Learning Object Representations for Visual Object Class Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Documents Associated With Scientific Events Year : 2007

Learning Object Representations for Visual Object Class Recognition

Cordelia Schmid
  • Function : Author
  • PersonId : 831154
Hedi Harzallah
  • Function : Author
  • PersonId : 861132
Joost van de Weijer
  • Function : Author
  • PersonId : 847654

Abstract

This talk discussed our object-class recognition method that won the classification contest of the Pascal VOC Challenge 2007. We submitted two recognition methods sharing the same underlying image representations defined by a choice of image sampler, local descriptor and global spatial grid. The submitted methods also share the classifier, which is a one-against-rest non-linear Support Vector Machine with chi-square kernel. The methods differ in the way they combine multiple representations (channels). The first method is based on the approach of Zhang et al., where the final similarity measure is the sum of per-channel similarities. The second method employs a genetic algorithm, which is used to determine (on per-class basis) the parameters of the generalized RBF kernel incorporating all the channels, i.e., to estimate the importance of each sampling/description/spatial method for the recognition and to optimize the required level of generalization. Both methods showed superior performance compared to other state-of-the-art submissions.

Keywords

Fichier principal
Vignette du fichier
MarszalekSchmid-VOC07-LearningRepresentations-slides.pdf (4.14 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00548669 , version 1 (20-12-2010)

Identifiers

  • HAL Id : inria-00548669 , version 1

Cite

Marcin Marszałek, Cordelia Schmid, Hedi Harzallah, Joost van de Weijer. Learning Object Representations for Visual Object Class Recognition. Visual Recognition Challange workshop, in conjunction with ICCV, Oct 2007, Rio de Janeiro, Brazil. 2007. ⟨inria-00548669⟩
746 View
631 Download

Share

Gmail Facebook X LinkedIn More