Deep Convolutional Symmetric Encoder - Decoder Neural Networks to Predict Students' Visual Attention.
Tomasz HachajAnna StolinskaMagdalena AndrzejewskaPiotr CzerskiPublished in: Symmetry (2021)
Keyphrases
- visual attention
- neural network
- video codec
- eye movements
- saliency map
- eye tracking
- deep learning
- decoding process
- low complexity
- focus of attention
- vision system
- visual search
- distributed video coding
- visual perception
- visual attention model
- noisy channel
- successive approximation
- attention mechanism
- wyner ziv video coding
- salient regions
- back propagation
- error control
- motion estimation
- rate distortion
- object based visual attention
- real time
- biological vision systems
- video compression
- motion compensation
- visual information
- motion compensated
- visual scene
- visual input
- wyner ziv
- video quality
- feed forward
- deep belief networks
- video coding
- bit rate
- distributed source coding
- higher level
- natural images
- high level