Revisiting the VLAD image representation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2013

Revisiting the VLAD image representation


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.
Fichier principal
Vignette du fichier
nextvlad_hal.pdf (219.42 Ko) Télécharger le fichier
Vignette du fichier
nextvlad.png (6.33 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image

Dates and versions

hal-00840653 , version 1 (02-07-2013)
hal-00840653 , version 2 (05-08-2013)


  • HAL Id : hal-00840653 , version 2


Jonathan Delhumeau, Philippe-Henri Gosselin, Hervé Jégou, Patrick Pérez. Revisiting the VLAD image representation. ACM Multimedia, Oct 2013, Barcelona, Spain. ⟨hal-00840653v2⟩
1189 View
4678 Download


Gmail Facebook X LinkedIn More