Computer Vision and Discrete Optimization Algorithms

Vladimir Kolmogorov

Vladimir Kolmogorov mainly focuses on developing efficient algorithms for inference in graphical models. Such algorithms have applications in many areas, e.g. computer vision, computer graphics, machine learning, and bioinformatics. Some of the inference techniques developed by Kolmogorov are widely used in the computer vision community, e.g. a maximum flow algorithm and the sequential tree-reweighted message passing algorithm (TRW-S). His other research interests include combinatorial optimization problems such as the min cost perfect matching problem, and some theoretical aspects of discrete optimization.

Contact
Vladimir Kolmogorov
Institute of Science and Technology Austria (IST Austria)
Am Campus 1
A – 3400 Klosterneuburg

Tel.: +43 (0)2243 9000-4801
E-mail: vladimir.kolmogorov@remove-this.ist.ac.at

CV

Vladimir Kolmogorov's website

Assistant
Christine Krebs

Tel.: +43 (0)2243 9000-1071
E-mail: christine.krebs@ist.ac.at

Team

  • Rustem Takhanov, Postdoc

Selected Publications

  • Kolmogorov V, Blossom V. 2009. A new implementation of a minimum cost perfect matching algorithm. Mathematical programming Computation 1: 43-67.
  • Kolmogorov V. 2006. Convergent tree-reweighted message passing for energy minimization. IEEE Transactions on Pattern Analysis and Machine Intelligence 28: 1568-1583.
  • Boykov Y, Kolmogorov V. 2004. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Transaction on Pattern Analysis and Machine Intelligence 26: 1124-1137.

Career

2011 Assistant Professor, IST Austria
2005-2011 Lecturer, University College London, UK
2003-2005 Assistant Researcher, Microsoft Research, Cambridge, UK
2003 PhD, Cornell University, USA

Selected Distinctions

2007 Honorable mention, outstanding student paper award (to M. Pawan Kumar) at Neural Information Processing Systems Conference
2006-2011 The Royal Academy of Engineering/EPSRC Research Fellowship
2005 Best paper honorable mention award at IEEE Conference on Computer Vision and Pattern Recognition
2002 Best paper award at the European Conference on Computer Vision

To top