Gender and ethnicity recognition based on visual attention-driven deep architectures.
Souad Khellat-KihelJawad MuhammadZhenan SunMassimo TistarelliPublished in: J. Vis. Commun. Image Represent. (2022)
Keyphrases
- visual attention
- deep architectures
- visual perception
- visual search
- saliency map
- eye tracking
- focus of attention
- eye movements
- visual attention model
- unsupervised learning
- vision system
- object recognition
- higher level
- deep learning
- attention mechanism
- salient regions
- visual saliency
- object based visual attention
- feature extraction
- low level
- real time
- action recognition
- higher order
- pairwise
- image processing