The purpose of this work is to evaluate the contribution of audio-visual prosody to the perception of complex mental states of virtual actors. We propose that global audio-visual prosodic contours - i.e. melody, rhythm and head movements over the utterance - constitute discriminant features for both the generation and recognition of social attitudes. The hypothesis is tested on an acted corpus of social attitudes in virtual actors and evaluation is done using objective measures and perceptual tests.

Digital shadowing is a source of interest in immersive and interactive artworks because it enhances the feeling of presence, and because it is a very intuitive and engaging interaction "device." After a presentation of some major pieces in shadow-based artwork along two categories (silhouette-based digital shadows and cast shadow-based digital shadows), we propose a real-time software platform that can produce these two types of shadows from video capture and image processing. The processing is divided into image analysis for shadow extraction, calibration, and special effects. It is made highly flexible and parameterized, so that it can fit various configurations. Two specific configurations are illustrated because of their genericity: one for infrared light silhouette-based shadow and live performance, and one for both digital shadowing categories and interactive art installations with visible light. We then present some of the applications of such a platform through various live performances made by two theater companies involved in a collaborative project with scientists. The examples confirm the wide variety of scenographic setups in which shadow can be involved as a key component.