Video
What is video intelligence?
Video intelligence is a pipeline that turns clips into structured outputs you can search: frames, detections, transcripts, and embeddings.
Updated
How it works
- Store the clip as video.
- Derive frames, labels, and text.
- Search or serve those rows.
What it is not
It is not a hosted video API that returns black-box JSON and no table you own.
video intelligence: this, and the thing it is confused with
| This | Not this | |
|---|---|---|
| You own | The table of clips and derivatives | Only an API response |
| Outputs | Frames, boxes, transcripts, vectors | One opaque JSON blob |
| Refresh | Changed clips only | Resubmit the library |
Where Pixeltable fits
Pixeltable is the table those outputs live on. A video-intelligence API can still be the model a computed column calls.
Questions
- How does video intelligence work?
- Store the clip as video. Derive frames, labels, and text. Search or serve those rows.
- What is video intelligence often confused with?
- It is not a hosted video API that returns black-box JSON and no table you own.