---

IEEE Transactions on Pattern Analysis and Machine Intelligence

Call for Papers

Special Issue on

Graphical Models in Computer Vision

The last five years has witnessed rapid growth in the popularity of graphical models, most notably Bayesian networks, as a tool for representing, learning, and computing complex probability distributions. Graphical models provide powerful computational support for the Bayesian approach to computer vision, which has become a standard framework for addressing vision problems. The class of graphical models includes some well-known tools such as Markov Random Fields, Hidden Markov models, and the Kalman filter. More importantly, the graphical models formalism makes it possible to generalize these tools and develop novel statistical representations and associated algorithms for inference and learning.

The graphical models formalism has been applied to a wide range of topics in computer vision, ranging from low-level issues like image segmentation and motion estimation to high-level issues such as head tracking and activity recognition. The goal of this special issue is to publish original papers that demonstrate the breadth of applicability of the graphical models formalism to vision problems. A second goal is to raise the awareness within the vision community of this line of research and to bridge the gap between emerging theoretical and algorithmic advances in graphical models and current practice in computer vision. Toward this end, the special issue will include one or more invited papers from senior researchers in the graphical models community.

Manuscripts submitted to this special issue should not be submitted to or in consideration by other journals or conferences which have proceedings. Papers which have appeared previously in proceedings of conferences can be submitted to this special issue if and only if they are substantially revised or improved from their earlier versions due to copyright issues. The first page of the submission should include the title, the names and affiliations of the authors, including the addresses, telephone, and fax numbers, a 150-word abstract, and a few index terms related to the subject matter.

Contact James M. Rehg at rehg@cc.gatech.edu for a password to access the ftp site.

1.       Use the corresponding author's name to identify your file and post it to

ftp://gmcv@ftp.computer.org/

2.       Send an e-mail message to rehg@cc.gatech.edu notifying the guest editor that you have posted a file on the TPAMI site, and clearly specify that the submission is intended for this special issue.

Guest Editors