Decoupled spatio-temporal grouping transformer for skeleton-based action recognition.
Shengkun SunZihao JiaYisheng ZhuGuangcan LiuZhengtao YuPublished in: Vis. Comput. (2024)
Keyphrases
- action recognition
- human actions
- spatio temporal
- spatio temporal interest points
- action recognition in videos
- spatial temporal
- view invariant
- recognition of human actions
- action classification
- bag of words
- human detection
- activity recognition
- spatial and temporal
- video dataset
- perceptual grouping
- space time
- body parts
- image sequences
- static images
- human activities
- mid level
- bag of features
- computer vision
- moving objects
- recognizing human actions
- recognizing actions
- human motion
- action primitives
- object recognition
- object detection