Revisiting the VLAD image representation

Jonathan Delhumeau 1 Philippe-Henri Gosselin 1 Hervé Jégou 1 Patrick Pérez 2
1 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Recent works on image retrieval have proposed to index images by compact representations encoding powerful local descriptors, such as the closely related vector of aggregated local descriptors (VLAD) and Fisher vector (FV). By combining them with a suitable coding technique, it is possible to encode an image in a few dozen bytes while achieving excellent retrieval results. This paper revisits some assumptions proposed in this context regarding the handling of ''visual burstiness'', and shows that ad-hoc choices are implicitly done which are not desirable. Focusing on VLAD without loss of generality, we propose to modify several steps of the original design. Albeit simple, these modifications significantly improve VLAD and make it compare favorably against the state of the art.
Document type :
Conference papers
Complete list of metadatas

Cited literature [18 references]  Display  Hide  Download


https://hal.inria.fr/hal-00840653
Contributor : Hervé Jégou <>
Submitted on : Monday, August 5, 2013 - 10:50:17 PM
Last modification on : Friday, November 16, 2018 - 1:22:34 AM
Long-term archiving on : Wednesday, April 5, 2017 - 7:25:20 PM

Files

nextvlad_hal.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00840653, version 2

Citation

Jonathan Delhumeau, Philippe-Henri Gosselin, Hervé Jégou, Patrick Pérez. Revisiting the VLAD image representation. ACM Multimedia, Oct 2013, Barcelona, Spain. ⟨hal-00840653v2⟩

Share

Metrics

Record views

1412

Files downloads

1226