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/WcMY9hjwN58_60.0_210.0.mp4
| 150
|
[
[
42,
66
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'Woman in flannel walks around a beach'.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/WcMY9hjwN58_360.0_510.0.mp4
| 150
|
[
[
2,
4
],
[
16,
18
],
[
22,
28
],
[
30,
32
],
[
34,
36
],
[
46,
48
],
[
54,
56
],
[
66,
68
],
[
76,
78
],
[
84,
90
],
[
96,
122
],
[
124,
126
],
[
128,
130
],
[
134,
142
],
[
146,
150
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Beautiful island on the earth' 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/WcMY9hjwN58_210.0_360.0.mp4
| 150
|
[
[
112,
150
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Woman in purple top wears sunglasses on top of her head' 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/WcMY9hjwN58_510.0_660.0.mp4
| 150
|
[
[
44,
58
],
[
60,
62
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'Woman in flannel shirt walks down the street'.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/uQQc6ZP6ISE_60.0_210.0.mp4
| 150
|
[
[
0,
54
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A couple is sharing the highlights of their Santorini Greece tour' 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/uQQc6ZP6ISE_210.0_360.0.mp4
| 150
|
[
[
18,
28
],
[
30,
36
],
[
44,
54
],
[
56,
60
],
[
72,
74
],
[
76,
82
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'Woman goes hiking in a black top'.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/uQQc6ZP6ISE_360.0_510.0.mp4
| 150
|
[
[
4,
18
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A blue table is being set with wine glasses and drinks' 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/yDTVgjU2L_E_210.0_360.0.mp4
| 150
|
[
[
102,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A large musical stage performance is filmed from the audience' 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/yDTVgjU2L_E_60.0_210.0.mp4
| 150
|
[
[
0,
74
],
[
80,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A woman and a little girl wearing a white clothes are talking to each other in front of the camera' 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/YuOQdcrATaI_210.0_360.0.mp4
| 150
|
[
[
0,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A lady talking from her house' 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/YuOQdcrATaI_60.0_210.0.mp4
| 150
|
[
[
0,
2
],
[
4,
32
],
[
36,
48
],
[
50,
74
],
[
78,
82
],
[
126,
130
],
[
138,
140
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Woman with hair pulled back stands next to red towel', 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/YuOQdcrATaI_360.0_510.0.mp4
| 150
|
[
[
78,
114
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A bookcase in the background has a spotlight on it' 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/YuOQdcrATaI_660.0_810.0.mp4
| 150
|
[
[
132,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Woman carries her baby in her arms' 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/YuOQdcrATaI_510.0_660.0.mp4
| 150
|
[
[
0,
4
],
[
12,
16
],
[
108,
116
],
[
120,
128
],
[
132,
140
],
[
144,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'a woman relates a story to the camera' 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/LbHMA9eOiYM_60.0_210.0.mp4
| 150
|
[
[
96,
122
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Woman pours ingredients into Tupperware and seals 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/LbHMA9eOiYM_210.0_360.0.mp4
| 150
|
[
[
0,
14
],
[
52,
60
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Chef cooks broccoli in a pot' 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/LbHMA9eOiYM_360.0_510.0.mp4
| 150
|
[
[
128,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A woman is adding spinach to a pan and stirring it around into the ingredients' 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/LbHMA9eOiYM_660.0_810.0.mp4
| 150
|
[
[
22,
72
],
[
74,
142
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Woman washes the dishes in the sink', 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/LbHMA9eOiYM_510.0_660.0.mp4
| 150
|
[
[
0,
106
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A video showing a woman mixing food and then showing plants', 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/jL1NOkOaO8M_60.0_210.0.mp4
| 150
|
[
[
18,
26
],
[
60,
82
],
[
128,
132
],
[
142,
148
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'Long haired woman dances on a balcony with a mountain view'.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/0nQgqIJbCZw_60.0_210.0.mp4
| 150
|
[
[
136,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Kids are sitting at the table eating breakfast' 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/0nQgqIJbCZw_210.0_360.0.mp4
| 150
|
[
[
20,
22
],
[
98,
124
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Baby rolls around on the floor next to their toys' 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/0nQgqIJbCZw_360.0_510.0.mp4
| 150
|
[
[
88,
98
],
[
100,
110
],
[
118,
140
],
[
146,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Young girl uses a pacifier while standing in front of a large container with yellow top' 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/0nQgqIJbCZw_660.0_810.0.mp4
| 150
|
[
[
0,
56
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A woman is loading up a very full dishwasher and closing it' 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/0nQgqIJbCZw_510.0_660.0.mp4
| 150
|
[
[
26,
36
],
[
46,
52
],
[
58,
70
],
[
74,
90
],
[
94,
96
],
[
98,
100
],
[
104,
