MTT: Multi-Scale Temporal Transformer for Skeleton-Based Action Recognition.
Jun KongYuhang BianMin JiangPublished in: IEEE Signal Process. Lett. (2022)
Keyphrases
- action recognition
- multiscale
- spatial temporal
- human actions
- motion history images
- activity recognition
- computer vision
- action classification
- bag of words
- human detection
- spatio temporal
- recognizing human actions
- recognition of human actions
- temporal information
- static images
- human activities
- body parts
- temporal relations
- independent subspace analysis
- depth sensors
- action detection
- image processing
- human pose
- keypoints
- scale space
- image segmentation
- view invariant
- bag of features
- space time
- view invariant action recognition