GCsT: Graph Convolutional Skeleton Transformer for Action Recognition.
Ruwen BaiMin LiBo MengFengfa LiJunxing RenMiao JiangDegang SunPublished in: CoRR (2021)
Keyphrases
- action recognition
- human actions
- human detection
- bag of words
- activity recognition
- computer vision
- action classification
- spatial temporal
- body parts
- graph structure
- bag of features
- recognizing human actions
- depth sensors
- human activities
- human pose
- static images
- video dataset
- action detection
- recognition of human actions
- view invariant
- viewpoint
- motion history images
- action primitives
- semi supervised