# Simulating Human Gaze with Neural Visual Attention

arXiv: https://arxiv.org/abs/2211.12100 · HTML: https://mlsanity.com/paper/2211.12100/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 24 references that are in the map.
- First posted on arXiv 22 Nov 2022.

## Builds on (most cited first, 5 of 5)

- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?](https://mlsanity.com/paper/1606.03556/) (2016)
- [Toward Improving the Evaluation of Visual Attention Models: a Crowdsourcing Approach](https://mlsanity.com/paper/2002.04407/) (2020)
- [Gravitational Models Explain Shifts on Human Visual Attention](https://mlsanity.com/paper/2009.06963/) (2020)

## Built on by (most cited first, 1 of 1)

- [SPGen: Stochastic scanpath generation for paintings using unsupervised domain adaptation](https://mlsanity.com/paper/2602.22049/) (2026)

## Abstract (arXiv)

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 that biologically constrained neural networks generate human-like scanpaths without being trained for this objective. Extensive experiments on three common benchmark datasets show that our method outperforms state-of-the-art unsupervised human attention models in generating human-like scanpaths.