GazeMAE: General Representations of Eye Movements using a Micro-Macro Autoencoder
This work addresses the need for generalizable eye movement representations to advance eye tracking research toward real-world applications, though it is incremental as it builds on existing autoencoder techniques.
The authors tackled the problem of representing complex eye movements in a stimuli-agnostic way by training deep temporal convolutional autoencoders to learn micro- and macro-scale features, resulting in accurate classification of gender and age groups and outperforming previous methods on biometrics and stimuli classification tasks.
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.