Showing papers by "Diane Larlus published in 2006"
13 May 2006
TL;DR: A novel approach for object category recognition that can find objects in challenging conditions using visual attention technique that combines saliency maps very closely with the extraction of random subwindows for classification purposes.
Abstract: We present a novel approach for object category recognition that can find objects in challenging conditions using visual attention technique. It combines saliency maps very closely with the extraction of random subwindows for classification purposes. The maps are built online by the classifier while being used by it to classify the image.
109 citations
04 Sep 2006
TL;DR: This work proposes to embed the visual vocabulary creation within the object model construction, allowing to make it more suited for object class discrimination, and shows that the proposed model outperforms approaches not learning such an adapted visual vocabulary.
Abstract: The visual vocabularyis an intermediate level representation which has been proven to be very powerful for addressing object categorization problems It is generally built by vector quantizing a set of local image descriptors, independently of the object model used for categorizing images We propose here to embed the visual vocabulary creation within the object model construction, allowing to make it more suited for object class discrimination We experimentally show that the proposed model outperforms approaches not learning such an adapted visual vocabulary
53 citations
25 Jan 2006
TL;DR: In this article, a methode de construction automatique de vocabulaires visuels is proposed, where the vocabulaire visuel is obtenu par quantification de descripteurs locaux des images.
Abstract: Nous proposons dans cet article une methode de construction automatique de vocabulaires visuels. Le vocabulaire visuel est obtenu par quantification de descripteurs locaux des images. Les vocabulaires visuels produits sont utilises pour construire automatiquement des representations discriminantes des objets presents dans les images. Nous decrivons une application de ces techniques a la categorisation d'images par sacs de primitives (bags of features) et montrons que les resultats obtenus sont tres superieurs a ceux obtenus par les methodes concurrentes.
15 citations