# Look Twice: A Generalist Computational Model Predicts Return Fixations across Tasks and Species

arXiv: https://arxiv.org/abs/2101.01611 · HTML: https://mlsanity.com/paper/2101.01611/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 83 references that are in the map.
- First posted on arXiv 5 Jan 2021.

## Builds on (most cited first, 11 of 11)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [DeepFix: A Fully Convolutional Neural Network for predicting Human Eye Fixations](https://mlsanity.com/paper/1510.02927/) (2015)
- [Putting visual object recognition in context](https://mlsanity.com/paper/1911.07349/) (2019)
- [Finding any Waldo: zero-shot invariant and efficient visual search](https://mlsanity.com/paper/1807.10587/) (2018)
- [Recurrent computations for visual pattern completion](https://mlsanity.com/paper/1706.02240/) (2017)
- [Spatial statistics and attentional dynamics in scene viewing](https://mlsanity.com/paper/1405.3270/) (2014)
- [Likelihood-based Parameter Estimation and Comparison of Dynamical Cognitive Models](https://mlsanity.com/paper/1606.07309/) (2016)
- [A normalization model of visual search predicts single trial human fixations in an object search task](https://mlsanity.com/paper/1404.6453/) (2014)
- [Searchers adjust their eye movement dynamics to the target characteristics in natural scenes](https://mlsanity.com/paper/1802.04069/) (2018)

## Built on by (most cited first, 8 of 8)

- [Training-free Object Counting with Prompts](https://mlsanity.com/paper/2307.00038/) (2023)
- [OmniCount: Multi-label Object Counting with Semantic-Geometric Priors](https://mlsanity.com/paper/2403.05435/) (2024)
- [Peering into the Unknown: Active View Selection with Neural Uncertainty Maps for 3D Reconstruction](https://mlsanity.com/paper/2506.14856/) (2025)
- [Pose Prior Learner: Unsupervised Categorical Prior Learning for Pose Estimation](https://mlsanity.com/paper/2410.03858/) (2024)
- [TPP-Gaze: Modelling Gaze Dynamics in Space and Time with Neural Temporal Point Processes](https://mlsanity.com/paper/2410.23409/) (2024)
- [Learning to See Through a Baby's Eyes: Early Visual Diets Enable Robust Visual Intelligence in Humans and Machines](https://mlsanity.com/paper/2511.14440/) (2025)
- [Learning to See the Elephant in the Room: Self-Supervised Context Reasoning in Humans and AI](https://mlsanity.com/paper/2211.12817/) (2022)
- [Gazing at Rewards: Eye Movements as a Lens into Human and AI Decision-Making in Hybrid Visual Foraging](https://mlsanity.com/paper/2411.09176/) (2024)

## Abstract (arXiv)

Primates constantly explore their surroundings via saccadic eye movements that bring different parts of an image into high resolution. In addition to exploring new regions in the visual field, primates also make frequent return fixations, revisiting previously foveated locations. We systematically studied a total of 44,328 return fixations out of 217,440 fixations. Return fixations were ubiquitous across different behavioral tasks, in monkeys and humans, both when subjects viewed static images and when subjects performed natural behaviors. Return fixations locations were consistent across subjects, tended to occur within short temporal offsets, and typically followed a 180-degree turn in saccadic direction. To understand the origin of return fixations, we propose a proof-of-principle, biologically-inspired and image-computable neural network model. The model combines five key modules: an image feature extractor, bottom-up saliency cues, task-relevant visual features, finite inhibition-of-return, and saccade size constraints. Even though there are no free parameters that are fine-tuned for each specific task, species, or condition, the model produces fixation sequences resembling the universal properties of return fixations. These results provide initial steps towards a mechanistic understanding of the trade-off between rapid foveal recognition and the need to scrutinize previous fixation locations.