Combining efficient object localization and image classification - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2009

Combining efficient object localization and image classification

Hedi Harzallah
  • Function : Author
  • PersonId : 861132
Frédéric Jurie
Cordelia Schmid
  • Function : Author
  • PersonId : 831154


In this paper we present a combined approach for object localization and classification. Our contribution is two-fold. (a) A contextual combination of localization and classification which shows that classification can improve detection and vice versa. (b) An efficient two stage sliding window object localization method that combines the efficiency of a linear classifier with the robustness of a sophisticated non-linear one. Experimental results evaluate the parameters of our two stage sliding window approach and show that our combined object localization and classification methods outperform the state-of-the-art on the PASCAL VOC 2007 and 2008 datasets.
Fichier principal
Vignette du fichier
combine_localiz_cls.pdf (302.05 Ko) Télécharger le fichier
combine_localiz_cls-presentation.ppt (4.83 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Other

Dates and versions

inria-00439516 , version 1 (07-12-2009)



Hedi Harzallah, Frédéric Jurie, Cordelia Schmid. Combining efficient object localization and image classification. ICCV 2009 - 12th International Conference on Computer Vision, Sep 2009, Kyoto, Japan. pp.237-244, ⟨10.1109/ICCV.2009.5459257⟩. ⟨inria-00439516⟩
492 View
1127 Download



Gmail Facebook X LinkedIn More