Two-stream siamese network with contrastive-center losses for RGB-D action recognition.
Chunxiao FanZhengyuan ZhaiYue MingLei TianPublished in: J. Electronic Imaging (2019)
Keyphrases
- action recognition
- human actions
- bag of words
- activity recognition
- action classification
- depth cameras
- computer vision
- spatial temporal
- human detection
- static images
- recognition of human actions
- action primitives
- view invariant
- body parts
- recognizing human actions
- action detection
- human pose
- wireless sensor networks
- bag of features
- action recognition in videos
- view invariant action recognition
- spatio temporal
- video sequences
- three dimensional
- machine learning
- depth sensors
- motion history images
- object segmentation
- recognizing actions
- human activities