video-constraint-map — Traditional AI Model

Video Constraint Map measures a long source once and reports what a planner cannot infer from a single frame: how deep a bottom crop may go before it eats the subject, read off the source's own burned-in captions.

Details

  • CategoryTraditional
  • Year-1
  • License

Inputs & Outputs

  • VideoInput · video

    The source video to measure (before trimming)

  • SegmentsInput · segments · optional

    Optional candidate segments to restrict measurement to. Leave unconnected to measure the whole source, which costs proportionally more.

  • ConstraintsOutput · string

    JSON: derived crop depth, caption spans, cut-boundary spans, and the per-window subject grid, each with its evidence

Tags

  • video
  • shorts
  • analysis
  • constraints
  • planner

Alternatives in Video Editing