Simulating Human Gaze with Neural Visual Attention. (arXiv:2211.12100v1 [cs.CV])

Existing models of human visual attention are generally unable to incorporate
direct task guidance and therefore cannot model an intent or goal when
exploring a scene. To integrate guidance of any downstream visual task into
attention modeling, we propose the Neural Visual Attention (NeVA) algorithm. To
this end, we impose to neural networks the biological constraint of foveated
vision and train an attention mechanism to generate visual explorations that
maximize the performance with respect to the downstream task. We observe …

arxiv attention human visual attention