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, INPG - Institut National Polytechnique de Grenoble
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.
Type de document :
Communication dans un congrès
CVPR 2009 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2009, Miami, United States. IEEE Computer society, pp.1169-1176, 2009, <http://www.computer.org/portal/web/csdl/doi/10.1109/CVPRW.2009.5206609>. <10.1109/CVPRW.2009.5206609>
Liste complète des métadonnées


https://hal.inria.fr/inria-00394211
Contributeur : Hervé Jégou <>
Soumis le : mardi 7 juin 2011 - 10:24:50
Dernière modification le : vendredi 13 janvier 2017 - 14:20:58
Document(s) archivé(s) le : dimanche 4 décembre 2016 - 14:21:45

Identifiants

Citation

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. IEEE Computer society, pp.1169-1176, 2009, <http://www.computer.org/portal/web/csdl/doi/10.1109/CVPRW.2009.5206609>. <10.1109/CVPRW.2009.5206609>. <inria-00394211v3>

Partager

Métriques

Consultations de
la notice

487

Téléchargements du document

578