Integrating Vision Transformer-Based Bilinear Pooling and Attention Network Fusion of RGB and Skeleton Features for Human Action Recognition.
Yaohui SunWeiyao XuXiaoyi YuJu GaoTing XiaPublished in: Int. J. Comput. Intell. Syst. (2023)
Keyphrases
- real time
- image features
- computer networks
- vision system
- multiple features
- wireless sensor networks
- fuzzy logic
- network structure
- data fusion
- computer vision
- topological features
- network model
- peer to peer
- co occurrence
- feature extraction
- image processing
- shape analysis
- color images
- extracted features
- distribution network
- fusion scheme
- person authentication