0.mp4
| 150 |
[
[
30,
106
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A girl is having fun at the beach' in the video, and output the start and end timestamps in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/jPe0V4TXdsg_360.0_510.0.mp4
| 150 |
[
[
100,
114
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Woman spins wheel while holding wheat', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/jPe0V4TXdsg_210.0_360.0.mp4
| 150 |
[
[
120,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A couple meeting locals and the guy trying bow and arrow game' within the video using timestamps.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/jPe0V4TXdsg_60.0_210.0.mp4
| 150 |
[
[
10,
44
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'A woman crossing a narrow unstable bridge made out of ropes and natural materials'.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/bC9m_id_Yds_60.0_210.0.mp4
| 150 |
[
[
114,
138
],
[
142,
150
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'A traveler describes the options for getting to Tokyo from Narita International Airport'.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/bC9m_id_Yds_360.0_510.0.mp4
| 150 |
[
[
70,
124
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A lady teaching a guy about using the chopsticks' in the video, and output the start and end timestamps in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/bC9m_id_Yds_210.0_360.0.mp4
| 150 |
[
[
10,
14
],
[
18,
24
],
[
88,
94
],
[
126,
136
],
[
144,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'The man is standing in the street and talking while wearing a pink collared shirt' within the video using timestamps.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/Aw_XvvepzYU_60.0_210.0.mp4
| 150 |
[
[
24,
40
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'a blonde lady discusses the weather in front of a prairie house background' is semantically aligned with a video moment, please give the start time and end time of the video moment.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/Aw_XvvepzYU_210.0_360.0.mp4
| 150 |
[
[
40,
76
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'News anchors are reporting from a circular white desk' within the video using timestamps.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/Aw_XvvepzYU_360.0_510.0.mp4
| 150 |
[
[
0,
20
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'Woman stands to the side of a pier'.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/c2zLFrMLktI_60.0_210.0.mp4
| 150 |
[
[
0,
20
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Guns parts are being displayed and a gun is being fired' is semantically aligned with a video moment, please give the start time and end time of the video moment.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/c2zLFrMLktI_210.0_360.0.mp4
| 150 |
[
[
14,
48
],
[
52,
100
],
[
104,
134
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'People in suits representing official offices are holding a large meeting' within the video using timestamps.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/c2zLFrMLktI_360.0_510.0.mp4
| 150 |
[
[
132,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Footage of bombed out buildings' within the video using timestamps.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/EN4zrb1mrrw_60.0_210.0.mp4
| 150 |
[
[
64,
100
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A woman is explaining the different spices and prepped vegetables that will go into her dish' within the video using timestamps.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/EN4zrb1mrrw_360.0_510.0.mp4
| 150 |
[
[
124,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A woman is cooking on a stove using a large metal pot with long handles' within the video using timestamps.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/EN4zrb1mrrw_210.0_360.0.mp4
| 150 |
[
[
0,
48
],
[
50,
82
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Vlogger makes foot in a bowl' within the video using timestamps.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/EN4zrb1mrrw_510.0_660.0.mp4
| 150 |
[
[
16,
60
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'Woman points out the different ingredients for frosting'.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/EN4zrb1mrrw_660.0_810.0.mp4
| 150 |
[
[
130,
150
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'a pot of food simmers on a stove', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/XnKUlE7OSjk_210.0_360.0.mp4
| 150 |
[
[
38,
64
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A man sits in the front trunk area of a car while wearing goggles and piloting a drone' and determine its start and end seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/XnKUlE7OSjk_60.0_210.0.mp4
| 150 |
[
[
10,
34
],
[
48,
50
],
[
52,
58
],
[
60,
64
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A mam test run a toy Monster truck on a snow ground' is semantically aligned with a video moment, please give the start time and end time of the video moment.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/XnKUlE7OSjk_360.0_510.0.mp4
| 150 |
[
[
126,
136
],
[
138,
150
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'Person is holding up a phone video next to the dog'.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/XnKUlE7OSjk_660.0_810.0.mp4
| 150 |
[
[
116,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A man is stretching in a periwinkle colored shirt and purple hat' in the video, and output the start and end timestamps in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/XnKUlE7OSjk_510.0_660.0.mp4
| 150 |
[
[
24,
52
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'Man puts a large box down in front of him then opens it' and determine its start and end seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/nMbV8hyH_sI_210.0_360.0.mp4
| 150 |
[
[
58,
80
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'Woman grabs and holds up a green tube'.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/nMbV8hyH_sI_360.0_510.0.mp4
| 150 |
[
[
134,
150
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A woman shows her boat ride and a dolphin swims near the boat' and determine its start and end seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/nMbV8hyH_sI_60.0_210.0.mp4
