Combining attributes and Fisher vectors for efficient image retrieval

Matthijs Douze 1, 2 Arnau Ramisa 1, 3 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Attributes were recently shown to give excellent results for category recognition. In this paper, we demonstrate their performance in the context of image retrieval. First, we show that retrieving images of particular objects based on attribute vectors gives results comparable to the state of the art. Second, we demonstrate that combining attribute and Fisher vectors improves performance for retrieval of particular objects as well as categories. Third, we implement an efficient coding technique for compressing the combined descriptor to very small codes. Experimental results on the Holidays dataset show that our approach significantly outperforms the state of the art, even for a very compact representation of 16 bytes per image. Retrieving category images is evaluated on the ''web-queries'' dataset. We show that attribute features combined with Fisher vectors improve the performance and that combined image features can supplement text features.
Document type :
Conference papers
CVPR 2011 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2011, Colorado Springs, United States. IEEE, pp.745-752, 2011, 〈10.1109/CVPR.2011.5995595〉
Liste complète des métadonnées

Cited literature [25 references]  Display  Hide  Download


https://hal.inria.fr/inria-00566293
Contributor : Thoth Team <>
Submitted on : Friday, April 8, 2011 - 6:20:28 PM
Last modification on : Wednesday, April 11, 2018 - 1:58:41 AM
Document(s) archivé(s) le : Thursday, November 8, 2012 - 3:45:50 PM

Files

douze_attributes_retrieval.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Matthijs Douze, Arnau Ramisa, Cordelia Schmid. Combining attributes and Fisher vectors for efficient image retrieval. CVPR 2011 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2011, Colorado Springs, United States. IEEE, pp.745-752, 2011, 〈10.1109/CVPR.2011.5995595〉. 〈inria-00566293〉

Share

Metrics

Record views

2797

Files downloads

5871