126
],
[
128,
136
],
[
140,
150
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A woman in grey t-shirt is filling up dishwasher' 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/_RiDsBJNJo8_60.0_210.0.mp4
| 150
|
[
[
82,
122
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'The woman is packing an alpaca book and two stuffed alpacas into a red bag'.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/_RiDsBJNJo8_360.0_510.0.mp4
| 150
|
[
[
0,
90
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A lady wrapping different gifts' 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/_RiDsBJNJo8_210.0_360.0.mp4
| 150
|
[
[
40,
70
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A lady with pink hair wraps a purple and a brown scarf to be given as as gift' 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/_RiDsBJNJo8_660.0_810.0.mp4
| 150
|
[
[
50,
52
],
[
54,
68
],
[
126,
142
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'A pink hair and top lady is holding and putting down a black baby lamb'.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/_RiDsBJNJo8_510.0_660.0.mp4
| 150
|
[
[
48,
50
],
[
60,
110
]
] |
[
{
"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 wraps a box of pots and pans'.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/1FRTjq7HJc0_210.0_360.0.mp4
| 150
|
[
[
68,
82
],
[
100,
108
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A woman steam ironing a yellow dress and a blue dress' 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/1FRTjq7HJc0_360.0_510.0.mp4
| 150
|
[
[
112,
150
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A curry is cooking in a wok', 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/1FRTjq7HJc0_60.0_210.0.mp4
| 150
|
[
[
8,
16
],
[
18,
52
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Young boy gets a haircut' 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/1FRTjq7HJc0_660.0_810.0.mp4
| 150
|
[
[
90,
110
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A woman is frying pieces of chicken in a cast iron pot' 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/1FRTjq7HJc0_510.0_660.0.mp4
| 150
|
[
[
14,
36
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A person is setting up a brass platter with different foods' 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/EvAJwlDZw1k_60.0_210.0.mp4
| 150
|
[
[
100,
114
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Man and woman walk down the beach' 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/EvAJwlDZw1k_210.0_360.0.mp4
| 150
|
[
[
14,
30
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Man lifts a stein and drinks beer', 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/MRCl9XEKsAM_210.0_360.0.mp4
| 150
|
[
[
0,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A guy talking on a couch from a house' 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/MRCl9XEKsAM_60.0_210.0.mp4
| 150
|
[
[
26,
40
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Man brushes his teeth in the bathroom', 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/HNP_762UZTI_360.0_510.0.mp4
| 150
|
[
[
80,
92
],
[
96,
150
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A man in black jacket is talking in front of a camera and then a video showing a floodwater the area' 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/UflHIC3rm9o_210.0_360.0.mp4
| 150
|
[
[
44,
66
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'A young woman inside a locker room talking to the camera'.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/UflHIC3rm9o_60.0_210.0.mp4
| 150
|
[
[
2,
20
],
[
24,
56
],
[
58,
60
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Tourist girl sharing some exquisite building video', 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/UflHIC3rm9o_360.0_510.0.mp4
| 150
|
[
[
100,
120
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Vlogger circles around a Prague square to show the old buildings' 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/i5PIus8BVpA_60.0_210.0.mp4
| 150
|
[
[
70,
98
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'A lady showing the capacity of a conference hall'.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/i5PIus8BVpA_210.0_360.0.mp4
| 150
|
[
[
12,
24
],
[
36,
74
]
] |
[
{
"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 in a bikini is relaxing beside a color changing pool at night'.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/i5PIus8BVpA_360.0_510.0.mp4
| 150
|
[
[
0,
30
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Woman is dancing in a pool', 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/IJZAHy4JtZo_60.0_210.0.mp4
| 150
|
[
[
16,
20
],
[
48,
68
],
[
102,
108
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A couple touring and getting sight of the dome on the rock' 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/IJZAHy4JtZo_360.0_510.0.mp4
| 150
|
[
[
2,
8
],
[
14,
16
],
[
22,
50
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Woman holds a sandwich and eats it' 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/IJZAHy4JtZo_210.0_360.0.mp4
| 150
|
[
[
108,
130
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A woman is ordering from a man in white standing beside a lucky bamboo plant', 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/Bhew0Pmwcx4_210.0_360.0.mp4
| 150
|
[
[
132,
150
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A woman is putting the finishing touches on her costume dress and walking out to stage' 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/Bhew0Pmwcx4_360.0_510.0.mp4
| 150
|
[
[
114,
