Auxiliary criterion conversion via spatiotemporal semantic encoding and feature entropy for action recognition.
Xiaoyan MengGuoliang ZhangSongmin JiaXiuzhi LiXiangyin ZhangPublished in: Vis. Comput. (2021)
Keyphrases
- action recognition
- motion features
- human actions
- computer vision
- human detection
- bag of words
- activity recognition
- mid level features
- action classification
- recognition of human actions
- bag of features
- body parts
- spatial temporal
- depth sensors
- view invariant
- recognizing human actions
- human activities
- space time
- static images
- independent subspace analysis
- object recognition
- human activity recognition
- spatial and temporal
- image features
- video dataset
- semantic information
- action recognition in videos
- view invariant action recognition