File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Category-specific incremental visual codebook training for scene categorization

TitleCategory-specific incremental visual codebook training for scene categorization
Authors
KeywordsIncremental learning
Scene categorization
Visual codebook
Issue Date2010
PublisherI E E E. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000349
Citation
The 17th IEEE International Conference on Image Processing (ICIP 2010), Hong Kong, China, 26-29 September 2010. In Proceedings of 17th ICIP, 2010, p. 1501-1504 How to Cite?
AbstractIn this paper, we propose a category-specific incremental visual codebook training method for scene categorization. In this method, based on a preliminary codebook trained from a subset of training samples, we incrementally introduce the remaining training samples to enrich the content of the visual codebook. Then, the incremental learned codebook is used to encode the images for scene categorization. The advantages of the proposed method are (1) computationally efficient comparing with batch mode clustering method; (2) the number of visual words is determined automatically in the incremental learning procedure; (3) scene categorization performance is improved using the enriched codebook comparing with using the codebook trained from a subset of training samples. The experimental results show the effectiveness of the proposed method. © 2010 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/137722
ISBN
ISSN
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorQin, Jen_HK
dc.contributor.authorYung, NHCen_HK
dc.date.accessioned2011-08-26T14:32:26Z-
dc.date.available2011-08-26T14:32:26Z-
dc.date.issued2010en_HK
dc.identifier.citationThe 17th IEEE International Conference on Image Processing (ICIP 2010), Hong Kong, China, 26-29 September 2010. In Proceedings of 17th ICIP, 2010, p. 1501-1504en_HK
dc.identifier.isbn978-1-4244-7994-8en_US
dc.identifier.issn1522-4880en_HK
dc.identifier.urihttp://hdl.handle.net/10722/137722-
dc.description.abstractIn this paper, we propose a category-specific incremental visual codebook training method for scene categorization. In this method, based on a preliminary codebook trained from a subset of training samples, we incrementally introduce the remaining training samples to enrich the content of the visual codebook. Then, the incremental learned codebook is used to encode the images for scene categorization. The advantages of the proposed method are (1) computationally efficient comparing with batch mode clustering method; (2) the number of visual words is determined automatically in the incremental learning procedure; (3) scene categorization performance is improved using the enriched codebook comparing with using the codebook trained from a subset of training samples. The experimental results show the effectiveness of the proposed method. © 2010 IEEE.en_HK
dc.languageengen_US
dc.publisherI E E E. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000349en_HK
dc.relation.ispartofProceedings of the IEEE International Conference on Image Processing, ICIP 2010en_HK
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.rightsIEEE International Conference on Image Processing Proceedings. Copyright © IEEE.-
dc.rights©2010 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.subjectIncremental learningen_HK
dc.subjectScene categorizationen_HK
dc.subjectVisual codebooken_HK
dc.titleCategory-specific incremental visual codebook training for scene categorizationen_HK
dc.typeConference_Paperen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=978-1-4244-7994-8&volume=&spage=1501&epage=1504&date=2010&atitle=Category-specific+incremental+visual+codebook+training+for+scene+categorizationen_US
dc.identifier.emailYung, NHC:nyung@eee.hku.hken_HK
dc.identifier.authorityYung, NHC=rp00226en_HK
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1109/ICIP.2010.5652347en_HK
dc.identifier.scopuseid_2-s2.0-78651071047en_HK
dc.identifier.hkuros190986en_US
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-78651071047&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.spage1501en_HK
dc.identifier.epage1504en_HK
dc.identifier.isiWOS:000287728001149-
dc.publisher.placeUnited Statesen_HK
dc.description.otherThe 17th IEEE International Conference on Image Processing (ICIP 2010), Hong Kong, China, 26-29 September 2010. In Proceedings of 17th ICIP, 2010, p. 1501-1504-
dc.identifier.scopusauthoridQin, J=24450951900en_HK
dc.identifier.scopusauthoridYung, NHC=7003473369en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats