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/9bQ98HLDQ38_60.0_210.0.mp4
| 150 |
[
[
92,
106
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A woman is showing the water enclosure for what looks like an otter' 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/TO3lkDEhBR0_360.0_510.0.mp4
| 150 |
[
[
10,
66
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Men struggling to make it over a boulder blocking their path along the river' 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/TO3lkDEhBR0_60.0_210.0.mp4
| 150 |
[
[
4,
24
],
[
26,
28
],
[
32,
44
],
[
50,
68
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'An Asian woman wearing a helmet mountain hiking' 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/TO3lkDEhBR0_210.0_360.0.mp4
| 150 |
[
[
78,
96
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Woman in wide top twirls a stick in the water' 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/D7b6kRDMLlY_360.0_510.0.mp4
| 150 |
[
[
24,
48
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A man films himself while walking on a street near a columned building and buses', 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/D7b6kRDMLlY_210.0_360.0.mp4
| 150 |
[
[
10,
32
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'Fog is surrounding the mountain'.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/D7b6kRDMLlY_60.0_210.0.mp4
| 150 |
[
[
90,
118
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Two men tandem jump out of a plane' 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/go12WJBcCOQ_360.0_510.0.mp4
| 150 |
[
[
118,
130
],
[
134,
142
],
[
146,
150
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'Man with hoodie sits and enjoys refreshing himself with mountain water' 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/go12WJBcCOQ_210.0_360.0.mp4
| 150 |
[
[
4,
6
],
[
22,
24
],
[
28,
30
],
[
40,
44
],
[
46,
48
],
[
54,
56
],
[
62,
64
],
[
66,
72
],
[
90,
92
],
[
94,
100
],
[
108,
112
],
[
116,
118
],
[
120,
122
],
[
124,
130
],
[
134,
136
],
[
142,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Our Travel VLOG to Manali' 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/go12WJBcCOQ_60.0_210.0.mp4
| 150 |
[
[
122,
150
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'People get in a blue lighted bus and sit down', 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/go12WJBcCOQ_510.0_660.0.mp4
| 128 |
[
[
2,
28
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'People point to a waterfall' 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/VP6JcJ9przo_210.0_360.0.mp4
| 150 |
[
[
68,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Guys buying and eating street foods' 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/VP6JcJ9przo_60.0_210.0.mp4
| 150 |
[
[
60,
84
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A group of asian friends taking silly pictures in a lobster display', 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/Mp7wN80amkQ_360.0_510.0.mp4
| 150 |
[
[
82,
120
],
[
124,
132
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Kids with different face paintings on them' 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/Mp7wN80amkQ_60.0_210.0.mp4
| 150 |
[
[
66,
112
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Two small children are playing with instruments in the living room by a gray sectional couch', 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/Mp7wN80amkQ_210.0_360.0.mp4
| 150 |
[
[
0,
60
],
[
72,
126
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'A mom is talking about her son birthday party'.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/Mp7wN80amkQ_660.0_810.0.mp4
| 150 |
[
[
102,
132
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Children at a birthday party are wearing costumes seated at a table ready for the cake', 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/Mp7wN80amkQ_510.0_660.0.mp4
| 150 |
[
[
50,
74
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A little boy with red and black jacket is hitting the birthday piñata' 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.