Modeling the Relative Visual Tempo for Self-supervised Skeleton-based Action Recognition.
Yisheng ZhuHu HanZhengtao YuGuangcan LiuPublished in: ICCV (2023)
Keyphrases
- action recognition
- mid level
- human actions
- bag of words
- activity recognition
- computer vision
- action classification
- human detection
- recognizing human actions
- spatial temporal
- body parts
- recognition of human actions
- multiscale
- human object interactions
- visual information
- human pose
- depth sensors
- visual features
- image classification
- recognizing actions
- action detection
- bag of features
- human activities
- bag of visual words
- video dataset
- view invariant
- action primitives
- image retrieval
- view invariant action recognition