Gaze-Based Virtual Task Predictor

Pen-based systems promise an intuitive and natural interaction paradigm for tablet PCs and stylus-enabled phones. However, typical pen-based interfaces require users to switch modes frequently in order to complete ordinary tasks. Mode switching is usually achieved through hard or soft modifier keys, buttons, and soft-menus. Frequent invocation of these auxiliary mode switching elements goes against the goal of intuitive, fluid, and natural interaction. In this paper, we present a gaze-based virtual task prediction system that has the potential to alleviate dependence on explicit mode switching in pen-based systems. In particular, we show that a range of virtual manipulation commands, that would otherwise require auxiliary mode switching elements, can be issued with an 80% success rate with the aid of users' natural eye gaze behavior during pen-only interaction.