Data Science Seminar

Le 5 octobre 2017 à Télécom Paris / Barrault. Séminaire entièrement en anglais.
The LTCI Data Science Seminar is a joint research seminar between the DIG and the S2A teams. It focuses on machine learning and data science topics.

October 5, 2017

The seminar took place from 2PM to 4PM in Amphi Grenat, and featured two talks:

Talk 1: Giovanna Varni (Télécom Paris): Automated analysis of socio-affective signals in interpersonal interaction

The slides for this talk were not shared by the speaker.

Abstract: The establishment of interpersonal interaction, understood as human-human and human-machine interaction, grounds on the skills to exchange and manage verbal and nonverbal socio-affective signals. Becoming an effective partner in interaction requires, first, the perception and the understanding of these signals and, then, a continuous adaptation of one’s own signals by predicting the future development of the interaction. Endowing systems and artificial agents with the skill to automatically analyze these signals and their dynamics is not a trivial task both offline and on the fly. Still, this is a crucial challenge for improving the effectiveness and naturalness of human-artificial agent interaction in several scenarios e.g. education, manufacturing industries, assistive technology and so on.

In this talk, I report my recent works on Social Signals Processing and Affective Computing with particular reference to laughter, emotional interdependence and personality traits. These works were performed in the framework of European and national French projects.

Talk 2: James Eagan (Télécom Paris): Reinventing the mind’s bicycle

The slides for this talk were not shared by the speaker.

Abstract: Steve Jobs once described the computer as “a bicycle for the mind.” My work focuses on making this bicycle a better, more expressive tool for humans: by making richer, more expressive interactions, by reinventing how we build software so users can adapt it to their own idiosyncratic needs, and by providing richer tools to interact with and understand data. In this talk, I will present an overview of my work in these three areas.

Bio: James Eagan is an Associate Professor (maître de conférences) in the DIVA group at Télécom Paris <> with a research focus on Human-Computer Interaction and Information Visualization. He is also co-chair of the MS Big Data program. Before joining Télécom Paris, he was a post-doctoral researcher at LRI (CNRS & Université Paris-Sud). He holds a Ph.D. and M.Sc. in Computer Science from the Georgia Institute of Technology and B.A. in Mathematics/Computer Science from Lawrence University.