Sparse Dense Transformer Network for Video Action Recognition.
Xiaochun QuZheyuan ZhangWei XiaoJinye RanGuodong WangZili ZhangPublished in: KSEM (2) (2022)
Keyphrases
- action recognition
- human actions
- action classification
- spatial temporal
- video dataset
- action detection
- bag of words
- static images
- recognizing human actions
- recognition of human actions
- motion features
- human activities
- mid level
- computer vision
- activity recognition
- video sequences
- space time interest points
- human detection
- motion history images
- multimedia
- view invariant
- human pose
- body parts
- action primitives
- sparse representation
- recognizing actions
- space time
- spatio temporal
- human activity recognition
- video retrieval
- depth sensors
- video frames
- view invariant action recognition