Multi-channels CNN temporal features for depth-based action recognition.
Jacek TrelinskiBogdan KwolekPublished in: ICMV (2019)
Keyphrases
- action recognition
- depth sensors
- bag of words
- human actions
- depth cameras
- activity recognition
- human detection
- spatial temporal
- action classification
- body parts
- computer vision
- recognition of human actions
- recognizing actions
- recognizing human actions
- depth information
- action detection
- bag of features
- human activities
- view invariant
- action primitives
- human pose
- depth data
- static images
- machine learning
- motion features
- mid level
- depth images
- depth map
- action recognition in videos