Skip to main content
Search

# FOCUS

1 related articles

Subscribe to updates
  1. arXiv

    FOCUS calls the video model only when the scene changes: 25.4 calls match 55 on EgoSchema

    Streaming video understanding does not require a vision-language model call on every frame. FOCUS measures patch-embedding dissimilarity with a smaller model from the same family, triggers a burst of inference only when the scene changes meaningfully, and feeds decoder attention back as the spatial prior for the next burst. On the 500-video EgoSchema subset it reaches 74.8% accuracy with 25.4 calls per clip, against 74.6% with 55 calls for uniform sampling.

You’re all caught up