Segmentation Driven Object Detection with Fisher Vectors

Ramazan Gokberk Cinbis 1 Jakob Verbeek 1 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We present an object detection system based on the Fisher vector (FV) image representation computed over SIFT and color descriptors. For computational and storage efficiency, we use a recent segmentation-based method to generate class-independent object detection hypotheses, in combination with data compression techniques. Our main contribution is a method to produce tentative object segmentation masks to suppress background clutter in the features. Re-weighting the local image features based on these masks is shown to improve object detection significantly. We also exploit contextual features in the form of a full-image FV descriptor, and an inter-category rescoring mechanism. Our experiments on the VOC 2007 and 2010 datasets show that our detector improves over the current state-of-the-art detection results.
Keywords : object detection Fisher vectors
Type de document :
Communication dans un congrès
ICCV - IEEE International Conference on Computer Vision, Dec 2013, Sydney, Australia. IEEE, pp.2968-2975, 2013, 〈10.1109/ICCV.2013.369〉
Liste complète des métadonnées

7_to.png
7_to.png
https://hal.inria.fr/hal-00873134
Contributeur : Thoth Team <>
Soumis le : lundi 10 février 2014 - 16:12:21
Dernière modification le : mardi 12 mars 2019 - 17:20:03
Document(s) archivé(s) le : dimanche 9 avril 2017 - 10:18:10

Fichiers

paper.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

INRIA | LJK_GI_LEAR | LJK | LJK_GI | UGA | QUAERO

Citation

Ramazan Gokberk Cinbis, Jakob Verbeek, Cordelia Schmid. Segmentation Driven Object Detection with Fisher Vectors. ICCV - IEEE International Conference on Computer Vision, Dec 2013, Sydney, Australia. IEEE, pp.2968-2975, 2013, 〈10.1109/ICCV.2013.369〉. 〈hal-00873134v2〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

3152

Téléchargements de fichiers

3913

Contact


archive-ouverte@inria.fr