pith. machine review for the scientific record. sign in

Temporal context min- ing for learned video compression

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

eess.SP 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Task-Oriented Communication for Human Action Understanding via Edge-Cloud Co-Inference

eess.SP · 2026-05-08 · unverdicted · novelty 5.0

TOAU compresses human motion videos to 9 bits per frame with pose estimation and VQ-VAE, then aligns the tokens to a vision-language model via a lightweight projector, achieving 1% transmission payload and 20% latency of video codecs while maintaining comparable action understanding accuracy.

citing papers explorer

Showing 1 of 1 citing paper.

  • Task-Oriented Communication for Human Action Understanding via Edge-Cloud Co-Inference eess.SP · 2026-05-08 · unverdicted · none · ref 29

    TOAU compresses human motion videos to 9 bits per frame with pose estimation and VQ-VAE, then aligns the tokens to a vision-language model via a lightweight projector, achieving 1% transmission payload and 20% latency of video codecs while maintaining comparable action understanding accuracy.