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.
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 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Task-Oriented Communication for Human Action Understanding via Edge-Cloud Co-Inference
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.