@InProceedings{Macak-FSLCV2014,
  IS = { zkontrolovano 26 Jun 2015 },
UPDATE   = { 2015-06-11 },
  author =      {Ma{\v c}{\'a}k, Jan and Drbohlav, Ond{\v r}ej},
  language =    {English},
  title =       {A Simple Stochastic Algorithm for Structural Features Learning},
year     = { 2015 },
book_pages  = { 716 },
  booktitle =   {Proceedings of the ACCV2014 Workshop: the International
                  Workshop on Feature and Similarity Learning for
                  Computer Vision 2014 (FSLCV 2014)},
editor   = { Jawahar, C.~V. and Shan, S. },
  publisher =   {Springer},
address     = { Cham, Switzerland },
isbn        = { 978-3-319-16633-9 },
volume      = { 9010 },
pages       = { 44-55 },
  month =       {November},
  day =         {1},
  venue =       {Singapore},
  organization ={},
  annote =      {A conceptually very simple unsupervised algorithm for
                  learning structure in the form of a hierarchical
                  probabilistic model is described in this paper. The
                  proposed probabilistic model can easily work with
                  any type of image primitives such as edge segments,
                  non-max-suppressed filter set responses, texels,
                  distinct image regions, {SIFT} features, etc., and is
                  even capable of modelling non-rigid and/or visually
                  variable objects.  The model has recursive form and
                  consists of sets of simple and gradually growing
                  sub-models that are shared and learned individually
                  in layers.  The proposed probabilistic framework
                  enables to exactly compute the probability of
                  presence of a certain model, regardless on which
                  layer it actually is. All these learned models
                  constitute a rich set of independent structure
                  elements of variable complexity that can be used as
                  features in various recognition tasks.},
  keywords =    {graphical models, inference},
  prestige =    {international},
  project =     {GACR P103/12/1578},
affiliation = { 13133-13133 },
series      = { Lecture Notes in Computer Science },
note        = { doi: 10.1007/978-3-319-16634-6_4 },
}