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.
@article{arxiv.2003.11399,
title = {Discriminative Viewer Identification using Generative Models of Eye Gaze},
author = {Silvia Makowski and Lena A. Jäger and Lisa Schwetlick and Hans Trukenbrod and Ralf Engbert and Tobias Scheffer},
journal= {arXiv preprint arXiv:2003.11399},
year = {2020}
}