Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition.
Yuxin ChenZiqi ZhangChunfeng YuanBing LiYing DengWeiming HuPublished in: CoRR (2021)
Keyphrases
- action recognition
- topological information
- human detection
- activity recognition
- bag of words
- human actions
- action classification
- computer vision
- spatial temporal
- video dataset
- body parts
- human activities
- recognizing actions
- recognizing human actions
- graph structure
- pairwise
- view invariant
- recognition of human actions
- depth sensors
- independent subspace analysis
- binary images
- d objects
- depth cameras
- action primitives
- viewpoint
- action recognition in videos
- image sequences