File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Multi-Label Classification by Semi-Supervised Singular Value Decomposition

TitleMulti-Label Classification by Semi-Supervised Singular Value Decomposition
Authors
Keywordsmulti-label
Image classification
manifold regularization
singular value decomposition
nuclear norm regularization
Issue Date2017
Citation
IEEE Transactions on Image Processing, 2017, v. 26, n. 10, p. 4612-4625 How to Cite?
Abstract© 1992-2012 IEEE. Multi-label problems arise in various domains, including automatic multimedia data categorization, and have generated significant interest in computer vision and machine learning community. However, existing methods do not adequately address two key challenges: exploiting correlations between labels and making up for the lack of labelled data or even missing labelled data. In this paper, we proposed to use a semi-supervised singular value decomposition (SVD) to handle these two challenges. The proposed model takes advantage of the nuclear norm regularization on the SVD to effectively capture the label correlations. Meanwhile, it introduces manifold regularization on mapping to capture the intrinsic structure among data, which provides a good way to reduce the required labelled data with improving the classification performance. Furthermore, we designed an efficient algorithm to solve the proposed model based on the alternating direction method of multipliers, and thus, it can efficiently deal with large-scale data sets. Experimental results for synthetic and real-world multimedia data sets demonstrate that the proposed method can exploit the label correlations and obtain promising and better label prediction results than the state-of-the-art methods.
Persistent Identifierhttp://hdl.handle.net/10722/277082
ISSN
2020 Impact Factor: 10.856
2020 SCImago Journal Rankings: 1.778
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorJing, Liping-
dc.contributor.authorShen, Chenyang-
dc.contributor.authorYang, Liu-
dc.contributor.authorYu, Jian-
dc.contributor.authorNg, Michael K.-
dc.date.accessioned2019-09-18T08:35:33Z-
dc.date.available2019-09-18T08:35:33Z-
dc.date.issued2017-
dc.identifier.citationIEEE Transactions on Image Processing, 2017, v. 26, n. 10, p. 4612-4625-
dc.identifier.issn1057-7149-
dc.identifier.urihttp://hdl.handle.net/10722/277082-
dc.description.abstract© 1992-2012 IEEE. Multi-label problems arise in various domains, including automatic multimedia data categorization, and have generated significant interest in computer vision and machine learning community. However, existing methods do not adequately address two key challenges: exploiting correlations between labels and making up for the lack of labelled data or even missing labelled data. In this paper, we proposed to use a semi-supervised singular value decomposition (SVD) to handle these two challenges. The proposed model takes advantage of the nuclear norm regularization on the SVD to effectively capture the label correlations. Meanwhile, it introduces manifold regularization on mapping to capture the intrinsic structure among data, which provides a good way to reduce the required labelled data with improving the classification performance. Furthermore, we designed an efficient algorithm to solve the proposed model based on the alternating direction method of multipliers, and thus, it can efficiently deal with large-scale data sets. Experimental results for synthetic and real-world multimedia data sets demonstrate that the proposed method can exploit the label correlations and obtain promising and better label prediction results than the state-of-the-art methods.-
dc.languageeng-
dc.relation.ispartofIEEE Transactions on Image Processing-
dc.subjectmulti-label-
dc.subjectImage classification-
dc.subjectmanifold regularization-
dc.subjectsingular value decomposition-
dc.subjectnuclear norm regularization-
dc.titleMulti-Label Classification by Semi-Supervised Singular Value Decomposition-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TIP.2017.2719939-
dc.identifier.scopuseid_2-s2.0-85023764628-
dc.identifier.volume26-
dc.identifier.issue10-
dc.identifier.spage4612-
dc.identifier.epage4625-
dc.identifier.isiWOS:000406329500002-
dc.identifier.issnl1057-7149-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats