Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition.
Helei QiuBiao HouBo RenXiaohua ZhangPublished in: CoRR (2022)
Keyphrases
- action recognition
- human actions
- spatio temporal
- action recognition in videos
- spatio temporal interest points
- spatial temporal
- view invariant
- computer vision
- activity recognition
- recognition of human actions
- action classification
- spatial and temporal
- bag of words
- human detection
- body parts
- recognizing actions
- human activities
- space time
- recognizing human actions
- image sequences
- independent subspace analysis
- bag of features
- human pose
- data streams
- action detection
- static images
- video dataset
- motion recognition
- motion patterns
- view invariant action recognition
- machine learning
- viewpoint
- space time interest points