Multi-Attention Transformer for Naturalistic Driving Action Recognition.
Xiaodong DongRuijie ZhaoHao SunDong WuJin WangXuyang ZhouJiang LiuShun CuiZhongjiang HePublished in: CVPR Workshops (2023)
Keyphrases
- action recognition
- static images
- human actions
- bag of words
- action classification
- activity recognition
- human detection
- recognizing human actions
- spatial temporal
- recognition of human actions
- body parts
- computer vision
- human pose
- bag of features
- video dataset
- depth sensors
- action primitives
- motion features
- independent subspace analysis
- view invariant
- action detection
- recognizing actions
- view invariant action recognition
- human activities
- depth cameras
- human activity recognition
- spatio temporal
- viewpoint