Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorXi, Yueen_US
dc.contributor.authorZheng, Jiangbinen_US
dc.contributor.authorJia, Wenjingen_US
dc.contributor.authorHe, Xiangjianen_US
dc.contributor.authorLi, Hanhuien_US
dc.contributor.authorRen, Zhuqiangen_US
dc.contributor.authorLam, Kin-Manen_US
dc.identifier.citationXi, Y., Zheng, J., Jia, W., He, X., Li, H., Ren, Z., & Lam, K.-M. (2020). See clearly in the distance : representation learning GAN for low resolution object recognition. IEEE Access, 8, 53203-53214. doi:10.1109/ACCESS.2020.2978980en_US
dc.description.abstractIdentifying tiny objects with extremely low resolution is generally considered a very challenging task even for human vision, due to limited information presented inside the object areas. There have been very limited attempts in recent years to deal with low-resolution recognition. The existing solutions rely on either generating super-resolution images or learning multi-scale features. However, their performance improvement becomes very limited, especially when the resolution becomes very low. In this paper, we propose a Representation Learning Generative Adversarial Network (RL-GAN) to generate super image representation that is optimized for recognition. Our solution deals with the classical vision task of object recognition in the distance. We evaluate our idea on the challenging task of low-resolution object recognition. Comparison of experimental results conducted on public and our newly created WIDER-SHIP datasets demonstrate the effectiveness of our RL-GAN, which improves the classification results significantly, with 10-15% gain on average, compared with benchmark solutions.en_US
dc.relation.ispartofIEEE Accessen_US
dc.rights© 2020 IEEE. This journal is 100% open access, which means that all content is freely available without charge to users or their institutions. All articles accepted after 12 June 2019 are published under a CC BY 4.0 license, and the author retains copyright. Users are allowed to read, download, copy, distribute, print, search, or link to the full texts of the articles, or use them for any other lawful purpose, as long as proper attribution is given.en_US
dc.subjectEngineering::Computer science and engineeringen_US
dc.titleSee clearly in the distance : representation learning GAN for low resolution object recognitionen_US
dc.typeJournal Articleen
dc.contributor.researchInstitute for Media Innovation (IMI)en_US
dc.description.versionPublished versionen_US
dc.subject.keywordsGenerative Adversarial Networksen_US
dc.subject.keywordsLow Resolution Object Recognitionen_US
item.fulltextWith Fulltext-
Appears in Collections:IMI Journal Articles
Files in This Item:
File Description SizeFormat 
09026982.pdf8.06 MBAdobe PDFThumbnail

Citations 20

Updated on Dec 10, 2023

Web of ScienceTM
Citations 50

Updated on Oct 27, 2023

Page view(s)

Updated on Dec 7, 2023

Download(s) 50

Updated on Dec 7, 2023

Google ScholarTM




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