Gaze Prediction as a Function of Eye Movement Type and Individual Differences

TL;DR

This study investigates how individual differences and eye movement types affect gaze prediction accuracy across different models, highlighting the importance of personalized approaches and variability reporting in eye-tracking systems.

Contribution

It introduces a comparative analysis of three distinct gaze prediction models across various eye-movement types, emphasizing subject variability and proposing directions for personalized improvements.

Findings

Significant subject-to-subject variation in gaze prediction performance.

Fixation noise correlates with poorer prediction during fixations.

Higher saccade velocities are linked to decreased prediction accuracy.

Abstract

Eye movement prediction is a promising area of research with the potential to improve performance and the user experience of systems based on eye-tracking technology. In this study, we analyze individual differences in gaze prediction performance. We use three fundamentally different models within the analysis: the lightweight Long Short-Term Memory network (LSTM), the transformer-based network for multivariate time series representation learning (TST), and the Oculomotor Plant Mathematical Model wrapped in the Kalman Filter framework (OPKF). Each solution was assessed on different eye-movement types. We show important subject-to-subject variation for all models and eye-movement types. We found that fixation noise is associated with poorer gaze prediction in fixation. For saccades, higher velocities are associated with poorer gaze prediction performance. We think these individual differences are important and propose that future research should report statistics related to inter-subject variation. We also propose that future models should be designed to reduce subject-to-subject variation.