Please use this identifier to cite or link to this item: https://doi.org/10.1109/CVPR.2013.112
DC FieldValue
dc.titleSubcategory-aware object classification
dc.contributor.authorDong, J.
dc.contributor.authorXia, W.
dc.contributor.authorChen, Q.
dc.contributor.authorFeng, J.
dc.contributor.authorHuang, Z.
dc.contributor.authorYan, S.
dc.date.accessioned2014-06-19T03:29:03Z
dc.date.available2014-06-19T03:29:03Z
dc.date.issued2013
dc.identifier.citationDong, J., Xia, W., Chen, Q., Feng, J., Huang, Z., Yan, S. (2013). Subcategory-aware object classification. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition : 827-834. ScholarBank@NUS Repository. https://doi.org/10.1109/CVPR.2013.112
dc.identifier.issn10636919
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/71894
dc.description.abstractIn this paper, we introduce a subcategory-aware object classification framework to boost category level object classification performance. Motivated by the observation of considerable intra-class diversities and inter-class ambiguities in many current object classification datasets, we explicitly split data into subcategories by ambiguity guided subcategory mining. We then train an individual model for each subcategory rather than attempt to represent an object category with a monolithic model. More specifically, we build the instance affinity graph by combining both intra-class similarity and inter-class ambiguity. Visual subcategories, which correspond to the dense sub graphs, are detected by the graph shift algorithm and seamlessly integrated into the state-of-the-art detection assisted classification framework. Finally the responses from subcategory models are aggregated by subcategory-aware kernel regression. The extensive experiments over the PASCAL VOC 2007 and PASCAL VOC 2010 databases show the state-of-the-art performance from our framework. © 2013 IEEE.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/CVPR.2013.112
dc.sourceScopus
dc.subjectAmbiguity Modeling
dc.subjectClassification
dc.subjectSubcategory Mining
dc.typeConference Paper
dc.contributor.departmentELECTRICAL & COMPUTER ENGINEERING
dc.description.doi10.1109/CVPR.2013.112
dc.description.sourcetitleProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
dc.description.page827-834
dc.description.codenPIVRE
dc.identifier.isiut000331094300105
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

69
checked on Aug 5, 2020

WEB OF SCIENCETM
Citations

48
checked on Jul 28, 2020

Page view(s)

64
checked on Aug 2, 2020

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.