Augmented two stream network for robust action recognition adaptive to various action videos.
Chuanjiang LengQichuan DingChengdong WuAnge ChenPublished in: J. Vis. Commun. Image Represent. (2021)
Keyphrases
- action recognition
- human actions
- view invariant
- action classification
- recognizing human actions
- recognizing actions
- recognition of human actions
- action detection
- space time interest points
- spatio temporal interest points
- spatio temporal
- video dataset
- bag of words
- ucf sports
- human activities
- activity recognition
- computer vision
- spatial temporal
- bag of features
- action primitives
- single view
- multi view
- human detection
- video sequences
- body parts
- human motion
- motion features
- robust tracking
- static images
- wireless sensor networks
- motion recognition
- space time
- mid level features
- depth sensors
- image classification
- data streams