Sign in

3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition.

Lei WangPiotr Koniusz
Published in: CoRR (2023)
Keyphrases
  • action recognition
  • human detection
  • computer vision
  • bag of words
  • recognizing human actions
  • human actions
  • activity recognition
  • spatial temporal
  • static images
  • action classification