This page is outdated please visit the new website

https://sims.unige.ch

Address

CUI
Computer Vision and Multimedia Laboratory
Battelle Bat. A
Rte de Drize 7
CH - 1227, Carouge (GE), Switzerland

Phone: +41 (22) 379 0183
Fax: +41 (22) 379 0250
Secretary: +41 (22) 379 0223

E-mail: guillaume[.]chanel[at]unige[.]ch

Office in Battelle: #227

Function

Maître-assistant (Senior researcher and lecturer) at the Swiss Center for Affective Sciences and Computer Vision and Multimedia Laboratory

Biography

Guillaume Chanel holds a Ph.D. in Computer science, University of Geneva, 2009, where he worked on machine learning for the automatic assessment of emotions based on EEG and peripheral signals. From 2009 to 2010 he was at the KML-Knowledge Media Laboratory, Aalto University, Helsinki, Finland, studying the physiological correlates of social processes taking place between players during video-gaming. Now a senior researcher and lecturer jointly affiliated with CISA and with CVML, his research investigates how machines can learn to behave in a social and affective environment. He is particularly interested in the use of multimodal and physiological measures for improving man-machine and human remote interactions. Examples of his research include: dynamic adjustment of games mechanic based on players' emotions, inclusion of physiological emotional cues in mediated social interactions, movie highlight detection based on spectators’ social reactions and adaptation of human social behaviors through machines.

Research

Research projects

Seconds that matter: Managing First Impressions for a more Engaging Virtual Agent

In any encounter the first moments are critical and the impressions that we form of others matter. These impressions tend to last and affect the interaction experience. The goal of this project is to build an anthropomorphic virtual character (ECA - Embodied Conversational Agent) able to make the best possible first impression on a user, thus effectively engaging him or her in an interaction. This goal will be realized by building an affective loop which ties the behavior of the ECA to the actual emotional reactions of the user facing it in real-time. This will give rise to an ECA capable of managing their first impressions on users. We focus on the identification and modeling of the nonverbal behavior, towards exhibiting, managing and maintaining impressions of two important socio-cognitive dimensions in the first minutes of interaction with a user. These dimensions are warmth (i.e. being friendly, agreeable, engaging and approachable) and competence (i.e. appear skilled, knowledgeable on a given topic). The IMPRESSIONS project has humanistic and computational components. The analysis and modeling of nonverbal communicative behavior is drawn from existing literature in sociology and psychology, as well as from new data gathered from controlled user studies. The computational component implements those models in a virtual agent, resulting in believable and effective social behaviors. Furthermore, user’s behaviors and physiological signals will help the agent managing the desired impressions. The analysis of multimodal signals is valuable to assess the user’s affective states, to determine the quality of the interaction, and, ultimately, for assessing the impressions that the user has formed of the agent. Results undergo a thorough user evaluation.

Emotional and aesthetic highlights detection in movies

Affective computing is now an important research area of computer science with existing ties with the humanities as is demonstrated by the activities in text sentiment analysis and affective tagging of movies. We plan to emphasize and develop these links with the humanities and namely with film studies, concentrating on one of the most popular media: the movies. In this project, we test the degree of emotional participation of the audience in film watching. How do viewers react to the sequences in a given movie that film critics and filmmakers consider as aesthetically successful and therefore emotionally relevant?. This project therefore aims at answering the following computer science research questions: (1) How to determine the users’ affective state from multimodal signals, in the context of real movie projection? (2) Can the information carried out from the physiological and behavioural signals of multiple spectators be utilised to predict the emotional and aesthetic value of movie scenes (highlights)? (3) Can a multimodal synchronization / highlight detection system be used in film studies to determine movie scenes with high aesthetic value?

EATMINT - Emotional awarness tools for mediated interaction

The project “Affective computing and emotion awareness in computer-mediated interaction” aims at developing emotion awareness tools (EAT) to improve the collaborative processes and outcomes of people working together through computers. In computer-mediated collaboration (CMC), it is rather difficult for people to recognize others’ emotions since emotional cues are limited. The project has two main objectives:

• to design and implement real time systems for automatic emotion awareness in CMC settings based on processing physiological and behavioral measurements. Such systems will continuously measure partners’ emotions and the quality of the ongoing interaction, and will display emotion awareness information so as to adapt to ongoing collaborative processes;
• to study the role of emotion awareness in CMC. EATs are expected to encourage collaborators to engage in strategies such as monitoring, regulating and reflecting on both their own- and their partner’s emotions and behaviors. We will thus analyze both the intra- and interpersonal effects of emotion awareness on collaboration, in different types of collaborative scenarios.

Other research activities

Reviewer for:

Has / will organize(d):

Teaching

Publications

I invite you to check my google scholar profile for publication downloads and to have the most recent list of publications.