July 18, 2010 to July 22, 2010
1Ø PLUS/VIPS ADVANCED SCHOOL ON COMPUTER VISION,
PATTERN RECOGNITION, AND IMAGE PROCESSING
July 18-22, 2010 – Sestri Levante (GE), Italy
This school follows the series of intensive courses, aimed at PhD
students and researchers in the areas of Computer Vision, Image
Processing, and Pattern Recognition.
It is organized and sponsored by the PLUS (Pattern analysis, Learning,
and image Understanding) laboratory of the Istituto Italiano di
Tecnologia, Genova (Italy) jointly with the VIPS (Vision, Image
Processing, and Sound) lab of the University of Verona.
The course is residential, spanning 5 days, so that attendees can
install a more productive interaction with the lecturers.
Course Title
SOCIAL SIGNAL PROCESSING: STATE OF THE ART AND PROSPECTS
———————————————————
Speakers
* Daniel Gatica-Perez
IDIAP, Switzerland
* Alessandro Vinciarelli
University of Glasgow (Scotland)
This course is an introduction to Social Signal Processing, the field
aimed at bridging the social intelligence gap between people and
machines. At its core, social intelligence consists of sensing nonverbal
behavioral cues displayed by people around us (facial expressions,
gestures, vocalizations, postures), interpreting these cues in terms of
social signals (relational attitudes like interest, hostility, empathy,
agreement and disagreement, or dominance), and displaying as a response
natural, consistent behaviors (interest for those we are interested in,
or hostility for those we are hostile to).
From a scientific point of view, this results into three core objectives:
1) Detection of nonverbal behavioral cues using sensors including
microphones, cameras, proximity detectors, or others.
2) Inference of social signals from nonverbal behavioral cues.
3) Synthesis of social signals through different forms of embodiment in
artificial agents, avatars, or synthetic voices.
The course focuses on the first two questions and provides an
introduction to the main scientific and technological problems and the
existing work for two major scenarios, namely face-to-face interaction
(meetings, conversations, etc.) and large scale social interaction
(daily life of populations sensed with mobile devices).
This interdisciplinary research has the potential of significantly
advancing several domains related to automatic monitoring, including
video surveillance, ambient intelligence, marketing, office space
design, and architecture and urbanism.
Course Program
—————-
Part I – Automatic Analysis Face-to-Face Interactions
Introduction
- Fundamentals of Nonverbal Behavior Analysis
- Social Signal Processing
Methodology
- Bayesian Decision Theory
- Naive Bayes Classifiers
- Maximum Entropy Models
- Hidden Markov Models
- Conditional Random Fields
Applications
- Extraction of nonverbal cues from speech
- Inference of social phenomena from turn-taking patters
- Inference of socially relevant information from prosody
- Inference of social phenomena from audiovisual cues
Part II – Large-scale social behavior modeling
- Behavioral cues at large scale
- Models for analysis of large-scale behavior
- Existing research and open problems
**************************************************
**** Registration deadline is 30th April 2010 ****
**************************************************
Late applications will still be considered on a single basis.
Director:
Prof. Vittorio Murino
Local Organizers and Program Managers:
Prof. Vittorio Murino, Marco Cristani, Manuele Bicego, Alessio Del Bue,
Reza Sabzevari, Michele Stoppa, Pietro Salvagnini
More information:
http://sspluschool.wordpress.com
Copyright © 2012