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: aecp@diku.dk

Program Committee

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

the formulation of a parameterized probabilistic model of image generation;
estimation and/or maximization of the posterior probability (given an image or image sequence) of model parameters (state variables).

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

papers which focus on a detailed study of generative models (e.g. as models of the statistics of natural images);
papers which present new estimation methods for model parameters, or compare different estimation methods applied to the same generative model;
papers providing a GMB interpretation (or modification) of established vision algorithms.

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

Timeline

paper registration deadline: 20 February 2004
papers distributed for review: 5 March 2004
notification of workshop acceptance: 30 March 2004 (with a few outliers)
deadline for final workshop papers: 4 May 2004
workshop date: 2 July 2004, immediately after CVPR 2004
selection of papers for special issue: July 2004
deadline for final papers for special issue: between Sept. and Dec. 2004
(depending on the required changes to the workshop papers)
final decision on acceptance for special issue: soon after the deadline for final papers
publication of special issue: first half of 2005