Cross-scale cascade transformer for multimodal human action recognition.
Zhen LiuQin ChengChengqun SongJun ChengPublished in: Pattern Recognit. Lett. (2023)
Keyphrases
- action recognition
- static images
- human movements
- human actions
- spatio temporal interest points
- human activities
- spatial temporal
- human detection
- computer vision
- motion history images
- action classification
- activity recognition
- bag of words
- body parts
- motion capture data
- human object interactions
- recognition of human actions
- recognizing actions
- depth sensors
- human pose
- view invariant
- bag of features
- action primitives
- recognizing human actions
- video dataset
- human motion
- scale space
- low level
- multiscale