General Interest: Computational social science, Multimodal signal processing, Machine learning

Current Research:  Computational modeling of face-to-face social interaction using nonverbal behavioral cues

The computational modeling of face-to-face interactions using nonverbal behavioral cues is an emerging and relevant problem in social computing. Studying face-to-face interactions in small groups helps in understanding the basic processes of individual and group behavior; and improving team productivity and satisfaction in the modern workplace. Apart from the verbal channel, nonverbal behavioral cues form a rich communication channel through which people infer - often automatically and unconsciously - emotions, relationships, and traits of fellow members.

I am interested in analyzing nonverbal behavioral cues from stationary sensors - cameras and microphones, or wearable sensors such as sociometers, or mobile sensors on a humanoid robot like Nao.

In order to capture the variable of interest and the inherant uncertainty in the measurement, probabilisitic graphical models are an excellant framework. My current interest is to apply and develop the best-suited graphical models for human-human and human-robot applications.


Supervised by:

Daniel Gatica Perez ( http://www.idiap.ch/~gatica/ )

Jean-Marc( http://www.idiap.ch/~odobez/)

Present Collaborators:

Kazuhiro: http://www.brl.ntt.co.jp/people/otsuka/

Past Collaborators:

Taemie: http://web.media.mit.edu/~taemie/
Hailey: http://staff.science.uva.nl/~hhung1/
Sileye: http://perso.telecom-bretagne.eu/sileyeba/
Bogdan: http://www.cvc.uab.es/~bogdan/
Andreas: http://www.unifr.ch/psycho/site/units/ke/equipe/sonderegger/
Denis: diuf.unifr.ch/people/lalanned/

Labs of interest:

http://ase.tufts.edu/psychology/ambady/people.html
http://pac.cs.dartmouth.edu/
http://projects.ict.usc.edu/multicomp/?page_id=26
http://www.cs.cmu.edu/~ftorre/