SEMANTIC POOLING FOR IMAGE CATEGORIZATION USING MULTIPLE KERNEL LEARNING

Thibaut Durand 1, 2 David Picard 1 Nicolas Thome 2 Matthieu Cord 2
1 MIDI
ETIS - Equipes Traitement de l'Information et Systèmes
2 MLIA - Machine Learning and Information Access
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : 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.
Document type :
Conference papers
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01077046
Contributor : Thibaut Durand <>
Submitted on : Thursday, October 23, 2014 - 4:57:43 PM
Last modification on : Thursday, March 21, 2019 - 1:03:27 PM

File

main.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01077046, version 1

Citation

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⟩

Share

Metrics

Record views

214

Files downloads

183