Skeleton-based action recognition via spatial and temporal transformer networks.
Chiara PlizzariMarco CanniciMatteo MatteucciPublished in: Comput. Vis. Image Underst. (2021)
Keyphrases
- spatial and temporal
- action recognition
- spatial temporal
- spatio temporal
- human actions
- space time
- bag of words
- activity recognition
- body parts
- action classification
- human detection
- computer vision
- mid level
- recognition of human actions
- view invariant
- video frames
- human pose
- recognizing human actions
- recognizing actions
- image sequences
- dynamic textures
- human activities
- spatial and temporal information