SEMANTIC POOLING FOR IMAGE CATEGORIZATION USING MULTIPLE KERNEL LEARNING - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès IEEE International Conference on Image Processing Année : 2014

SEMANTIC POOLING FOR IMAGE CATEGORIZATION USING MULTIPLE KERNEL LEARNING

Résumé

In this paper, we propose a new method for taking into ac-count the spatial information in image categorization. More specifically, we remove the loss of spatial information in Bag of Words related methods by computing the image signature over specific regions selected by object detectors. We propose to select the detectors using Multiple Kernel Learning tech-niques. We carry out experiments on the well known VOC 2007 dataset, and show our semantic pooling obtains promis-ing results.
Fichier principal
Vignette du fichier
main.pdf (867.96 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01077046 , version 1 (23-10-2014)

Identifiants

  • HAL Id : hal-01077046 , version 1

Citer

Thibaut Durand, David Picard, Nicolas Thome, Matthieu Cord. SEMANTIC POOLING FOR IMAGE CATEGORIZATION USING MULTIPLE KERNEL LEARNING. IEEE International Conference on Image Processing, Oct 2014, Paris, France. ⟨hal-01077046⟩
161 Consultations
33 Téléchargements

Partager

Gmail Facebook X LinkedIn More