ResSaNet: A Hybrid Backbone of Residual Block and Self-Attention Module for Masked Face Recognition.
Wei-Yi ChangMing-Ying TsaiShih-Chieh LoPublished in: ICCVW (2021)
Keyphrases
- face recognition
- face images
- focus of attention
- discriminant analysis
- principal component analysis
- feedback loop
- face identification
- multiresolution
- face databases
- linear discriminant analysis
- residual signal
- block wise
- block size
- image blocks
- facial images
- recognition accuracy
- database
- human faces
- sparse representation
- recognition rate
- support vector
- feature extraction
- image sequences
- computer vision