@InProceedings{Micusik-CVPR2007,
  IS = { zkontrolovano 15 Dec 2007 },
  UPDATE  = { 2007-12-11 },
  author =       { Mi{\v c}u{\v s}{\'\i}k, Branislav and 
                   Pajdla, Tom{\'a}{\v s} },
  title =        { Multi-label Image Segmentation via Max-sum Solver},
  booktitle =    { Proceedings of the Computer Vision and
                   Pattern Recognition conference (CVPR)},
  publisher =    { IEEE Computer Society },
  address      = { Los Alamitos, USA },
  year =         { 2007 },
  month =        { June },
  day =          { 19-21 },
  venue =        { Minneapolis, USA},
  project =      { DIRAC FP6-IST-027787, MSM6840770038 },
  keywords =     { segmentation, max-sum, MRF },
  pages =        { 6 },
  book_pages =   { 2816 },
  authorship =   { 50-50 },
  annote = { We formulate single-image multi-label segmentation into
    regions coherent in texture and color as a MAX-SUM problem for
    which efficient linear programming based solvers have recently
    appeared. By handling more than two labels, we go beyond
    widespread binary segmentation methods, e.g., MIN-CUT or
    normalized cut based approaches.  We show that the MAX-SUM solver
    is a very powerful tool for obtaining the MAP estimate of a Markov
    random field (MRF). We build the MRF on superpixels to speed up
    the segmentation while preserving color and texture. We propose
    new quality functions for setting the MRF, exploiting priors from
    small representative image seeds, provided either manually or
    automatically. We show that the proposed automatic segmentation
    method outperforms previous techniques in terms of the Global
    Consistency Error evaluated on the Berkeley segmentation
    database. },
  organization = { {IEEE} Computer Society },
  isbn         = { 1-4244-1180-7 },
  psurl        = { http://ai.stanford.edu/~micusik/Papers/Micusik-Pajdla-CVPR2007.pdf },
  prestige     = { important },
  note         = { CD-ROM },
}