jointly supported by

The European COST Action 2102 (www.cost2102.eu)

The euCognition network (www.euCognition.org )

Summary of the CONTENTS

1) Verbal and non verbal information in the face-to-face communication;

2) Cross modal analysis of speech, gestures, gaze and facial expressions;

3) Socio-cultural differences and personal traits;

4) Multimodal algorithms and procedures for the automatic recognition of emotions, faces, facial expressions, and gestures;

5) Audio and video features for implementing intelligent avatars and interactive dialogue systems.

6) Others.

AIMS

the school will be built on existing and growing connections between the emerging field of technology devoted to the development of intelligent avatars and interactive dialogue systems and the fundamentals of verbal and non verbal communication which includes facial expressions, tone of voice, gestures, eye contact, spatial arrangements, patterns of touch, expressive movement, cultural differences, and other "nonverbal" components. Several further key aspects will be considered, such as the integration of algorithms and procedures for the recognition of emotional states, gesture, speech and facial expressions, in anticipation of the implementation of useful applications that could be exploited to improve user access to future telecommunication services.

TARGET AUDIENCE

The school is oriented towards scientists, researchers and students working in the field of multimodal communication who are invited (COST 2102 MC members are particularly invited to contribute and /or report on COST 2102 activities) to submit short contributions to allow exchanges and discussions with the invited speakers.

ORGANIZATION

The school is organized as a series of lectures presented by the invited speakers, with short presentations given by the participants that will focus on recent developments and open problems in the field of multimodal signals in face-to-face interactions.