HiPot: ECCV 2012 Workshop on Higher-Order Models and Global Constraints in Computer Vision


17/10: Slides from the keynote talks are available below.

17/10: The call for papers for the TPAMI Special Issue is here.


Venue : Adua 1F (1st floor) in Palazzo Affari
  9:15 am  Opening remarks: Organizers
  9:20 am  Keynote Talk: Endre Boros, Rutgers University
  "Quadratization of higher degree binary optimization problems" [slides]
10:00 am   "Tighter Relaxations for Higher-Order Models based on Generalized Roof Duality",
    Johan Fredriksson, Carl Olsson, Petter Strandmark, Fredrik Kahl
 10:20 am
   "Approximate Envelope Minimization for Curvature Regularity",
    Stefan Heber, Rene Ranftl, Thomas Pock

 10:40 am   Coffee Break
 11:00 am   Keynote Talk: Fredrik Kahl, Lund University
   "Generalized Roof Duality" [slides: pptx]
 11:40 am   "Relating Things and Stuff by High-Order Potential Modeling",
    Byung-soo Kim, Min Sun, Pushmeet Kohli, Silvio Savarese
 12:00 pm   Poster Session:
   "Submodular Relaxation for MRFs with High-Order Potentials",
    Anton Osokin, Dmitry Vetrov (Moscow State University)

   "Adjacency Matrix Construction Using Sparse Coding for Label Propagation",
    Haixia Zheng, H. S. Horace Ip, Liang Tao (City University of Hong Kong)
   "Climbing: A unified approach for global constraints on hierarchical segmentation",
    Bangalore Kiran, Jean Serra, Jean Cousty (A3SI, ESIEE)
   "Tighter Relaxations for Higher-Order Models based on Generalized Roof Duality",
    Johan Fredriksson, Carl Olsson, Petter Strandmark, Fredrik Kahl (Lund University)
   "Approximate Envelope Minimization for Curvature Regularity",
    Stefan Heber, Rene Ranftl, Thomas Pock (TU Graz)

    "Relating Things and Stuff by High-Order Potential Modeling",
     Byung-soo Kim (University of Michigan), Min Sun (University of Michigan),
     Pushmeet Kohli (Microsoft), Silvio Savarese (University of Michigan)

12:30 pm    
   Lunch break + posters + discussions
  2:30 pm   Keynote Talk: Yann LeCun, New York University
Long-range Constraints though Hierarchical Models for Scene Parsing" [slides]
  3:10 pm   Keynote Talk: Nikos Komodakis, Ecole des Ponts-ParisTech
   "Flexible inference and learning methods for high-order models: taking full advantage of models'
  3:50 pm   Coffee Break + discussions
  4:30 pm   Keynote Talk: René Vidal, Johns Hopkins University
   "Global Bag of Latent Features Models for Semantic Segmentation"
  5:10 pm   Discussions + Conclusion


Many tasks in computer vision, including low-level ones such as image segmentation, stereo estimation, as well as high-level ones such as object recognition, scene understanding, have been modelled as discrete labelling problems. Furthermore, discrete optimization has emerged as an indispensable tool to solve these problems over the last two decades. It is now a routine process to write an explicit energy function, understand the Bayesian priors it incorporates, and then depending on its properties, perform exact or approximate inference.

Initially, one of the popular ways to model a labelling problem has been in terms of an energy function comprising of unary and pairwise clique potentials. This assumption severely restricts the representational power of these models as they are unable to capture the rich statistics of natural images. More recently, a second wave of success can be attributed to the incorporation of higher-order terms that have the ability to encode significantly more sophisticated priors and structural dependencies between variables – e.g., 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 image segmentation.

The goal of this workshop is to bring together researchers working on different aspects of this problem (modelling, inference and learning) and discuss various techniques, common solutions, open questions and future pursuits, such as:


(a) What other forms of higher order potentials can be used (e.g. grammar-based)?
(b) Which image priors should we aim to model?

(c) How feasible is it to extend the class of functions exactly solvable?
(d) Given the "satisfactory" results of many approximate algorithms, what more can we gain from exact solutions?
(e) Can we find theoretical upper bound for the approximate solutions?
(f) How do we compare the various inference methods?

(g) How do we learn with higher-order potentials and global constraints?
(h) Should we explore piece-wise or distributed or coarse-to-fine learning?

Important Dates

  • Paper submission Deadline          July 5, 5pm PST (Passed)
  • Acceptance Notification               August 3
  • Camera Ready Due                     August 7
  • Workshop Date                           October 13

Invited Speakers

Endre Boros, Rutgers University
Fredrik Kahl, Lund University
Nikos KomodakisEcole des Ponts-ParisTech
Yann LeCun, New York University
René Vidal, Johns Hopkins University

Call for Papers

The workshop invites high-quality submissions that will be presented in an oral or a poster form. Papers presenting theoretical or application-driven or (preferably) both contributions are suitable. Topics of interest include, but are not limited to:

  • Forms of higher order potentials and global constraints
  • Learning in models with these potentials/constraints
  • Inference methods
  • Efficiency, tractability, approximation bounds and comparison of inference methods

In addition to the oral and poster presentations, the program will include invited talks and an open session involving all the participants.

Papers must be in PDF format and must not exceed 10 pages (ECCV format). All submissions are subject to a double-blind review process by the program committee. Extended abstracts describing work in progress are also acceptable.

Further details about the submission process can be found here.

Program Committee

Bjoern Andres, Harvard University
Stephen Gould, Australian National University
Stefanie Jegelka, University of California Berkeley
Julian McAuley, Stanford University
Sebastian Nowozin, Microsoft Research Cambridge
George Papandreou, University of California, Los Angeles
Daniel Tarlow, University of Toronto
Tomas Werner, Czech Technical University


Karteek Alahari
Dhruv Batra
TTI-Chicago /
Virginia Tech
Nikos Paragios
Srikumar Ramalingam
Rich Zemel
University of Toronto