• DocumentCode
    248804
  • Title

    Improving VLAD: Hierarchical coding and a refined local coordinate system

  • Author

    Eggert, Christian ; Romberg, Stefan ; Lienhart, Rainer

  • fYear
    2014
  • fDate
    27-30 Oct. 2014
  • Firstpage
    3018
  • Lastpage
    3022
  • Abstract
    The enormous growth of image databases calls for new techniques for fast and effective image search that scales with millions of images. Most importantly, the setting requires a compact but also descriptive image signature. Recently, the vector of aggregated local descriptors (VLAD) [1] has received much attention in large-scale image retrieval. In this paper we present two modifications for VLAD which improve the retrieval performance of the signature.
  • Keywords
    image coding; image retrieval; visual databases; VLAD; descriptive image signature; hierarchical coding; image databases; image search; large-scale image retrieval; refined local coordinate system; vector of aggregated local descriptors; Computer vision; Conferences; Encoding; Principal component analysis; Vectors; Visualization; Vocabulary; LCS; VLAD; compact signatures; image retrieval;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image Processing (ICIP), 2014 IEEE International Conference on
  • Conference_Location
    Paris
  • Type

    conf

  • DOI
    10.1109/ICIP.2014.7025610
  • Filename
    7025610