Skeleton Sequence and RGB Frame Based Multi-Modality Feature Fusion Network for Action Recognition.
Xiaoguang ZhuYe ZhuHaoyu WangHonglin WenYan YanPeilin LiuPublished in: CoRR (2022)
Keyphrases
- action recognition
- multi modality
- feature fusion
- multi modal
- human actions
- bag of words
- medical images
- activity recognition
- information theoretic
- image registration
- multiple features
- computer vision
- feature extraction
- human activities
- object recognition
- mutual information
- image processing
- shape analysis
- machine learning