Over the last few decades, energy minimization methods have become an established
paradigm to resolve a variety of challenges in the fields of computer vision
and pattern recognition. While traditional approaches to computer vision were
often based on a heuristic sequence of processing steps and merely allowed a
very limited theoretical understanding of the respective methods, most state-ofthe-
art methods are nowadays based on the concept of computing solutions to a given problem by minimizing the respective energies.
This volume contains the papers presented at the 8th International Conference
on Energy Minimization Methods in Computer Vision and Pattern Recognition
(EMMCVPR 2011), held at the Radisson Royal Hotel in Saint Petersburg,
July 25–27, 2011. These papers demonstrate that energy minimization methods
have become a mature field of research spanning a broad range of areas from
discrete graph theoretic approaches and Markov random fields to variational
methods and partial differential equations. Application areas include image segmentation
and tracking, shape optimization and registration, inpainting and
image denoising, color and texture modeling, statistics and learning. Overall, we
received 52 high-quality submissions. Based on the reviewer recommendations,
after double-blind review process 30 papers were selected for publication, 16 as
oral and 14 as poster presentations.
Both oral and poster papers were attributed the same number of pages in
the conference proceedings. Furthermore, we were delighted that three leading
experts from the fields of computer vision and energy minimization, namely,
Andrew Blake (Microsoft Research), Emmanuel Candes (Stanford University),
Alan Yuille (UCLA), and Vladimir Kolmogorov (IST Austria), agreed to further
enrich the conference with inspiring keynote lectures.
We would like to express our gratitude to those who made this event possible
and contributed to its success. In particular, our Program Committee of top
international experts in the field provided excellent reviews. A major donation
from Microsoft Research and a financial contribution from Yandex covered a
significant part of the conference expenses. We are grateful to Andrew Delong,
Lena Gorelick, and a grant from the University of Western Ontario for covering
the conference’s printing needs. Anna Medvedeva provided very helpful local administrative
support. It is our belief that this conference will help to advance the
field of energy minimization methods and to further establish the mathematical
foundations of computer vision.