Understanding how humans move their eyes to gather visual information is a central question in neuroscience, cognitive science, and vision research. While recent deep learning (DL) models achieve state-of-the-art performance in predicting human scanpaths, their underlying decision processes remain opaque. At an opposite end of the modeling spectrum, cognitively inspired mechanistic models aim to explain scanpath behavior through interpretable cognitive mechanisms but lag far behind in predictive accuracy. In this work, we bridge this gap by using a high-performing deep model—DeepGaze III—to discover and test mechanisms that improve a leading mechanistic model, SceneWalk. By identifying individual fixations where DeepGaze III succeeds and SceneWalk fails, we isolate behaviorally meaningful discrepancies and use them to motivate targeted extensions of the mechanistic framework. These include time-dependent temperature scaling, saccadic momentum and an adaptive cardinal attention bias: Simple, interpretable additions that substantially boost predictive performance. With these extensions, SceneWalk’s explained variance on the MIT1003 dataset doubles from 35% to 70%, setting a new state of the art in mechanistic scanpath prediction. Our findings show how performance-optimized neural networks can serve as tools for cognitive model discovery, offering a new path toward interpretable and high-performing models of visual behavior. Our code is available at https://github.com/bethgelab/what-moves-the-eyes

Biometric recognition systems are an integral part of security in modern computer systems. Contrary to related work, our approach to biometrics does not base on individual patterns in sensor data. We measure visual self-recognition as an in-brain identity validation mechanism and aim to employ it as a biometric trait. This work builds on a public data set of an eye-tracking study investigating the visual self-recognition of 116 volunteers. Exploration of this high-quality data revealed significant effects of self-recognition in the time course of pupil size and microsaccade generation. These findings facilitated the extraction of features to train four different experimental classification models. The best-performing model is a pre-trained classifier on integrated data by achieving an accuracy of 0.82. Our research supports the hypothesis that self-recognition can be a feasible biometric trait. Furthermore, we found that self-recognition can be measured using eye-tracking devices. Future work on model optimization and additional feature extraction is required. It will enable to introduce technologies utilizing self-recognition to real-world applications.

We study the problem of identifying viewers of arbitrary images based on their eye gaze. Psychological research has derived generative stochastic models of eye movements. In order to exploit this background knowledge within a discriminatively trained classification model, we derive Fisher kernels from different generative models of eye gaze. Experimentally, we find that the performance of the classifier strongly depends on the underlying generative model. Using an SVM with Fisher kernel improves the classification performance over the underlying generative model.

Understanding the decision process underlying gaze control is an important question in cognitive neuroscience with applications in diverse fields ranging from psychology to computer vision. The decision for choosing an upcoming saccade target can be framed as a selection process between two states: Should the observer further inspect the information near the current gaze position (local attention) or continue with exploration of other patches of the given scene (global attention)? Here we propose and investigate a mathematical model motivated by switching between these two attentional states during scene viewing. The model is derived from a minimal set of assumptions that generates realistic eye movement behavior. We implemented a Bayesian approach for model parameter inference based on the model's likelihood function. In order to simplify the inference, we applied data augmentation methods that allowed the use of conjugate priors and the construction of an efficient Gibbs sampler. This approach turned out to be numerically efficient and permitted fitting interindividual differences in saccade statistics. Thus, the main contribution of our modeling approach is two-fold; first, we propose a new model for saccade generation in scene viewing. Second, we demonstrate the use of novel methods from Bayesian inference in the field of scan path modeling.