Autonomous social gaze model for an interactive virtual character in real-life settings

Abstract

This paper presents a gaze behavior model for an interactive virtual character situatedin the real world. We are interested in estimating which user has an intention tointeract, in other words which user is engaged with the virtual character. The modeltakes into account behavioral cues such as proximity, velocity, posture, and sound;estimates an engagement score; and drives the gaze behavior of the virtual character.Initially, we assign equal weights to these features. Using data collected in a realsetting, we analyze which features have higher importance. We found that the modelwith weighted features correlates better with the ground-truth data