@INPROCEEDINGS{Mikulik-ECCV-2010,
  IS = { zkontrolovano 31 Jan 2011 },
  update   = { 2010-12-20 },
  UPDATE  = { 2010-10-19 },
  author = {Mikulik, Andrej and Perdoch, Michal and Chum, Ond{\v r}ej and Matas, Ji{\v r}{\' \i}},
  title = {Learning a Fine Vocabulary},
  year = {2010},
  pages = {1--14},
  booktitle =   {Computer Vision - {ECCV 2010}, 11th European Conference on
                 Computer Vision, Proceedings, Part {III}},
  editor = {Kostas Daniilidis and Petros Maragos and Nikos Paragios},
  publisher = {Springer},
  address = {Heidelberg, Germany},
  isbn = {978-3-642-15557-4},
  issn = {0302-9743},
  series = {Lecture Notes in Computer Science},
  book_pages = {813},
  month = {September},
  day = {5-11},
  venue = {Hersonissos, Greece},
  volume = {6313},
  organization = {Foundation for Research and Technology-Hellas (FORTH)},
  annote   = { We present a novel similarity measure for bag-of-words
    type large scale image retrieval. The similarity function is
    learned in an unsupervised manner, requires no extra space over
    the standard bag-of-words method and is more discriminative than
    both L2-based soft assignment and Hamming
    embedding. Experimentally we show that the novel similarity
    function achieves mean average precision that is superior to any
    result published in the literature on the standard Oxford 105k
    dataset/protocol.  At the same time, retrieval with the proposed
    similarity function is faster than the reference method. },
  keywords = {content based image retrieval, visual vocabulary learning, large scale},
  prestige = {important},
  authorship = {25-25-25-25},
  project = {ICT-215078 DIPLECS, MSM6840770038, GACR 102/09/P423},
  update = {2010-09-30},
}