Motion Modeling for Expressive Interaction

While human-human or human-object interactions involve very rich, complex and nuanced gestures, gestures as they are captured for human-computer interaction remain relatively simplistic. Our approach is to consider the study of variation of motion input as a way of understanding expression and expressivity in human-computer interaction and in order to propose computational solutions for capturing and using these expressive variations. The paper reports an attempt at drawing the lines of design guidelines for modeling systems adapting to motion variations. We propose to illustrate them through two case studies: the first model is used to estimate temporal and geometrical motion variations while the second is used to track variations of motion dynamics. These case studies are illustrated in two applications