[OCB10] Interactive Learning of Heterogeneous Visual Concepts with Local Features

Conférence Internationale avec comité de lecture : ACM Multimedia 2010 (short paper), November 2010, pp.995-998,

Mots clés: Relevance feedback, interactive retrieval, object localization

Résumé: In the context of computer-assisted plant identification we are facing challenging information retrieval problems because of the very high within-class variability and of the limited number of training examples. To address these problems, we suggest a new interactive learning approach that combines similarity-based retrieval and re-ranking by SVM using local feature distributions. This approach leads to improved sample selection, allowing to obtain better results.

Equipe: vertigo
Collaboration: INRIA


@inproceedings {
title="{Interactive Learning of Heterogeneous Visual Concepts with Local Features}",
author=" W. Ouertani and M. Crucianu and N. Boujemaa ",
booktitle="{ACM Multimedia 2010 (short paper)}",