Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/82238
Full metadata record
DC FieldValueLanguage
dc.contributor.authorWeng, Chaoqunen
dc.contributor.authorWang, Hongxingen
dc.contributor.authorYuan, Junsongen
dc.contributor.authorJiang, Xudongen
dc.date.accessioned2017-07-31T06:21:01Zen
dc.date.accessioned2019-12-06T14:51:29Z-
dc.date.available2017-07-31T06:21:01Zen
dc.date.available2019-12-06T14:51:29Z-
dc.date.issued2016en
dc.identifier.citationWeng, C., Wang, H., Yuan, J., & Jiang, X. (2017). Discovering Class-Specific Spatial Layouts for Scene Recognition. IEEE Signal Processing Letters, 24(8), 1143-1147.en
dc.identifier.issn1070-9908en
dc.identifier.urihttps://hdl.handle.net/10356/82238-
dc.description.abstractScene image is a spatial composition of objects and background contexts and finding discriminative spatial layouts is critical for scene recognition. In this letter, we propose an ℓ1-regularized max-margin formulation to discover class-specific spatial layouts by jointly learning the image classifier and the class-specific spatial layouts for scene recognition. Unlike previous methods that classify images into different categories either without considering the spatial layouts explicitly or only using class generic spatial layout, our proposed method can discover a sparse combination of class-specific spatial layouts for different scenes and boost the recognition performance. Experiments on scene-15, landuse-21, and MIT indoor-67 datasets validate the advantages of our proposed algorithm.en
dc.description.sponsorshipMOE (Min. of Education, S’pore)en
dc.format.extent5 p.en
dc.language.isoenen
dc.relation.ispartofseriesIEEE Signal Processing Lettersen
dc.rights© 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: [http://dx.doi.org/10.1109/LSP.2016.2641020].en
dc.subjectDiscovering class-specific spatial layoutsen
dc.subjectScene recognitionen
dc.titleDiscovering Class-Specific Spatial Layouts for Scene Recognitionen
dc.typeJournal Articleen
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen
dc.identifier.doi10.1109/LSP.2016.2641020en
dc.description.versionAccepted versionen
item.fulltextWith Fulltext-
item.grantfulltextopen-
Appears in Collections:EEE Journal Articles
Files in This Item:
File Description SizeFormat 
Discovering Class-Specific Spatial Layouts for Scene Recognition.pdf957.99 kBAdobe PDFThumbnail
View/Open

SCOPUSTM   
Citations

5
Updated on Jul 24, 2020

PublonsTM
Citations

3
Updated on Feb 23, 2021

Page view(s)

195
Updated on Feb 24, 2021

Download(s)

89
Updated on Feb 24, 2021

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.