Learning Composite Latent Structures for 3D Human Action Representation and Recognition.
Ping WeiHongbin SunNanning ZhengPublished in: IEEE Trans. Multim. (2019)
Keyphrases
- action recognition
- learning process
- learning algorithm
- active learning
- human actions
- activity recognition
- unsupervised learning
- video sequences
- object recognition
- spatio temporal
- information retrieval
- reinforcement learning
- prior knowledge
- feature extraction
- latent variables
- supervised learning
- image representation
- image sequences
- human activities
- computer vision
- view invariant
- recognizing human actions