Trio-Lumen · Video understanding
Every action, in words.
Turn first-person video into timed English descriptions. See what the left hand holds, what the right hand moves, and how the work unfolds.
Open vocabulary. Specific to the scene.
Describe packing, sorting, handling garments and working with tools in free text. Each segment pairs a start and end time with a caption that names the hands, objects and actions visible in the scene.
One API, from video to JSON.
Submit a batch, review its quote and download one verified JSON result per video. Use hosted results or your own bucket, with polling or signed webhooks.
See the descriptions.
Exact excerpts from two previously shared demo videos. Full results also include input metadata, coverage and quality checks.
event_0001_video_0001
{
"segments": [
{
"index": 0,
"start_s": 0,
"end_s": 3.6,
"caption": "hold hanger with right hand, pick up shirt with left hand, place shirt on hanger with both hands"
},
{
"index": 1,
"start_s": 3.6,
"end_s": 5,
"caption": "hold hanger with left hand, place shirt on hanger with right hand"
},
{
"index": 2,
"start_s": 5,
"end_s": 7.6,
"caption": "hold hanger with right hand, pick up shirt with left hand"
},
{
"index": 3,
"start_s": 7.6,
"end_s": 8.6,
"caption": "place the blue cloth on the table with the left hand while holding the hanger with the right hand"
},
{
"index": 4,
"start_s": 8.6,
"end_s": 10.2,
"caption": "hang hanger on rack with right hand"
},
{
"index": 5,
"start_s": 8.65,
"end_s": 12.4,
"caption": "place hanger on rack with right hand, pick up blue shirt with both hands"
},
{
"index": 6,
"start_s": 10.2,
"end_s": 12,
"caption": "pick up blue cloth with both hands"
}
]
}event_0003_video_0001
{
"segments": [
{
"index": 0,
"start_s": 0,
"end_s": 4.25,
"caption": "place black object on chair with left hand, pick up red object with right hand"
},
{
"index": 1,
"start_s": 4.25,
"end_s": 6.5,
"caption": "pick up the white box from the blue box with both hands"
}
]
}