Cross-enhancement transform two-stream 3D ConvNets for action recognition.
Dong CaoLisha XuDongdong ZhangPublished in: AIIPCC (2019)
Keyphrases
- action recognition
- feed forward
- human actions
- bag of words
- human detection
- action classification
- activity recognition
- body parts
- back propagation
- spatial temporal
- data streams
- computer vision
- static images
- neural network
- recognition of human actions
- human activities
- sliding window
- artificial neural networks
- depth sensors
- recognizing human actions
- action detection
- action primitives
- recognizing actions
- bag of features
- stream processing
- latent variables
- video dataset
- view invariant action recognition