@TechReport{Mikulik-TR-2012-05,
  IS = { zkontrolovano 15 Jan 2013 },
  UPDATE  = { 2012-03-02 },
  author =      {Mikul{\'i}k, Andrej},
  supervisor =  {Matas, Ji{\v r}{\'i} and  Chum, Ond{\v r}ej},
  title =       {Large Scale Image Search for Objects and Categories -- {PhD} Thesis Proposal},
  institution = {Center for Machine Perception, K13133 FEE
                 Czech Technical University},
  address =     {Prague, Czech Republic},
  year =        {2012},
  month =       {February},
  type =        {Research Report},
  number =      {CTU--CMP--2012--05},
  issn =        {1213-2365},
  pages =       {40},
  figures =     {15},
  authorship =  {100},
  psurl = {[Mikulik-TR-2012-05.pdf]},
  project =     {Microsoft scholarship},
  annote = {In this report we summarize recent progress in large image
    retrieval, investigate ways to improve its robustness to viewpoint
    and environmental conditions change, increase mean average
    precision and increase recall for difficult or small objects. Most
    effective particular object and image retrieval approaches are
    based on the bag-of-words (BoW) model. We present a novel
    similarity measure for this model. 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 5k, Oxford 105k and Paris
    dataset/protocol. We study fine quantization and very large
    vocabularies (up to 64 million words) and show that the
    performance of specific object retrieval increases with the size
    of the vocabulary. This observation is in contrast with previously
    published methods. We further demonstrate that the large
    vocabularies increase the speed of the tf-idf scoring step. All
    state-of-the-art retrieval results have been achieved by methods
    that include a query expansion that brings a significant boost in
    performance. We introduce three modifications to automatic query
    expansion: (i) a method capable of preventing query expansion
    failure caused by the presence of confusers, (ii) an improved
    spatial verification and re-ranking step that incrementally builds
    a statistical model of the query object and (iii) we learn
    relevant spatial context to boost retrieval performance.  The
    three improvements of query expansion were evaluated on
    established Paris and Oxford datasets according to a standard
    protocol, and state-of-the-art results were achieved.},
  keywords =    {large scale, content based, image, retrieval},
}