Skip to Main content Skip to Navigation
Conference papers

Hierarchical Part-Based Visual Object Categorization

Guillaume Bouchard 1 Bill Triggs 2 
2 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : We propose a generative model that codes the geometry and appearance of generic visual object categories as a loose hierarchy of parts, with probabilistic spatial relations linking parts to subparts, soft assignment of subparts to parts, and scale invariant keypoint based local features at the lowest level of the hierarchy. The method is designed to efficiently handle categories containing hundreds of redundant local features, such as those returned by current key-point detectors. This robustness allows it to outperform constellation style models, despite their stronger spatial models. The model is initialized by robust bottom-up voting over location-scale pyramids, and optimized by expectation-maximization. Training is rapid, and objects do not need to be marked in the training images. Experiments on several popular datasets show the method's ability to capture complex natural object classes.
Document type :
Conference papers
Complete list of metadata

Cited literature [12 references]  Display  Hide  Download
Contributor : THOTH Team Connect in order to contact the contributor
Submitted on : Monday, December 20, 2010 - 9:08:38 AM
Last modification on : Saturday, June 25, 2022 - 7:39:29 PM
Long-term archiving on: : Monday, March 21, 2011 - 3:07:51 AM


Files produced by the author(s)




Guillaume Bouchard, Bill Triggs. Hierarchical Part-Based Visual Object Categorization. IEEE Conference on Computer Vision & Pattern Recognition (CPRV '05), Jun 2005, San Diego, United States. pp.710--715, ⟨10.1109/CVPR.2005.174⟩. ⟨inria-00548513⟩



Record views


Files downloads