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.

This work was partially funded by the QUAERO project supported by OSEO, the European integrated project AXES, the ANR project GAIA, and by MICINN under project MIPRCV Consolider Ingenio CSD2007-00018.

Trabajo presentado al CVPR celebrado en Providence (USA) del 20 al 25 de junio de 2011.

Peer Reviewed