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/zGfm5PoYyLo_60.0_210.0.mp4
| 150
|
[
[
42,
58
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'Different dollar amounts are shown in slides'.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/zGfm5PoYyLo_360.0_510.0.mp4
| 150
|
[
[
78,
94
],
[
126,
128
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Man in red top stands between two silos', 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/2VcAA9uhDj8_60.0_210.0.mp4
| 150
|
[
[
68,
78
],
[
132,
140
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Photo of green chairs are next to a man talking' 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/iID--KXm1po_210.0_360.0.mp4
| 150
|
[
[
0,
108
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Couple sharing some outstanding scenes from south India' 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/iID--KXm1po_360.0_510.0.mp4
| 150
|
[
[
48,
74
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A woman inside a moving car filming an white SVU been driven on a street', 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/iID--KXm1po_60.0_210.0.mp4
| 150
|
[
[
18,
24
],
[
26,
32
],
[
114,
124
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'A baby being hold by young girls in the backseat'.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/HP33Hpf9OxU_60.0_210.0.mp4
| 150
|
[
[
0,
48
],
[
50,
52
],
[
60,
118
],
[
120,
150
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'Reporter reports on Flooding from Sydney Australia'.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/WqAJWrU9C1s_360.0_510.0.mp4
| 150
|
[
[
130,
150
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'People are swimming underwater in scuba gear'.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/WqAJWrU9C1s_60.0_210.0.mp4
| 150
|
[
[
70,
120
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Woman wears a soccer jersey when she's holding out her arm like she's talking a selfie', 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/WqAJWrU9C1s_210.0_360.0.mp4
| 150
|
[
[
70,
118
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'Man in white helmet falls from a tall building'.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/5_waeBOXQBE_360.0_510.0.mp4
| 150
|
[
[
134,
150
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Vloggers eat dinner together 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/5_waeBOXQBE_60.0_210.0.mp4
| 150
|
[
[
50,
54
],
[
66,
80
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Vlogger sees different statues around the city' 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/5_waeBOXQBE_210.0_360.0.mp4
| 150
|
[
[
0,
38
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Man and woman walk down the street together' 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/Wfyuia-N510_360.0_510.0.mp4
| 150
|
[
[
0,
14
],
[
34,
46
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Indian woman drives a car with a red dot on 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/Wfyuia-N510_60.0_210.0.mp4
| 150
|
[
[
16,
40
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Mother packs a suitcase next to her daughter' 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/Wfyuia-N510_210.0_360.0.mp4
| 150
|
[
[
88,
138
]
] |
[
{
"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 prepares to go on a road trip with the help of servants'.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/Wfyuia-N510_510.0_660.0.mp4
| 150
|
[
[
0,
58
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Indian woman talks to her family in the doorway', 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/Wfyuia-N510_660.0_810.0.mp4
| 150
|
[
[
92,
114
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A vlogger is showing lots and lots of street food in India', 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/Nax7FwI-YgM_60.0_210.0.mp4
| 150
|
[
[
74,
106
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A student continues vlogging as she enters her high school' 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/Nax7FwI-YgM_360.0_510.0.mp4
| 150
|
[
[
10,
22
],
[
24,
32
],
[
36,
52
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Girls playing and giggling in a school', 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/Nax7FwI-YgM_210.0_360.0.mp4
| 150
|
[
[
98,
100
],
[
118,
150
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Boy sitting at a school cafeteria touching his head', 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/W1rKSyGjDmg_210.0_360.0.mp4
| 150
|
[
[
0,
8
],
[
32,
56
]
] |
[
{
"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 with the view of the coast behind her'.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/W1rKSyGjDmg_60.0_210.0.mp4
| 150
|
[
[
10,
52
],
[
62,
68
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A couple saw a turtle on the road and are walking towards her' 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/W1rKSyGjDmg_360.0_510.0.mp4
| 150
|
[
[
128,
138
],
[
140,
146
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Vlogger walks down a path to 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/EDdPOELyP9o_360.0_510.0.mp4
| 150
|
[
[
0,
114
],
[
116,
150
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Boys having fun and enjoy opening Christmas gift', 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/EDdPOELyP9o_210.0_360.0.mp4
| 150
|
[
[
0,
40
],
[
92,
104
],
[
106,
150
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'Two boys are enthusiastically grabbing and opening their Christmas presents' 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/EDdPOELyP9o_60.0_210.0.mp4