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 girl doing her make up'.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/Bhew0Pmwcx4_60.0_210.0.mp4
| 150
|
[
[
32,
84
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A young theatre actress playing the Snow Queen talks about the amazing feedback she got from her \"I hate my body\" video' 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/Bhew0Pmwcx4_510.0_660.0.mp4
| 150
|
[
[
54,
126
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Dance troupe is performing a ballet' 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/TWa_ArpQHFg_210.0_360.0.mp4
| 150
|
[
[
72,
90
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'People are dancing with colored lights' 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/TWa_ArpQHFg_60.0_210.0.mp4
| 150
|
[
[
20,
30
],
[
56,
70
],
[
94,
98
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Boy with striped sop sits next to his mom inside their house' 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/TWa_ArpQHFg_360.0_510.0.mp4
| 150
|
[
[
28,
50
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A timelapse of people setting up the balloons and decoration for someone's 16th birthday' 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/TWa_ArpQHFg_660.0_810.0.mp4
| 150
|
[
[
0,
28
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Woman is dressed like a princess next to pink and white balloon tower' 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/TWa_ArpQHFg_510.0_660.0.mp4
| 150
|
[
[
56,
68
],
[
70,
78
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'The lady with green top is applying the eye liners to the lady with pink top' 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/HY7EC5zXoEE_210.0_360.0.mp4
| 150
|
[
[
0,
34
],
[
36,
68
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A girl talking about the phone cases she bought' 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/HY7EC5zXoEE_360.0_510.0.mp4
| 150
|
[
[
100,
150
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A young woman talks about her day's plans as she gets ready to go to the grocery store' 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/HY7EC5zXoEE_60.0_210.0.mp4
| 150
|
[
[
2,
20
],
[
36,
102
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A couple walking together around and showing their outfits' 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/HY7EC5zXoEE_660.0_810.0.mp4
| 150
|
[
[
4,
24
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A woman is showing the way she organizes her fridge', 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/HY7EC5zXoEE_510.0_660.0.mp4
| 150
|
[
[
34,
84
],
[
96,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A girl displays the groceries she bought from a shopping trip' 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/_gV6GYfnpvk_60.0_210.0.mp4
| 150
|
[
[
2,
14
],
[
20,
26
],
[
32,
42
],
[
48,
54
],
[
64,
76
],
[
82,
88
],
[
96,
106
],
[
110,
122
],
[
134,
142
],
[
148,
150
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'The Speaker, Sumitra Mahajan, is sitting in a chair with a microphone in front of her' 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/_gV6GYfnpvk_360.0_510.0.mp4
| 150
|
[
[
0,
6
],
[
48,
76
],
[
84,
136
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'Speaker of a parliament listening to the parliament members' 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/_gV6GYfnpvk_210.0_360.0.mp4
| 150
|
[
[
0,
6
],
[
36,
42
],
[
62,
72
],
[
90,
112
],
[
130,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'As a crowd of people are shown in one panel, a woman in purple garments appears to be addressing an audience of politicians in the other panel' 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/TzdjEviN9JQ_60.0_210.0.mp4
| 150
|
[
[
58,
74
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Woman is whisking the batter in a bowl', 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/TzdjEviN9JQ_210.0_360.0.mp4
| 150
|
[
[
72,
116
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Batter is measured out in the cups of a muffin tin', 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/TzdjEviN9JQ_360.0_510.0.mp4
| 150
|
[
[
104,
150
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'An asian woman in a blue apron is whisking and blending ingrednients in the kitchen', 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/TzdjEviN9JQ_660.0_810.0.mp4
| 150
|
[
[
114,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Woman uses a hand mixer for her dessert bowl' 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/TzdjEviN9JQ_510.0_660.0.mp4
| 150
|
[
[
0,
14
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A woman is mixing ingredients in a standing blender in the kitchen' 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/LdQXiOZWgsw_360.0_510.0.mp4
| 150
|
[
[
0,
150
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Girl having photo session in 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/LdQXiOZWgsw_60.0_210.0.mp4
| 150
|
[
[
68,
110
],
[
138,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'The woman is crouching at the produce drawer in her fridge' 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/LdQXiOZWgsw_210.0_360.0.mp4
| 150
|
[
[
12,
34
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Woman with pink pants grows through her fridge', 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/z6oJAn7kMpM_360.0_510.0.mp4
| 150
|
[
[
12,
26
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'Chef makes their yogurt in a bowl' 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/z6oJAn7kMpM_210.0_360.0.mp4
