GazeMAE: General Representations of Eye Movements using a Micro-Macro Autoencoder

TL;DR

GazeMAE introduces a novel autoencoder-based method to learn stimuli-agnostic micro and macro eye movement representations, enabling accurate classification of demographic and biometric features from raw gaze data.

Contribution

The paper presents a new deep autoencoder framework that captures multi-scale eye movement features, improving classification performance and generalizability over previous methods.

Findings

Effective discrimination of gender and age groups from eye movements.

Outperforms previous biometric and stimulus classification methods.

Demonstrates robustness and applicability to real-world eye tracking data.

Abstract

Eye movements are intricate and dynamic events that contain a wealth of information about the subject and the stimuli. We propose an abstract representation of eye movements that preserve the important nuances in gaze behavior while being stimuli-agnostic. We consider eye movements as raw position and velocity signals and train separate deep temporal convolutional autoencoders. The autoencoders learn micro-scale and macro-scale representations that correspond to the fast and slow features of eye movements. We evaluate the joint representations with a linear classifier fitted on various classification tasks. Our work accurately discriminates between gender and age groups, and outperforms previous works on biometrics and stimuli clasification. Further experiments highlight the validity and generalizability of this method, bringing eye tracking research closer to real-world applications.