Video Detective

Enable VLMs to find relevant clips in long videos through sparse observation and graph-based propagation. Iteratively hypothesize promising segments, extract multimodal evidence (captions, OCR, speech), and propagate relevance scores via visual-temporal affinity graph. Jointly model extrinsic relevance (query-to-segment matching) and intrinsic relevance (video internal structure) to infer unobserved segments. Achieves competitive accuracy with significantly fewer tokens than dense sampling.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 5c0d39a6bb

Frequently asked questions

npx get-skill add adu2021/video-detective