Temporal Transformer Networks with Self-Supervision for Action Recognition.
Yongkang ZhangJun LiGuoming WuHan ZhangZhiping ShiZhaoxun LiuZizhang WuPublished in: CoRR (2021)
Keyphrases
- action recognition
- spatial temporal
- bag of words
- human actions
- human detection
- action classification
- motion history images
- activity recognition
- recognition of human actions
- computer vision
- recognizing human actions
- spatial and temporal
- body parts
- human activities
- static images
- independent subspace analysis
- spatio temporal
- bag of features
- human pose
- video dataset
- depth cameras
- temporal reasoning
- view invariant
- action primitives
- recognizing actions
- multi camera
- max margin
- depth sensors
- active learning
- moving objects
- machine learning