| 150
|
[
[
12,
32
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Woman in Santa hat opens a shoe box' 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/EDdPOELyP9o_510.0_660.0.mp4
| 150
|
[
[
2,
22
],
[
24,
26
],
[
68,
92
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A little boy with black and red pyjama set is opening the Christmas presents', 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/EDdPOELyP9o_660.0_810.0.mp4
| 150
|
[
[
0,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Three children are opening their presents' 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/fssoZaWJs88_360.0_510.0.mp4
| 150
|
[
[
0,
120
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Dash cam of motorcycle in transit in a busy street', 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/fssoZaWJs88_210.0_360.0.mp4
| 150
|
[
[
22,
40
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'The motor cyclists stops by a gas station and gets filled up' 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/fssoZaWJs88_60.0_210.0.mp4
| 150
|
[
[
66,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Dash view of a motorcycle driving down the road' 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/OGYY9xydZu8_210.0_360.0.mp4
| 150
|
[
[
0,
150
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A woman is sharing her experience about delivery' 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/OGYY9xydZu8_360.0_510.0.mp4
| 150
|
[
[
24,
44
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'Woman brushes makeup on her face' 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/OGYY9xydZu8_60.0_210.0.mp4
| 150
|
[
[
50,
92
],
[
112,
116
],
[
120,
132
],
[
138,
142
],
[
146,
150
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Woman dabs her face with a pink sponge' 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/OGYY9xydZu8_510.0_660.0.mp4
| 150
|
[
[
24,
34
],
[
64,
70
],
[
84,
96
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Woman applies makeup to their face' 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/OGYY9xydZu8_660.0_810.0.mp4
| 150
|
[
[
0,
78
],
[
82,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A woman with long hair and in grey top is talking 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/Fo77sTGpngQ_210.0_360.0.mp4
| 150
|
[
[
14,
22
],
[
52,
60
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A map of Israel and Palestine' 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/Fo77sTGpngQ_60.0_210.0.mp4
| 150
|
[
[
16,
64
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A man in a plaid shirt is speaking to a crowd near a vast open area of Israel' 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/Fo77sTGpngQ_360.0_510.0.mp4
| 150
|
[
[
34,
44
],
[
66,
68
],
[
78,
86
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'Man in flannel top gives a speech in front of a small group of people'.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/kp-Nh3XoN6E_360.0_510.0.mp4
| 150
|
[
[
32,
54
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A silouetted mother and daughter walk along a beach and in the waves' 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/kp-Nh3XoN6E_60.0_210.0.mp4
| 150
|
[
[
0,
20
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'People go through an ornate gate and sign into a booklet on a table' 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/kp-Nh3XoN6E_210.0_360.0.mp4
| 150
|
[
[
0,
12
],
[
24,
26
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'Girl in blue dress holds paper'.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/ki_8XoJzkfo_360.0_510.0.mp4
| 150
|
[
[
0,
150
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'a man in black suit and pink tie is talking in front of the camera about weather forecast' 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/B3yOejNbNks_60.0_210.0.mp4
| 150
|
[
[
0,
18
],
[
24,
30
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Woman holds a selfie stick in the closet', 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/B3yOejNbNks_210.0_360.0.mp4
| 142
|
[
[
82,
88
],
[
98,
122
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'People in masks ride the train together' 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/X8hwx15mVgQ_360.0_510.0.mp4
| 150
|
[
[
0,
150
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Woman in blue top talks to camera next to a fern' 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/X8hwx15mVgQ_60.0_210.0.mp4
| 150
|
[
[
54,
86
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'Woman rolls her suitcase next to 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/X8hwx15mVgQ_210.0_360.0.mp4
| 150
|
[
[
0,
2
],
[
4,
44
],
[
48,
56
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A couple is showing the Streets of Accra' 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/X8hwx15mVgQ_510.0_660.0.mp4
| 150
|
[
[
0,
150
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'Woman in blue top sits between two plants' 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/MkXgcnWHF_Q_60.0_210.0.mp4
| 150
|
[
[
88,
96
],
[
102,
110
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Instagram type pictures of restaurant food are shown' 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/p_ZXqV5nCu8_210.0_360.0.mp4
| 150
|
[
[
0,
6
],
[
10,
12
],
[
20,
22
],
[
28,
30
],
[
32,
34
],
[
44,
46
],
[
60,
66
],
[
70,
72
],
[
74,
76
],
[
116,
122
],
[
136,
144
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Vlogger is playing first person shooters' 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/p_ZXqV5nCu8_60.0_210.0.mp4
| 150
