Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/77326
DC FieldValueLanguage
dc.contributorDepartment of Computing-
dc.creatorShi, Y-
dc.creatorWang, K-
dc.creatorChen, C-
dc.creatorXu, L-
dc.creatorLin, L-
dc.date.accessioned2018-07-30T08:27:36Z-
dc.date.available2018-07-30T08:27:36Z-
dc.identifier.issn1520-9210-
dc.identifier.urihttp://hdl.handle.net/10397/77326-
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineersen_US
dc.subjectContext learningen_US
dc.subjectConvolutional networken_US
dc.subjectMultitask learningen_US
dc.subjectStructure-preserving image super-resolution (SR)en_US
dc.titleStructure-preserving image super-resolution via contextualized multitask learningen_US
dc.typeJournal/Magazine Articleen_US
dc.identifier.spage2804-
dc.identifier.epage2815-
dc.identifier.volume19-
dc.identifier.issue12-
dc.identifier.doi10.1109/TMM.2017.2711263-
dcterms.abstractSingle-image super-resolution (SR), which refers to reconstructing a higher resolution image from the observed low-resolution (LR) image, has received substantial attention due to its tremendous application potentials. Despite the breakthroughs of recently proposed SR methods using convolutional neural networks, their generated results usually lack of preserving structural (high-frequency) details. In this paper, regarding global boundary context and residual context as complimentary information for enhancing structural details in image restoration, we develop a contextualized multitask learning framework to address the SR problem. Specifically, our method first extracts convolutional features from the input LR image and applies one deconvolutional module to interpolate the LR feature maps in a content-adaptive way. Then, the resulting feature maps are fed into two branched subnetworks. On several standard benchmarks (e.g., Set5, Set14, and BSD200 ), our extensive evaluations demonstrate the effectiveness of our SR method on achieving both higher restoration quality and computational efficiency compared with several state-of-the-art SR approaches.-
dcterms.bibliographicCitationIEEE transactions on multimedia, 2017, v. 19, no. 127938379, p. 2804-2815-
dcterms.isPartOfIEEE transactions on multimedia-
dcterms.issued2017-
dc.identifier.scopus2-s2.0-85040586703-
dc.identifier.eissn1941-0077-
dc.identifier.artn7938379-
dc.description.validate201807 bcrc-
Appears in Collections:Journal/Magazine Article
Access
View full-text via PolyU eLinks SFX Query
Show simple item record

SCOPUSTM   
Citations

11
Last Week
1
Last month
Citations as of Feb 5, 2020

WEB OF SCIENCETM
Citations

6
Last Week
1
Last month
Citations as of Feb 12, 2020

Page view(s)

88
Last Week
6
Last month
Citations as of Feb 16, 2020

Google ScholarTM

Check

Altmetric


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