File Download
  Links for fulltext
     (May Require Subscription)
  • Find via Find It@HKUL
Supplementary

Conference Paper: SCaLE: Supervised and cascaded laplacian eigenmaps for visual object recognition based on nearest neighbors

TitleSCaLE: Supervised and cascaded laplacian eigenmaps for visual object recognition based on nearest neighbors
Authors
Issue Date2013
PublisherIEEE Computer Society.
Citation
The 26th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2013), Portland, OR., 23-28 June 2013. In IEEE Conference on Computer Vision and Pattern Recognition Proceedings, 2013, p. 867-874 How to Cite?
AbstractRecognizing the category of a visual object remains a challenging computer vision problem. In this paper we develop a novel deep learning method that facilitates example-based visual object category recognition. Our deep learning architecture consists of multiple stacked layers and computes an intermediate representation that can be fed to a nearest-neighbor classifier. This intermediate representation is discriminative and structure-preserving. It is also capable of extracting essential characteristics shared by objects in the same category while filtering out nonessential differences among them. Each layer in our model is a nonlinear mapping, whose parameters are learned through two sequential steps that are designed to achieve the aforementioned properties. The first step computes a discrete mapping called supervised Laplacian Eigenmap. The second step computes a continuous mapping from the discrete version through nonlinear regression. We have extensively tested our method and it achieves state-of-the-art recognition rates on a number of benchmark datasets.
DescriptionThis CVPR 2013 paper is the Open Access version, provided by the Computer Vision Foundation. The authoritative version of this paper is available in IEEE Xplore (NYP).
Persistent Identifierhttp://hdl.handle.net/10722/186496
ISSN

 

DC FieldValueLanguage
dc.contributor.authorWu, Ren_US
dc.contributor.authorYu, Yen_US
dc.contributor.authorWang, WPen_US
dc.date.accessioned2013-08-20T12:11:14Z-
dc.date.available2013-08-20T12:11:14Z-
dc.date.issued2013en_US
dc.identifier.citationThe 26th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2013), Portland, OR., 23-28 June 2013. In IEEE Conference on Computer Vision and Pattern Recognition Proceedings, 2013, p. 867-874en_US
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10722/186496-
dc.descriptionThis CVPR 2013 paper is the Open Access version, provided by the Computer Vision Foundation. The authoritative version of this paper is available in IEEE Xplore (NYP).-
dc.description.abstractRecognizing the category of a visual object remains a challenging computer vision problem. In this paper we develop a novel deep learning method that facilitates example-based visual object category recognition. Our deep learning architecture consists of multiple stacked layers and computes an intermediate representation that can be fed to a nearest-neighbor classifier. This intermediate representation is discriminative and structure-preserving. It is also capable of extracting essential characteristics shared by objects in the same category while filtering out nonessential differences among them. Each layer in our model is a nonlinear mapping, whose parameters are learned through two sequential steps that are designed to achieve the aforementioned properties. The first step computes a discrete mapping called supervised Laplacian Eigenmap. The second step computes a continuous mapping from the discrete version through nonlinear regression. We have extensively tested our method and it achieves state-of-the-art recognition rates on a number of benchmark datasets.-
dc.languageengen_US
dc.publisherIEEE Computer Society.-
dc.relation.ispartofIEEE Conference on Computer Vision and Pattern Recognition Proceedingsen_US
dc.rightsIEEE Conference on Computer Vision and Pattern Recognition Proceedings. Copyright © IEEE Computer Society.-
dc.rights©2013 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.titleSCaLE: Supervised and cascaded laplacian eigenmaps for visual object recognition based on nearest neighborsen_US
dc.typeConference_Paperen_US
dc.identifier.emailWU, R: rbwu@cs.hku.hken_US
dc.identifier.emailYu, Y: yzyu@cs.hku.hken_US
dc.identifier.emailWang, WP: wenping@cs.hku.hk-
dc.identifier.authorityYu, Y=rp01415en_US
dc.identifier.authorityWang, WP=rp00186en_US
dc.description.naturepostprint-
dc.identifier.hkuros220948en_US
dc.identifier.spage867-
dc.identifier.epage874-
dc.publisher.placeUnited States-
dc.customcontrol.immutablesml 130830-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats