Call for Papers

Special Issue on “Higher Order Graphical Models in Computer Vision: Modelling, Inference & Learning”

To be published in IEEE Transactions on Pattern Analysis and Machine Intelligence

Recently, there has been an increasing interest in modelling image priors with higher-order models and global constraints. These models have the ability to encode significantly more sophisticated priors and structural dependencies among image pixels, compared to the traditional pairwise interactions. Examples of such models in computer vision include, second-order smoothness priors in stereo, priors on natural image statistics for de-noising, robust smoothness priors for object labelling, co-occurrence priors for object category segmentation, connectivity and bounding-box priors for segmentation.


This special issue invites original articles addressing the issues of modelling, inference, and learning in models with higher-order terms and global constraints. We also welcome survey and overview papers in these general areas. Specific topics of interest include, but are not limited to:


(a) Different forms of higher order potentials

(b) Grammar-based models

(c) Which image priors should be modelled?


(d) Extending the class of exactly solvable higher-order models

(e) Approximate inference in higher-order models

(f) Theoretical upper bound for the approximate solutions


(g) Learning with higher-order potentials and global constraints

(h) Piecewise or distributed or coarse-to-fine learning.

Paper Submission

Papers must be submitted online to the TPAMI submission site: (Please select "SI: Higher Order Graphical Models in Computer Vision" as the Manuscript Type). Complete manuscripts formatted according to TPAMI guidelines, available at, are expected.


Submission Deadline:                  June 1, 2013

Reviews:                                           December 20, 2013 January 15, 2014 [Initial decisions sent to EIC]

Revisions of Submissions:          April/May 2014 [Please see the email from TPAMI for details]

Final Decisions/Manuscript:        June 30, 2014 July 31, 2014 [Decisions sent]

Estimated Online Publication:     End of 2014 [Published online] [To appear in the July 2015 issue]

Guest Editors

Karteek Alahari

Researcher, Inria Grenoble - Rhône-Alpes

Dhruv Batra

Research Assistant Professor, TTI-Chicago / Assistant Professor, Virginia Tech

Srikumar Ramalingam

Principal Research Scientist, Mitsubishi Electric Research Lab (MERL)

Nikos Paragios

Professor, Ecole Centrale de Paris / Ecole des Ponts-ParisTech / Inria Saclay-Ile-de-France

Richard Zemel

Professor, University of Toronto