Multiple depth-levels features fusion enhanced network for action recognition.
Shengquan WangJun KongMin JiangTianshan LiuPublished in: J. Vis. Commun. Image Represent. (2020)
Keyphrases
- action recognition
- depth cameras
- depth sensors
- bag of features
- static images
- activity recognition
- human movements
- human actions
- bag of words
- motion features
- spatial temporal
- human detection
- feature space
- mid level
- action classification
- deformable part models
- feature extraction
- computer vision
- body parts
- multiple features
- view invariant
- space time interest points
- action primitives
- motion history images
- action detection
- image features
- human pose
- co occurrence
- low level
- human motion
- feature vectors
- depth information
- feature descriptors
- recognizing actions
- salient features