Abstract
Eye movements are rich but ambiguous biosignals that usually require a meticulous selection of features. We instead propose to learn feature representations of eye movements in a self-supervised manner. We adopt a contrastive learning approach and a set of data transformations that enable a deep neural network to discern salient and granular gaze patterns. We evaluate on six eye-tracking data sets and assess the learned features on biometric tasks. We achieve accuracies as high as 97.3%. Our work provides insights into a general representation learning method not only for eye movements but also possibly for similar biosignals.
Abstract (translated)
URL
https://arxiv.org/abs/2010.13046