IS = { zkontrolovano 24 Jan 2011 },
  UPDATE  = { 2010-07-27 },
  author = {Chum, Ond{\v r}ej and Matas, Ji{\v r}{\' i}},
  title = {Unsupervised Discovery of Co-occurrence in Sparse High Dimensional Data},
  booktitle =   {{CVPR} 2010: Proceedings of the 2010 IEEE Computer
                 Society Conference on Computer Vision and Pattern Recognition},
  language = {english},
  year = {2010},
  pages = {3416--3423},
  month = {June},
  annote = {An efficient min-Hash based algorithm for discovery of
    dependencies in sparse high-dimensional data is presented.  The
    dependencies are represented by sets of features cooccurring with
    high probability and are called co-ocsets.  Sparse high
    dimensional descriptors, such as bag of words, have been proven
    very effective in the domain of image retrieval. To maintain high
    efficiency even for very large data collection, features are
    assumed independent.  We show experimentally that co-ocsets are
    not rare, i.e. the independence assumption is often violated, and
    that they may ruin retrieval performance if present in the query
    image.  Two methods for managing co-ocsets in such cases are
    proposed. Both methods significantly outperform the
    state-of-the-art in image retrieval, one is also significantly
  keywords =    {co-occurrence, min-hash, data mining},
  publisher =   {Omnipress},
  address =     {Madison, USA},
  book_pages =  {3523},
  prestige =    {important},
  day = {13--18},
  isbn = {978-1-4244-6984-0},
  issn = {1063-6919},
  venue = {San Francisco, USA},
  project = {ICT-215078 DIPLECS only EU, GACR 102/09/P423, SGS10/069/OHK3/1T/13},
  www = {http://cmp.felk.cvut.cz/~chum/papers/chum-cooc-cvpr10.pdf},