|
[
[
46,
60
],
[
74,
76
],
[
78,
80
],
[
82,
92
],
[
94,
96
],
[
98,
102
],
[
114,
116
],
[
128,
130
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Man vlogs in a red tank top around his 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/p_ZXqV5nCu8_360.0_510.0.mp4
| 128
|
[
[
6,
8
],
[
12,
18
],
[
52,
54
],
[
66,
72
],
[
96,
110
],
[
116,
120
],
[
122,
124
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'Gamer plays a first person shooter' 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/zdT66QkmN-U_360.0_510.0.mp4
| 150
|
[
[
116,
138
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A woman gets back into her car and gets ready to depart' 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/zdT66QkmN-U_60.0_210.0.mp4
| 150
|
[
[
122,
150
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A man sits on the floor and shows off the features of his suitcase' 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/zdT66QkmN-U_210.0_360.0.mp4
| 150
|
[
[
66,
100
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A couple lug heavy bags of food and a cooler of drinks to the car for a trip' 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/MvR-Eyf7334_360.0_510.0.mp4
| 150
|
[
[
20,
22
],
[
30,
32
],
[
34,
70
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Bald Asian man stands in front of his staircase' 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/MvR-Eyf7334_210.0_360.0.mp4
| 150
|
[
[
88,
130
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A vlogger interviews an immigration lawyer full of positive energy who helps individual and families with the American Dream' 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/MvR-Eyf7334_510.0_660.0.mp4
| 150
|
[
[
10,
42
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A boy with a black top is holding a container with some stuff in 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/iy6ebyYvNoA_210.0_360.0.mp4
| 150
|
[
[
28,
38
],
[
52,
58
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A man is looking at an article on the phone in landscape mode' 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/iy6ebyYvNoA_60.0_210.0.mp4
| 150
|
[
[
2,
22
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Governor of Illinois discussing marijuana criminalization' 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/iy6ebyYvNoA_360.0_510.0.mp4
| 150
|
[
[
84,
98
],
[
102,
110
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Men enter the podium and shake each others hands' 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/2Z8R2vv78VQ_60.0_210.0.mp4
| 130
|
[
[
46,
74
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Officials spray protesters with water' 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/OcdwIhUTVzg_210.0_360.0.mp4
| 150
|
[
[
34,
46
],
[
68,
80
],
[
110,
122
]
] |
[
{
"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 white top 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/OcdwIhUTVzg_60.0_210.0.mp4
| 150
|
[
[
90,
96
],
[
98,
110
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A band is playing in the street with a tuba player in front' 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/OcdwIhUTVzg_360.0_510.0.mp4
| 150
|
[
[
120,
134
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Woman with black shirt is alone on the bus', 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/OcdwIhUTVzg_510.0_660.0.mp4
| 150
|
[
[
82,
96
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Woman walks by cars parked on the street' 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/0B9BySokeSc_60.0_210.0.mp4
| 150
|
[
[
22,
52
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A foreigner in his video tour taking a local bus in India' 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/0B9BySokeSc_360.0_510.0.mp4
| 150
|
[
[
0,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A young man wearing a black t-shirt and backpack walks down a busy street and enjoys the sights' 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/0B9BySokeSc_210.0_360.0.mp4
| 150
|
[
[
0,
6
],
[
10,
32
],
[
36,
40
],
[
112,
140
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'Man in black top walks down the street with his backpack' 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/D2Fk3Zke6Kc_60.0_210.0.mp4
| 150
|
[
[
62,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A guy talking and having food in front of a building' 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/D2Fk3Zke6Kc_210.0_360.0.mp4
| 150
|
[
[
98,
130
],
[
140,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Man with white and black walks outside on a sunny day' 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/D2Fk3Zke6Kc_360.0_510.0.mp4
| 150
|
[
[
56,
80
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A guy preparing a plate of healthy foods' 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/l_s0sBhMprU_360.0_510.0.mp4
| 150
|
[
[
0,
44
],
[
112,
116
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A cute video of a toddler' 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/l_s0sBhMprU_60.0_210.0.mp4
| 150
|
[
[
102,
134
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Mother feeds daughter at the tabel', 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/l_s0sBhMprU_210.0_360.0.mp4
| 150
|
[
[
70,
94
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'A mother and child see father off to work in the morning' 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/l_s0sBhMprU_660.0_810.0.mp4
| 150
|
[
[
86,
110
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Mom cleans her kid's hands then picks her up' 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/l_s0sBhMprU_510.0_660.0.mp4
