5 papers with code • 2 benchmarks • 1 datasets
Learning to Predict Sequences of Human Fixations.
The first part of the network consists of a model trained to generate saliency volumes, whose parameters are fit by back-propagation computed from a binary cross entropy (BCE) loss over downsampled versions of the saliency volumes.
We introduce PathGAN, a deep neural network for visual scanpath prediction trained on adversarial examples.
Attention supports our urge to forage on social cues.