| 150 |
[
[
6,
10
],
[
22,
34
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'Koi are swimming in a pond'.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/GcA_FwTZ-xo_60.0_210.0.mp4
| 150 |
[
[
106,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A couple is riding on a boat with a red canopy on it down a river' in the video, and output the start and end timestamps in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/GcA_FwTZ-xo_210.0_360.0.mp4
| 150 |
[
[
86,
102
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'The man wearing a dark blue shirt carries a little boy while talking', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/GcA_FwTZ-xo_360.0_510.0.mp4
| 150 |
[
[
122,
138
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Group of people ride in a van at night' within the video using timestamps.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/Kg_bkoYFfEY_210.0_360.0.mp4
| 150 |
[
[
62,
86
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A man is sitting in front of a large neon green bean bag while holding up his phone', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/Kg_bkoYFfEY_60.0_210.0.mp4
| 150 |
[
[
0,
22
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Cyclists are waiting at the top of a tall stunt ramp before a competition' in the video, and output the start and end timestamps in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/Kg_bkoYFfEY_360.0_510.0.mp4
| 150 |
[
[
132,
150
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A man is interviewed by another man using a microphone' and determine its start and end seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/Kg_bkoYFfEY_510.0_660.0.mp4
| 132 |
[
[
118,
132
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'End of the video telling the viewers to subscribe' is semantically aligned with a video moment, please give the start time and end time of the video moment.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/_CZq9npzLJw_360.0_510.0.mp4
| 150 |
[
[
16,
36
],
[
46,
58
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A display of Indian foods on a plate' and determine its start and end seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/_CZq9npzLJw_60.0_210.0.mp4
| 150 |
[
[
24,
44
],
[
84,
108
],
[
132,
144
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A lady performing a Indian ritual' within the video using timestamps.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/_CZq9npzLJw_210.0_360.0.mp4
| 150 |
[
[
0,
50
],
[
56,
60
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A couple sits in bed feeding one another chocolates' is semantically aligned with a video moment, please give the start time and end time of the video moment.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/ZKqTFJOUg6k_360.0_510.0.mp4
| 150 |
[
[
18,
38
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A guy is pointing towards the menu' is semantically aligned with a video moment, please give the start time and end time of the video moment.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/ZKqTFJOUg6k_210.0_360.0.mp4
| 150 |
[
[
132,
144
],
[
146,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A woman speaks while sitting in an outdoor restaurant' within the video using timestamps.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/ZKqTFJOUg6k_60.0_210.0.mp4
| 150 |
[
[
94,
100
],
[
120,
128
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Man goes to a coffee shop and drinks some' in the video, and output the start and end timestamps in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/EiD10PvM-l0_360.0_510.0.mp4
| 150 |
[
[
44,
52
],
[
62,
66
],
[
72,
84
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Woman is rolling her suitcase behind her' in the video, and output the start and end timestamps in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/EiD10PvM-l0_210.0_360.0.mp4
| 150 |
[
[
122,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A flight attendant gets a delicious fruit drink before her long day at work' within the video using timestamps.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/EiD10PvM-l0_60.0_210.0.mp4
| 150 |
[
[
0,
120
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Woman monologues to the camera in a bathrobe' within the video using timestamps.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/EiD10PvM-l0_510.0_660.0.mp4
| 150 |
[
[
58,
78
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Vlogger points to different chocolates at a patisserie', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/KvRMS8z41ng_360.0_510.0.mp4
| 150 |
[
[
0,
8
],
[
60,
66
],
[
68,
72
],
[
82,
100
],
[
142,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Man with pink turban poses with different groups of people' within the video using timestamps.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/KvRMS8z41ng_60.0_210.0.mp4
| 150 |
[
[
42,
48
],
[
82,
88
],
[
96,
102
],
[
106,
110
],
[
132,
136
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'People pose for photos with man in pink turban' is semantically aligned with a video moment, please give the start time and end time of the video moment.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/KvRMS8z41ng_210.0_360.0.mp4
| 150 |
[
[
22,
52
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A man in a pink turban talks to a young girl in glasses' and determine its start and end seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/KvRMS8z41ng_510.0_660.0.mp4
| 150 |
[
[
128,
150
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Two men with the same matching color turbans are hanging out together in an outdoor area', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/KvRMS8z41ng_660.0_810.0.mp4
| 150 |
[
[
80,
96
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Men are sitting in tradition Indian garb against a red light which shines on their clothing', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/351G5E5XWXw_60.0_210.0.mp4
| 150 |
[
[
2,
18
],
[
20,
22
],
[
24,
34
],
[
36,
38
],
[
46,
54
],
[
60,
62
],
[
68,
70
],
[
72,
74
],
[
84,
90
],
[
102,
106
],
[
120,
136
],
[
138,
150
