Litcius/Paper detail

Decoding Task From Oculomotor Behavior In Virtual Reality

Ashima Keshava, Anete Aumeistere, Krzysztof Izdebski, Peter König

2020ACM Symposium on Eye Tracking Research and Applications16 citationsDOI

Abstract

In the present study, we aim to explore whether and how well we can predict tasks based on eye movements in a virtual environment. We designed four different tasks in which participants had to align two cubes of different sizes. To define where participants looked, we used a ray-based method to calculate the point-of-regard (POR) on each cube at each time point. Using leave-one-subject-out cross-validation, our model performed well with an f1-score of 0.51 ± 0.17 (chance level 0.25) in predicting the four alignment types. Results suggest that the type of task can be decoded based on the aggregation of PORs. We further discuss the implications of object size on task inference and thus set an exciting road-map for how to design intention recognition experiments in virtual reality.

Topics & Concepts

Computer scienceTask (project management)Decoding methodsVirtual realityPoint (geometry)Object (grammar)InferenceSet (abstract data type)Human–computer interactionArtificial intelligenceCube (algebra)Computer visionAlgorithmMathematicsCombinatoricsEconomicsManagementGeometryProgramming languageGaze Tracking and Assistive TechnologyVisual perception and processing mechanismsNeural and Behavioral Psychology Studies
Decoding Task From Oculomotor Behavior In Virtual Reality | Litcius