Skip to Main content Skip to Navigation
Conference papers

On the burstiness of visual elements

Hervé Jégou 1, 2 Matthijs Douze 1 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
2 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Burstiness, a phenomenon initially observed in text retrieval, is the property that a given visual element appears more times in an image than a statistically independent model would predict. In the context of image search, burstiness corrupts the visual similarity measure, i.e., the scores used to rank the images. In this paper, we propose a strategy to handle visual bursts for bag-of-features based image search systems. Experimental results on three reference datasets show that our method significantly and consistently outperforms the state of the art.
Complete list of metadata
Contributor : Hervé Jégou Connect in order to contact the contributor
Submitted on : Tuesday, June 7, 2011 - 10:24:50 AM
Last modification on : Tuesday, October 19, 2021 - 11:13:06 PM
Long-term archiving on: : Sunday, December 4, 2016 - 2:21:45 PM



Hervé Jégou, Matthijs Douze, Cordelia Schmid. On the burstiness of visual elements. CVPR 2009 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2009, Miami, United States. pp.1169-1176, ⟨10.1109/CVPRW.2009.5206609⟩. ⟨inria-00394211v3⟩



Les métriques sont temporairement indisponibles