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Man shoots a vlog of him traveling', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/351G5E5XWXw_210.0_360.0.mp4
| 150 |
[
[
102,
126
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'The man goes through the drive thru at McDonalds and orders some food' is semantically aligned with a video moment, please give the start time and end time of the video moment.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/351G5E5XWXw_360.0_510.0.mp4
| 148 |
[
[
2,
16
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'A black and yellow SUV pulls up to a hotel's porte-cochère'.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/VCeWr8OFuEs_60.0_210.0.mp4
| 150 |
[
[
0,
8
],
[
30,
36
],
[
46,
52
],
[
68,
76
],
[
86,
96
],
[
100,
104
],
[
118,
124
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A family is shown throughout time' in the video, and output the start and end timestamps in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/NnL8Xh7iSxs_60.0_210.0.mp4
| 150 |
[
[
6,
12
],
[
14,
16
],
[
18,
26
],
[
30,
48
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'Man is working under his RV' and determine its start and end seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/NnL8Xh7iSxs_210.0_360.0.mp4
| 150 |
[
[
98,
126
],
[
140,
142
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'Man with a red cap cleans a rv'.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/NnL8Xh7iSxs_360.0_510.0.mp4
| 150 |
[
[
118,
150
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A man examines his vehicle and cleans it using a small tool', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/NnL8Xh7iSxs_510.0_660.0.mp4
| 150 |
[
[
86,
114
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Man in baseball cap stands under his rv' in the video, and output the start and end timestamps in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/21cCX0V9_lw_210.0_360.0.mp4
| 150 |
[
[
0,
14
],
[
26,
42
],
[
74,
86
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A woman putting on makeup in front of the camera', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/21cCX0V9_lw_60.0_210.0.mp4
| 150 |
[
[
84,
90
],
[
104,
112
],
[
142,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Teen girl does her skincare routine' within the video using timestamps.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/21cCX0V9_lw_360.0_510.0.mp4
| 150 |
[
[
28,
48
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A girl in a green shirt is in the kitchen with her roommate in black' in the video, and output the start and end timestamps in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/VCpdnbPUauA_60.0_210.0.mp4
| 150 |
[
[
20,
60
],
[
114,
118
],
[
124,
130
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A man is driving the car while talking to the camera' and determine its start and end seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/VCpdnbPUauA_360.0_510.0.mp4
| 150 |
[
[
90,
98
],
[
102,
116
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Man in white hat walks around outside' is semantically aligned with a video moment, please give the start time and end time of the video moment.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/VCpdnbPUauA_210.0_360.0.mp4
| 150 |
[
[
78,
92
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Man has a red bag next to him in the car' within the video using timestamps.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/M1kwtgh8qQU_360.0_510.0.mp4
| 150 |
[
[
132,
146
],
[
148,
150
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'Vlogger messes with a iPad'.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/M1kwtgh8qQU_60.0_210.0.mp4
| 150 |
[
[
0,
40
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Woman puts together a breakfast bowl and eats it', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/M1kwtgh8qQU_210.0_360.0.mp4
| 150 |
[
[
42,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Girl making some yummy Chinese food' in the video, and output the start and end timestamps in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/M1kwtgh8qQU_510.0_660.0.mp4
| 150 |
[
[
62,
76
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A woman chops vegetables on a chopping board' is semantically aligned with a video moment, please give the start time and end time of the video moment.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/S0lRpPiA84g_360.0_510.0.mp4
| 150 |
[
[
64,
80
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Paintings and their artist are shown on the beach' in the video, and output the start and end timestamps in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/S0lRpPiA84g_210.0_360.0.mp4
| 150 |
[
[
2,
4
],
[
16,
18
],
[
30,
32
],
[
34,
36
],
[
38,
42
],
[
64,
66
],
[
74,
76
],
[
78,
80
],
[
88,
90
],
[
92,
94
],
[
102,
104
],
[
106,
114
],
[
120,
122
],
[
126,
128
],
[
142,
144
],
[
146,
150
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Street seller and performer at the beach' is semantically aligned with a video moment, please give the start time and end time of the video moment.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/S0lRpPiA84g_60.0_210.0.mp4
| 150 |
[
[
104,
132
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Visitors are browsing items for sale on display on a red cloth' is semantically aligned with a video moment, please give the start time and end time of the video moment.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/S0lRpPiA84g_660.0_810.0.mp4
| 150 |
[
[
10,
26
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Woman talks to camera while a fire burns behind her' is semantically aligned with a video moment, please give the start time and end time of the video moment.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/sn2T70B_Wjs_60.0_210.0.mp4
| 150 |
[
[
120,
150
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A man showing a mural of a man against a starry night on the side of a building', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/sn2T70B_Wjs_360.0_510.0.mp4
| 150 |
[
[
40,
76
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A couple unwraps a candy bar and tries it out' is semantically aligned with a video moment, please give the start time and end time of the video moment.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/sn2T70B_Wjs_210.0_360.0.mp4
