Combining attributes and Fisher vectors for efficient image retrieval - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2011

Combining attributes and Fisher vectors for efficient image retrieval


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.
Fichier principal
Vignette du fichier
douze_attributes_retrieval.pdf (1.63 Mo) Télécharger le fichier
Vignette du fichier
douze_attributes_retrieval_image.png (40.58 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image

Dates and versions

inria-00566293 , version 1 (08-04-2011)



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. pp.745-752, ⟨10.1109/CVPR.2011.5995595⟩. ⟨inria-00566293⟩
2093 View
3904 Download



Gmail Facebook Twitter LinkedIn More