Multi-views reinforced LSTM for video-based action recognition.
Zhenzhen MaoMin JiangJun KongPublished in: J. Electronic Imaging (2021)
Keyphrases
- action recognition
- multi views
- multi view
- d objects
- face recognition
- bag of words
- activity recognition
- human actions
- human detection
- action classification
- computer vision
- spatial temporal
- body parts
- bag of features
- human activities
- independent subspace analysis
- human pose
- video dataset
- view invariant
- recognizing human actions
- viewpoint
- action detection
- three dimensional
- machine learning
- pose estimation
- mid level
- static images
- motion features
- depth cameras
- recognizing actions