AVLAD: Optimizing the VLAD image signature for specific feature descriptors

Dominik Van Opdenbosch, Eckehard Steinbach

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

4 Zitate (Scopus)

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.

OriginalspracheEnglisch
TitelProceedings - 2016 IEEE International Symposium on Multimedia, ISM 2016
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten545-550
Seitenumfang6
ISBN (elektronisch)9781509045709
DOIs
PublikationsstatusVeröffentlicht - 18 Jan. 2017
Veranstaltung18th IEEE International Symposium on Multimedia, ISM 2016 - San Jose, USA/Vereinigte Staaten
Dauer: 11 Dez. 201613 Dez. 2016

Publikationsreihe

NameProceedings - 2016 IEEE International Symposium on Multimedia, ISM 2016

Konferenz

Konferenz18th IEEE International Symposium on Multimedia, ISM 2016
Land/GebietUSA/Vereinigte Staaten
OrtSan Jose
Zeitraum11/12/1613/12/16

Fingerprint

Untersuchen Sie die Forschungsthemen von „AVLAD: Optimizing the VLAD image signature for specific feature descriptors“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren