SP-EyeGAN: Generating Synthetic Eye Movement Data with Generative Adversarial Networks
Open Access
- 30 May 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Abstract
Neural networks that process the raw eye-tracking signal can outperform traditional methods that operate on scanpaths preprocessed into fixations and saccades. However, the scarcity of such data poses a major challenge. We, therefore, present SP-EyeGAN, a neural network that generates synthetic raw eye-tracking data. SP-EyeGAN consists of Generative Adversarial Networks; it produces a sequence of gaze angles indistinguishable from human micro- and macro-movements. We demonstrate how the generated synthetic data can be used to pre-train a model using contrastive learning. This model is fine-tuned on labeled human data for the task of interest. We show that for the task of predicting reading comprehension from eye movements, this approach outperforms the previous state-of-the-art.Keywords
Funding Information
- German Federal Ministry of Education and Research (01|S20043)
This publication has 12 references indexed in Scilit:
- GazeBase, a large-scale, multi-stimulus, longitudinal eye movement datasetScientific Data, 2021
- Discrimination at the Intersection of Age, Race, and Gender: Evidence from an Eye‐Tracking ExperimentJournal of Policy Analysis and Management, 2021
- Eye movement synthesis2016
- Rendering of Eyes for Eye-Shape Registration and Gaze Estimation2015
- Eye movement synthesis with 1/ f pink noise2015
- Saliency-based Bayesian modeling of dynamic viewing of static scenes2014
- EyecatchACM Transactions on Graphics, 2012
- Live Speech Driven Head-and-Eye Motion GeneratorsIEEE Transactions on Visualization and Computer Graphics, 2012
- The E-Z Reader model of eye-movement control in reading: Comparisons to other modelsBehavioral and Brain Sciences, 2003
- Eyes alive2002