Semantic Hierarchies for Visual Object Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2007

Semantic Hierarchies for Visual Object Recognition

Abstract

In this paper we propose to use lexical semantic networks to extend the state-of-the-art object recognition techniques. We use the semantics of image labels to integrate prior knowledge about inter-class relationships into the visual appearance learning. We show how to build and train a semantic hierarchy of discriminative classifiers and how to use it to perform object detection. We evaluate how our approach influences the classification accuracy and speed on the PASCAL VOC challenge 2006 dataset, a set of challenging real-world images. We also demonstrate additional features that become available to object recognition due to the extension with semantic inference tools - we can classify high-level categories, such as animals, and we can train part detectors, for example a window detector, by pure inference in the semantic network.
Fichier principal
Vignette du fichier
MarszalekSchmid-CVPR07-SemanticHierarchies.pdf (639.21 Ko) Télécharger le fichier
Vignette du fichier
semhier.png (33.12 Ko) Télécharger le fichier
MarszalekSchmid-CVPR07-SemanticHierarchies-poster.pdf (699.28 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Format : Other

Dates and versions

inria-00548680 , version 1 (20-12-2010)

Identifiers

Cite

Marcin Marszałek, Cordelia Schmid. Semantic Hierarchies for Visual Object Recognition. CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2007, Minneapolis, United States. pp.1-7, ⟨10.1109/CVPR.2007.383272⟩. ⟨inria-00548680⟩
4276 View
2516 Download

Altmetric

Share

Gmail Facebook X LinkedIn More