AVLAD: Optimizing the VLAD image signature for specific feature descriptors

Dominik Van Opdenbosch, Eckehard Steinbach

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

Recent works on content-based image retrieval have successfully used the Vector of Locally Aggregated Descriptors (VLAD) as a compact image signature. In this paper, we improve the VLAD signature by tailoring the VLAD representation to the specific properties of the visual feature descriptors. We combine this improvement with the recently proposed hierarchical VLAD approach and demonstrate the effectiveness of this extension for the two well-known feature descriptors SIFT and SURF. Furthermore, we investigate how to efficiently reduce the dimensionality of the resulting representation using different unsupervised dimensionality reduction techniques.

Original languageEnglish
Title of host publicationProceedings - 2016 IEEE International Symposium on Multimedia, ISM 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages545-550
Number of pages6
ISBN (Electronic)9781509045709
DOIs
StatePublished - 18 Jan 2017
Event18th IEEE International Symposium on Multimedia, ISM 2016 - San Jose, United States
Duration: 11 Dec 201613 Dec 2016

Publication series

NameProceedings - 2016 IEEE International Symposium on Multimedia, ISM 2016

Conference

Conference18th IEEE International Symposium on Multimedia, ISM 2016
Country/TerritoryUnited States
CitySan Jose
Period11/12/1613/12/16

Keywords

  • Image retrieval
  • Mobile visual search
  • VLAD

Fingerprint

Dive into the research topics of 'AVLAD: Optimizing the VLAD image signature for specific feature descriptors'. Together they form a unique fingerprint.

Cite this