Skip to Main content Skip to Navigation
Conference papers

Combining regions and patches for object class localization

Caroline Pantofaru 1 Gyuri Dorkó 2 Cordelia Schmid 3, * Martial Hebert 1 
* Corresponding author
3 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 introduce a method for object class detection and localization which combines regions generated by image segmentation with local patches. Region-based descriptors can model and match regular textures reliably, but fail on parts of the object which are textureless. They also cannot repeatably identify interest points on their boundaries. By incorporating information from patch-based descriptors near the regions into a new feature, the Region-based Context Feature (RCF), we can address these issues. We apply Region-based Context Features in a semi-supervised learning framework for object detection and localization. This framework produces object-background segmentation masks of deformable objects. Numerical results are presented for pixel-level performance.
Document type :
Conference papers
Complete list of metadata

Cited literature [25 references]  Display  Hide  Download
Contributor : THOTH Team Connect in order to contact the contributor
Submitted on : Monday, December 20, 2010 - 9:49:22 AM
Last modification on : Wednesday, September 7, 2022 - 3:36:04 PM
Long-term archiving on: : Monday, March 21, 2011 - 3:19:50 AM


Files produced by the author(s)




Caroline Pantofaru, Gyuri Dorkó, Cordelia Schmid, Martial Hebert. Combining regions and patches for object class localization. Conference on Computer Vision and Pattern Recognition Workshop (Beyond Patches workshop, CVPR '06), Jun 2006, New York, United States. pp.23, ⟨10.1109/CVPRW.2006.57⟩. ⟨inria-00548581⟩



Record views


Files downloads