| 150
|
[
[
84,
112
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A girl having a weird looking chocolate ice cream' 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/z6oJAn7kMpM_60.0_210.0.mp4
| 150
|
[
[
106,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A woman is opening packages and taking the contents out' 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/v7VF55cyDUc_60.0_210.0.mp4
| 150
|
[
[
60,
74
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A man in blue is walking in front of what appears to be a huge temple complex surrounded by a white wall' 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/v7VF55cyDUc_360.0_510.0.mp4
| 150
|
[
[
50,
86
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A Thai young woman with a megaphone is leading a letter writing campaign directed at the king' 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/v7VF55cyDUc_210.0_360.0.mp4
| 150
|
[
[
14,
20
],
[
24,
28
],
[
40,
44
],
[
50,
54
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'Woman in red speaks to a crowd while on stage' 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/mZxyaFhDo6Y_60.0_210.0.mp4
| 150
|
[
[
132,
148
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A woman in traditional garb is flipping through a photo album' 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/mZxyaFhDo6Y_210.0_360.0.mp4
| 150
|
[
[
0,
14
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Woman in pink sits with her face blurred out' 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/mZxyaFhDo6Y_360.0_510.0.mp4
| 140
|
[
[
20,
42
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A woman in a yellow jacket and mask is giving an interview' 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/81-cNmBcufE_60.0_210.0.mp4
| 150
|
[
[
50,
52
],
[
70,
76
],
[
80,
86
],
[
98,
102
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'Vlogger manipulate different restaurant food' 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/81-cNmBcufE_360.0_510.0.mp4
| 150
|
[
[
90,
104
],
[
106,
120
],
[
148,
150
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Man in gray top walks around the docks' 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/81-cNmBcufE_210.0_360.0.mp4
| 150
|
[
[
114,
138
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A man tries some food and talks about it at a café', 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/lUC-SVEn1ZM_60.0_210.0.mp4
| 150
|
[
[
118,
124
],
[
128,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Man and woman have a conversation next to a bridge' 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/lUC-SVEn1ZM_210.0_360.0.mp4
| 150
|
[
[
0,
8
],
[
12,
16
],
[
20,
24
],
[
28,
40
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A couple talking on a bridge that goes over 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/lUC-SVEn1ZM_360.0_510.0.mp4
| 150
|
[
[
36,
118
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'American tourist couple sharing some random scenes from Poland' 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/sjPPUhmZizM_360.0_510.0.mp4
| 150
|
[
[
82,
150
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'An Asian woman wearing a pink jacket talking about a storm' 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/sjPPUhmZizM_60.0_210.0.mp4
| 150
|
[
[
20,
80
],
[
82,
142
],
[
144,
150
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Official brief press about NOVA SCOTIA HURRICANE' 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/vOCXMt0yWYc_60.0_210.0.mp4
| 150
|
[
[
0,
150
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A man drives in his car and talks as we see footage from the dash camera of a busy city' 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/vOCXMt0yWYc_360.0_510.0.mp4
| 150
|
[
[
0,
150
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'Dash cam view of a car in transit on busy city streets' 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/vOCXMt0yWYc_210.0_360.0.mp4
| 150
|
[
[
120,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'White text on the bottom left showing us where the car is currently drv/iing' 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/psNjHIpXxEs_210.0_360.0.mp4
| 150
|
[
[
112,
134
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Two young girls eating finger food snacks at a table at a restaurant', 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/psNjHIpXxEs_60.0_210.0.mp4
| 150
|
[
[
80,
90
],
[
92,
106
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Kids are interviewed by a pink wall', 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/psNjHIpXxEs_360.0_510.0.mp4
| 150
|
[
[
58,
88
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'Woman in white top dances in a studio' 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/JnOIoOxVjtA_360.0_510.0.mp4
| 150
|
[
[
100,
150
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'some group of people in a cooking class mixing up some recipies for zucchini balls and cheese pie'.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/JnOIoOxVjtA_60.0_210.0.mp4
| 150
|
[
[
58,
72
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Vlogger shows a food stand with lots of Pepsi' 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/JnOIoOxVjtA_210.0_360.0.mp4
| 150
|
[
[
0,
46
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Soldiers preform marching for a audience', 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>."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.