| 150 |
[
[
22,
26
],
[
30,
52
],
[
62,
84
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Man and woman have a conversation in front of graffiti', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/w9CwRbVvPqM_60.0_210.0.mp4
| 150 |
[
[
10,
44
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A woman walks into her kitchen and prepares coffee and breakfast', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/w9CwRbVvPqM_360.0_510.0.mp4
| 150 |
[
[
64,
104
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A student takes a fried chicken lunch break before resuming her studies' in the video, and output the start and end timestamps in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/w9CwRbVvPqM_210.0_360.0.mp4
| 150 |
[
[
8,
26
],
[
28,
42
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A woman is doing work on a white laptop and large tablet that are side by side' in the video, and output the start and end timestamps in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/w9CwRbVvPqM_510.0_660.0.mp4
| 150 |
[
[
62,
94
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A lady with grey top is chilling and texting with her phone', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/VQx4h40Nrss_60.0_210.0.mp4
| 150 |
[
[
14,
28
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Vlogger puts a sticker on their car', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/VQx4h40Nrss_360.0_510.0.mp4
| 150 |
[
[
4,
12
],
[
14,
18
],
[
20,
32
],
[
64,
68
],
[
72,
74
],
[
108,
114
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'The various water features in a tropical sanctuary', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/VQx4h40Nrss_210.0_360.0.mp4
| 150 |
[
[
0,
94
],
[
102,
108
],
[
132,
150
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Tourist sharing astonishing scenes from Indonesia' is semantically aligned with a video moment, please give the start time and end time of the video moment.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/FGrHVXXu1WY_60.0_210.0.mp4
| 150 |
[
[
92,
120
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'kids having funny conversation during meal' in the video, and output the start and end timestamps in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/FGrHVXXu1WY_210.0_360.0.mp4
| 150 |
[
[
34,
56
],
[
62,
80
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'On vaction a family purchase a mosquito zapper' in the video, and output the start and end timestamps in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/FGrHVXXu1WY_360.0_510.0.mp4
| 150 |
[
[
74,
76
],
[
118,
128
],
[
132,
142
],
[
144,
150
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'Umbrellas are set up at the beach' and determine its start and end seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/gFFAsDDUYiY_210.0_360.0.mp4
| 150 |
[
[
132,
146
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A man in a black shirt is hanging out outside beside a teal house' and determine its start and end seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/gFFAsDDUYiY_360.0_510.0.mp4
| 150 |
[
[
110,
150
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'After a long drive through a dry landscape, travellers reach a fishing destination' and determine its start and end seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/gFFAsDDUYiY_60.0_210.0.mp4
| 150 |
[
[
0,
12
],
[
18,
40
],
[
46,
76
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Man walks down the street carrying two backpacks', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/gFFAsDDUYiY_510.0_660.0.mp4
| 150 |
[
[
74,
118
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'a man on a boat makes dough' is semantically aligned with a video moment, please give the start time and end time of the video moment.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/gFFAsDDUYiY_660.0_810.0.mp4
| 150 |
[
[
102,
118
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Man holds a stick into the water' is semantically aligned with a video moment, please give the start time and end time of the video moment.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/gE8BfrKIYfQ_210.0_360.0.mp4
| 150 |
[
[
10,
32
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Girl mixing colour in liquid and dancing' is semantically aligned with a video moment, please give the start time and end time of the video moment.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/gE8BfrKIYfQ_60.0_210.0.mp4
| 150 |
[
[
26,
68
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A father doing grocery shopping with his kids' in the video, and output the start and end timestamps in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/gE8BfrKIYfQ_360.0_510.0.mp4
| 150 |
[
[
2,
24
],
[
42,
50
],
[
54,
64
],
[
72,
88
],
[
92,
98
],
[
104,
110
],
[
120,
126
],
[
128,
144
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A family cooks colorful design food on round black portable cooking skillets', when does the described content occur in the video? Please return the timestamp in seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/gE8BfrKIYfQ_510.0_660.0.mp4
| 150 |
[
[
110,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'An excited father and his more normal daughter flip cartoon face pancakes made from coloured batter' within the video using timestamps.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/gE8BfrKIYfQ_660.0_810.0.mp4
| 150 |
[
[
0,
88
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A man and three children are cooking in the kitchen' is semantically aligned with a video moment, please give the start time and end time of the video moment.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
tvg
|
qvhighlights
|
qvh/videos/IfZb3Q2cVzg_60.0_210.0.mp4
| 150 |
[
[
72,
116
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'The Bahraini Cowboys have their own weekly competitions in winter' and determine its start and end seconds.The format of your response should be: 'The event happens in <start time> - <end time>''."
},
{
"from": "gpt",
"value": "The event happens in <vid> - <vid>."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.