| 150
|
[
[
56,
70
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A woman holds up a one pot dinner and feeds her daughter at the dinner table', 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/BzGz18LynZY_60.0_210.0.mp4
| 150
|
[
[
0,
14
],
[
30,
36
],
[
42,
54
],
[
64,
70
],
[
82,
92
],
[
112,
124
],
[
128,
132
],
[
142,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A man in grey t-shirt is talking in front of the camera' 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/BzGz18LynZY_210.0_360.0.mp4
| 150
|
[
[
0,
8
],
[
18,
22
],
[
26,
38
],
[
48,
50
],
[
56,
62
],
[
96,
102
],
[
108,
116
],
[
118,
120
],
[
132,
134
],
[
140,
150
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A man sitting on a tree trunk talking to 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/BzGz18LynZY_360.0_510.0.mp4
| 140
|
[
[
108,
130
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A shirtless guy has jumped on 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/l2t6ful9mmw_210.0_360.0.mp4
| 150
|
[
[
46,
52
],
[
58,
66
],
[
78,
90
],
[
94,
98
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'Woman in white sweater stands on the road between palm trees' 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/l2t6ful9mmw_360.0_510.0.mp4
| 150
|
[
[
62,
112
],
[
120,
128
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'A video blogger chatting with a local kid', 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/l2t6ful9mmw_60.0_210.0.mp4
| 150
|
[
[
126,
150
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A couple is walking along a series of ancient pillars together' 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/c-AzfXMJkI8_60.0_210.0.mp4
| 150
|
[
[
74,
80
],
[
86,
108
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Asian protestors are in the streets using umbrellas, googles and masks to protect against the teargas the police are using on them' 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/c-AzfXMJkI8_360.0_510.0.mp4
| 150
|
[
[
90,
126
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Student protesters set fire to parts of the university in a desperate last stand', 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/c-AzfXMJkI8_210.0_360.0.mp4
| 150
|
[
[
14,
24
],
[
26,
52
],
[
78,
116
],
[
118,
120
],
[
126,
134
],
[
142,
144
],
[
146,
148
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'Clashes between police and citizens of Hong Kong erupted during protest' 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/eELlXEBn_Z8_360.0_510.0.mp4
| 150
|
[
[
104,
150
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'A woman gets into a red car and drives around' 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/eELlXEBn_Z8_60.0_210.0.mp4
| 150
|
[
[
16,
42
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Man picks fruit for the woman to eat', 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/eELlXEBn_Z8_210.0_360.0.mp4
| 150
|
[
[
0,
30
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Woman in white top talks while riding in a 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/T2t1_b9qPyQ_210.0_360.0.mp4
| 150
|
[
[
0,
14
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'Boy is sitting on a motorcycle' 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/T2t1_b9qPyQ_360.0_510.0.mp4
| 150
|
[
[
4,
38
]
] |
[
{
"from": "human",
"value": "<image>\nDetect and report the start and end timestamps of the video segment that semantically matches the given textual query 'South India Father playing and enjoying with his son'.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/T2t1_b9qPyQ_60.0_210.0.mp4
| 150
|
[
[
0,
66
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'South Indian boy having morning walk with his dog' 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/T2t1_b9qPyQ_510.0_660.0.mp4
| 150
|
[
[
52,
60
],
[
62,
96
]
] |
[
{
"from": "human",
"value": "<image>\nLocalize the visual content described by the given textual query 'A woman in yellow is whisking flour with other ingredients in a glass 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/T2t1_b9qPyQ_660.0_810.0.mp4
| 150
|
[
[
110,
128
],
[
132,
134
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'The little boy with white top is sliding down the tube with his mom' 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/DO1LrFYPduk_210.0_360.0.mp4
| 150
|
[
[
2,
6
],
[
12,
14
],
[
16,
18
],
[
24,
28
],
[
34,
36
],
[
40,
42
],
[
46,
48
],
[
54,
58
],
[
62,
66
],
[
72,
74
],
[
76,
80
],
[
86,
88
],
[
90,
92
],
[
98,
100
],
[
104,
106
],
[
116,
118
],
[
124,
126
],
[
132,
134
],
[
136,
140
],
[
146,
150
]
] |
[
{
"from": "human",
"value": "<image>\nFind the video segment that corresponds to the given textual query 'Most amazing day of my life' 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/DO1LrFYPduk_60.0_210.0.mp4
| 150
|
[
[
14,
28
],
[
66,
68
]
] |
[
{
"from": "human",
"value": "<image>\nLocate the visual content mentioned in the text query 'Woman with black hat boards a plane' 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/DO1LrFYPduk_360.0_510.0.mp4
| 150
|
[
[
16,
76
]
] |
[
{
"from": "human",
"value": "<image>\nThe given natural language query 'A woman goes for a scary but fun dune buggy ride in the desert' 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/AcuIsmYtmCY_210.0_360.0.mp4
| 150
|
[
[
0,
20
],
[
22,
32
],
[
34,
42
],
[
94,
134
],
[
136,
150
]
] |
[
{
"from": "human",
"value": "<image>\nGiven a textual query: 'Blonde woman vlogs in a kitchen with blue cabinets', 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.