Language Guided Graph Transformer for Skeleton Action Recognition.
Libo WengWeidong LouFei GaoPublished in: ICONIP (10) (2023)
Keyphrases
- action recognition
- activity recognition
- human actions
- human detection
- bag of words
- spatial temporal
- recognizing human actions
- computer vision
- recognizing actions
- body parts
- graph structure
- action classification
- view invariant action recognition
- static images
- bag of features
- action detection
- human activities
- independent subspace analysis
- view invariant
- depth sensors
- action primitives
- action recognition in videos
- video dataset
- recognition of human actions
- depth cameras
- spatio temporal