Self-Supervised Representation Learning with Spatial-Temporal Consistency for Sign Language Recognition.

Weichao ZhaoWengang ZhouHezhen HuMin WangHouqiang Li
Published in: CoRR (2024)
Keyphrases
  • image sequences
  • temporal consistency
  • sign language recognition
  • optical flow
  • spatial information
  • reinforcement learning
  • search space
  • gesture recognition
  • sign language