GazeIntent: Adapting Dwell-time Selection in VR Interaction with Real-time Intent Modeling

• DOI: 10.1145/3655600
• Publication Date: 2024-05-28T20:00:05Z
• Authors: Anish S. Narkar; Jan J. Michalak; Candace E. Peacock; Brendan David-John
• Keywords: Dwell time

The use of ML models to predict a user's cognitive state from behavioral data has been studied for various applications which includes predicting the intent perform selections in VR. We developed novel technique that uses gaze-based adapt dwell-time thresholds aid gaze-only selection. A dataset users performing selection arithmetic tasks was used develop prediction (F1 = 0.94). GazeIntent dwell times based on model outputs and conducted an end-user study with returning new additional varied frequencies. Personalized effectively accounted prior experience were preferred by 63% users. Our work provides field methods dwell-based users, account over time, consider vary frequency.