English
The SignCom project aims to improve the quality of the real-time interaction between real humans and virtual agents, by exploiting natural communication modalities such as gestures, facial expressions and gaze direction. Based on gestural languages highly structured and coded, the real and virtual humans produce statements towards their interlocutor through a dialog model. Gestures of the user, previously recorded by motion capture techniques, are used on the one hand to facilitate the vision-based recognition of gestures in real-time, and on the other hand to drive the character's animation.
