Home
Call for Papers
Important News
Paper Submission
Conference Registration
Presenter Instructions

Final Program
Flyer S+SSPR 2010
Special Session
Invited Speakers

Travel and Transportation
Arrival Instructions
Tours

Videolectures

Important Dates
Mar 1: Extended Paper Submission Deadline
Apr 17: Notification of acceptance
May 10: Submission of camera-ready papers
Early Author Registration
Aug 18-20: Workshops

S+SSPR is qualified as A in the CORE Conference Ranking.

Special Session at S+SSPR 2010


SIMILARITY-BASED PATTERN RECOGNITION: CHALLENGES AND PROSPECTS


Saturday, August 21, 2010

Cesme, Izmir, Turkey


Traditional pattern recognition techniques are centered around the notion of "feature". According to this view, the objects to be classified are represented in terms of properties that are intrinsic to the object itself. Hence, a typical pattern recognition system makes its decisions by simply looking at one or more feature vectors provided as input. The strength of this approach is that it can leverage a wide range of mathematical tools ranging from statistics, to geometry, to optimization. However, in many real-world applications a feasible feature-based description of objects might be difficult to obtain or inefficient for learning purposes. In these cases, it is often possible to obtain a measure of the (dis)similarity of the objects to be classified, and in some applications the use of dissimilarities (rather than features) makes the problem more viable. In the last few years, researchers in pattern recognition and machine learning are becoming increasingly aware of the importance of similarity information per se. Indeed, by abandoning the realm of vectorial representations one is confronted with the challenging problem of dealing with (dis)similarities that do not necessarily obey the requirements of a metric. This undermines the very foundations of traditional pattern recognition theories and algorithms, and poses totally new theoretical and computational questions.


The SIMBAD project is a EU FP7 project which aims at undertaking a thorough study of several aspects of purely similarity-based pattern analysis and recognition methods, from the theoretical, computational, and applicative perspective. It aims at covering a wide range of problems and perspectives, including supervised and unsupervised learning, generative and discriminative models, and its interest ranges from purely theoretical problems to real-world practical applications.


The SIMBAD consortium is planning to hold a half-day meeting on these topics within the S+SSPR Workshop on the morning of Saturday, 21 August 2010. The meeting will contain the following elements:


a) Presentations from the SIMBAD project about methodologies and philosophies in similarity-based pattern recognition, and the challenges it offers as a subfield in pattern recognition;


b) a panel session involving invited speakers;


c) a session of contributed position papers and poster spotlights.


d) a poster session on specific methods and techniques.


Topics of interest for contributed papers include (but are not limited to):



The workshop aims to explore the spectrum of alternative approaches, methodologies and challenges in the area, rather than detailed techniques. Contributions can be of two kinds:


a) position papers that aim to stimulate discussion of the philosophy of approach underpinning the field,


b) individual technical contributions on a focused topic.


We aim to have a 90 minute oral session devoted to the contributed position papers and together with shorter spotlights for the technical papers. There will be an open poster session for technical papers, with an opportunity to present a five minute 'spotlight' talk. Since there is no published proceedings, authors should feel free to provide position papers or posters on previously published work.


Prospective particpants should send a one-page abstract to


Marcello Pelillo (pelillo@dsi.unive.it)


by 1st June 2010.


We plan to make the videos of the lectures available on VideoLectures.


ORGANIZERS


Joachim M. Buhmann, ETH Zurich, Switzerland

Robert P. W. Duin, Delft University of Technology, The Netherlands

Mario A. T. Figueiredo, Insituto Superior Technico, Lisbon,

Portugal Edwin R. Hancock, University of York, UK

Vittorio Murino, University of Verona, Italy

Marcello Pelillo, Ca' Foscari University, Venice, Italy (chair)


SCHEDULE


09:00 - 09:10 M. Pelillo
Introduction and overview of the SIMBAD project
09:10 - 09:30 L. Han, R. Wilson, and E. R. Hancock
Generative Models for Relational Structures
09:30 - 09:50 M. Loog et. al.
Dissimilarity-based Classification of MRIs for Early Diagnosis of Dementia
09:50 - 10:10 F. Escolano, E. R. Hancock, and M. A. Lozano
Graph Similarity, I-Divergences and Entropic Manifold Alignment
10:10 - 10:30 Coffee break
10:30 - 10:50 A. Carli, M. Bicego, S. Baldo, and V. Murino
Nonlinear Mappings for Generative Kernels on Latent Variable Models
10:50 - 11:10 D. R. Kisku
Complexity Analysis of Multi-View Face Recognition System
11:10 - 11:30 A. Torsello
A Game-Theoretic Approach to Robust Inlier Selection
11:30 - 12:30 Panel discussion
Panelists: Narendra Ahuja, Horst Bunke, Ernesto Estrada, Josef Kittler, and Fatih Porikli
Moderator: Edwin Hancock
Important News Updates

Arrival instructions have been updated

Final Program has been posted

Presenter instructions have been posted

Special Session at S+SSPR 2010

Confirmed Invited Speakers:
Narendra Ahuja (UIUC)
Ernesto Estrada (University of Strathclyde)
Fatih Porikli (Mithshubishi Electric Research Laboratories)
Luc Devroye (McGill University)


More News . . .

Sponsored By: