IS = { zkontrolovano 01 Feb 2010 },
  UPDATE  = { 2010-01-08 },
  author = {Chum, Ond{\v r}ej and Per{\v d}och, Michal and Matas, Ji{\v r}{\' i}},
  title = {Geometric min-Hashing: Finding a (thick) needle in a haystack},
  booktitle =   {CVPR 2009: Proceedings of the 2009 IEEE Computer
                 Society Conference on Computer Vision and Pattern Recognition},
  language = {english},
  year = {2009},
  pages = {17--24},
  month = {June},
  annote = {We propose a novel hashing scheme for image retrieval,
    clustering and automatic object discovery. Unlike commonly used
    bag-of-words approaches, the spatial extent of image features is
    exploited in our method. The geometric information is used both to
    construct repeatable hash keys and to increase the
    discriminability of the description.  Each hash key combines
    visual appearance (visual words) with semi-local geometric
    information. Compared with the state-of-the-art min-hash, the
    proposed method has both higher recall (probability of collision
    for hashes on the same object) and lower false positive rates
    (random collisions). The advantages of geometric min-hashing
    approach are most pronounced in the presence of viewpoint and
    scale change, significant occlusion or small physical overlap of
    the viewing fields. We demonstrate the power of the proposed
    method on small object discovery in a large unordered collection
    of images and on a large scale image clustering problem.},
  keywords =    {geometric min-hash, large scale image clustering, automatic object discovery},
  publisher =   {Omnipress},
  address =     {Madison, USA},
  book_pages =  {3000},
  prestige =    {important},
  day = {20--25},
  isbn = {978-1-4244-3991-1},
  issn = {1063-6919},
  venue = {Miami, USA},
  project = {ICT-215078 DIPLECS, GACR 102/09/P423},
  www = {http://cmp.felk.cvut.cz/~perdom1/papers/cvpr09a.pdf},
  note = {CD-ROM},