Workshop and Special Issue on

Generative-Model Based Vision:

GMBV 2004

Washington DC, USA
2 July 2004


Workshop to be held in conjunction with CVPR 2004
Special issue to be published in Computer Vision and Image Understanding.

Workshop Program

This workshop/special issue is the second in a series.

The first workshop was held in conjunction with ECCV 2002.
The first special issue has appeared in Image and Vision Computing vol. 21(1), January 2003.
Five of the articles in the special issue were amongst the 15 most downloaded articles in 2003 from the Image and Vision Computing web site.

At GMBV 2004, 31 workshop submissions have been received (3 papers rejected without review) and 17 papers have been accepted.

Special Issue Guest Editors and Workshop Organizing Committee

Rasmus Larsen

Arthur Pece

Alan Yuille

Chairman and contact person: Arthur Pece, E-mail:

Program Committee

Andrew Blake

Richard Bowden

Terry Caelli

Dorin Comaniciu

Tim Cootes

James Coughlan

Daniel Cremers


        Trevor Darrell

Ahmed Elgammal

James Ferryman

William Freeman

Brendan Frey

Bram van Ginneken

Chris Glasbey

Lars Kai Hansen

        Aapo Hyvarinen

Michael Isard

Stan Li

Esther Koller-Meier

Ann Lee

David Lowe

Hedvig Sidenbladh


        Stephen Pizer

Mikkel B. Stegmann

Philip Torr

Carole Twining

Chris Williams

John Winn

Ying Nian Wu

Song-Chun Zhu

Additional reviews provided by:

Sarang Joshi (University of North Carolina)

Peihua Li (IRISA/INRIA Rennes)
Bo Markussen (University of Copenhagen)
Gloria Menegaz (University of Siena)

Goals and Scope

In the last decade, there has been a convergence of statistical and model-based approaches to computational vision. This is an ongoing process, leading to the emerging paradigm of generative-model-based (GMB) vision.

This workshop/special issue aims to bring together researchers working on different problems within computational vision, who are interested in this paradigm.
For the purposes of the workshop/special issue, GMB vision is a methodology which prescribes Often, the generative model is used not only by the software developer in the formulation of the algorithm, but also by the algorithm itself as a component of an iterative estimation process.
The state variables are whatever people want to know, (e.g. position, size, shape, color) about objects of interest.
This definition is not meant to be dogmatic or to inhibit the development of the field, but only to give a focus to the presentations.

In addition to papers describing new GMB algorithms, also appropriate to the workshop/special issue are

Examples of topics relevant to the workshop/special issue include, but are by no means limited to, the topics covered in the first GMBV workshop.

Instructions for Authors

Guidelines for Authors