Auto-pick thumbnail candidate frames from frame captions
Judges: one frame caption from vision model. Questions: noul:face_visible_emotive; noul:text_safe_area_free; score:clickworthiness 1-5. Action: Top 5 frames per video cropped and sent to designer.
AA clean typed decision (yes/no, a pick from a list, or a level on a scale) that is concrete, repeats routinely, and has meaningful value.3.92
Key facts
- Vertical
- Agencies, media & creators
- Function
- Social & creator
- Status
- Idea
- Volume
- routine
- Value
- meaningful
- Risk
- moderate
- Evidence
- —
- Flags
- None
Build this with a classifier
Define a typed decision with a bounded answer, then evaluate it on examples.
{
"decision_type": "choice",
"question": "Does this input match the decision in “Auto-pick thumbnail candidate frames from frame captions”?",
"input": "<input to classify>",
"output": "one label from a fixed list"
}Related use cases
Cite this
Copy a link in your preferred format.