Skeleton MixFormer: Multivariate Topology Representation for Skeleton-based Action Recognition.
Wentian XinQiguang MiaoYi LiuRuyi LiuChi-Man PunCheng ShiPublished in: ACM Multimedia (2023)
Keyphrases
- action recognition
- recognizing human actions
- recognition of human actions
- view invariant
- action recognition in videos
- human actions
- delaunay triangulation
- topological information
- bag of features
- activity recognition
- computer vision
- bag of words
- medial axis
- human detection
- action classification
- body parts
- shape analysis
- action primitives
- independent subspace analysis
- spatial temporal
- recognizing actions
- atomic actions
- action detection
- human activities
- spatio temporal
- depth sensors
- video dataset
- object detection