• DocumentCode
    19869
  • Title

    How Many Visual Concepts?

  • Author

    Smith, John R.

  • Author_Institution
    IBM T. J. Watson Research Center
  • Volume
    21
  • Issue
    1
  • fYear
    2014
  • fDate
    Jan.-Mar. 2014
  • Firstpage
    2
  • Lastpage
    3
  • Abstract
    Visual scenes require complex description and modeling that involves more than a list of words. The visual semantic concept basis is larger than the number of unique words. More efforts are needed to build out the set of visual semantic concepts.
  • Keywords
    Scene analysis; Semantics; Visualization; WordNet; computer vision; image classification; multimedia; multimedia machine learning; semantic concept detection; semantic gap; visual taxonomy;
  • fLanguage
    English
  • Journal_Title
    MultiMedia, IEEE
  • Publisher
    ieee
  • ISSN
    1070-986X
  • Type

    jour

  • DOI
    10.1109/MMUL.2014.8
  • Filename
    6756900