Robust Low-Rank Tensor Minimization via a New Tensor Spectral k -Support Norm
Recently, based on a new tensor algebraic framework for third-order tensors, the tensor singular value decomposition (t-SVD) and its associated tubal rank definition have shed new light on low-rank tensor modeling. Its applications to robust image/video recovery and background modeling show promisin...
Uložené v:
| Vydané v: | IEEE transactions on image processing Ročník 29; s. 2314 - 2327 |
|---|---|
| Hlavní autori: | , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
United States
IEEE
01.01.2020
|
| Predmet: | |
| ISSN: | 1057-7149, 1941-0042, 1941-0042 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Recently, based on a new tensor algebraic framework for third-order tensors, the tensor singular value decomposition (t-SVD) and its associated tubal rank definition have shed new light on low-rank tensor modeling. Its applications to robust image/video recovery and background modeling show promising performance due to its superior capability in modeling cross-channel/frame information. Under the t-SVD framework, we propose a new tensor norm called tensor spectral k-support norm (TSP-k) by an alternative convex relaxation. As an interpolation between the existing tensor nuclear norm (TNN) and tensor Frobenius norm (TFN), it is able to simultaneously drive minor singular values to zero to induce low-rankness, and to capture more global information for better preserving intrinsic structure. We provide the proximal operator and the polar operator for the TSP-k norm as key optimization blocks, along with two showcase optimization algorithms for mediumand large-size tensors. Experiments on synthetic, image and video datasets in medium and large sizes, all verify the superiority of the TSP-k norm and the effectiveness of both optimization methods in comparison with the existing counterparts. |
|---|---|
| AbstractList | Recently, based on a new tensor algebraic framework for third-order tensors, the tensor singular value decomposition (t-SVD) and its associated tubal rank definition have shed new light on low-rank tensor modeling. Its applications to robust image/video recovery and background modeling show promising performance due to its superior capability in modeling cross-channel/frame information. Under the t-SVD framework, we propose a new tensor norm called tensor spectral k-support norm (TSP-k) by an alternative convex relaxation. As an interpolation between the existing tensor nuclear norm (TNN) and tensor Frobenius norm (TFN), it is able to simultaneously drive minor singular values to zero to induce low-rankness, and to capture more global information for better preserving intrinsic structure. We provide the proximal operator and the polar operator for the TSP-k norm as key optimization blocks, along with two showcase optimization algorithms for medium-and large-size tensors. Experiments on synthetic, image and video datasets in medium and large sizes, all verify the superiority of the TSP-k norm and the effectiveness of both optimization methods in comparison with the existing counterparts. Recently, based on a new tensor algebraic framework for third-order tensors, the tensor singular value decomposition (t-SVD) and its associated tubal rank definition have shed new light on low-rank tensor modeling. Its applications to robust image/video recovery and background modeling show promising performance due to its superior capability in modeling cross-channel/frame information. Under the t-SVD framework, we propose a new tensor norm called tensor spectral k-support norm (TSP-k) by an alternative convex relaxation. As an interpolation between the existing tensor nuclear norm (TNN) and tensor Frobenius norm (TFN), it is able to simultaneously drive minor singular values to zero to induce low-rankness, and to capture more global information for better preserving intrinsic structure. We provide the proximal operator and the polar operator for the TSP-k norm as key optimization blocks, along with two showcase optimization algorithms for medium-and large-size tensors. Experiments on synthetic, image and video datasets in medium and large sizes, all verify the superiority of the TSP-k norm and the effectiveness of both optimization methods in comparison with the existing counterparts.Recently, based on a new tensor algebraic framework for third-order tensors, the tensor singular value decomposition (t-SVD) and its associated tubal rank definition have shed new light on low-rank tensor modeling. Its applications to robust image/video recovery and background modeling show promising performance due to its superior capability in modeling cross-channel/frame information. Under the t-SVD framework, we propose a new tensor norm called tensor spectral k-support norm (TSP-k) by an alternative convex relaxation. As an interpolation between the existing tensor nuclear norm (TNN) and tensor Frobenius norm (TFN), it is able to simultaneously drive minor singular values to zero to induce low-rankness, and to capture more global information for better preserving intrinsic structure. We provide the proximal operator and the polar operator for the TSP-k norm as key optimization blocks, along with two showcase optimization algorithms for medium-and large-size tensors. Experiments on synthetic, image and video datasets in medium and large sizes, all verify the superiority of the TSP-k norm and the effectiveness of both optimization methods in comparison with the existing counterparts. Recently, based on a new tensor algebraic framework for third-order tensors, the tensor singular value decomposition (t-SVD) and its associated tubal rank definition have shed new light on low-rank tensor modeling. Its applications to robust image/video recovery and background modeling show promising performance due to its superior capability in modeling cross-channel/frame information. Under the t-SVD framework, we propose a new tensor norm called tensor spectral k-support norm (TSP-k) by an alternative convex relaxation. As an interpolation between the existing tensor nuclear norm (TNN) and tensor Frobenius norm (TFN), it is able to simultaneously drive minor singular values to zero to induce low-rankness, and to capture more global information for better preserving intrinsic structure. We provide the proximal operator and the polar operator for the TSP-k norm as key optimization blocks, along with two showcase optimization algorithms for mediumand large-size tensors. Experiments on synthetic, image and video datasets in medium and large sizes, all verify the superiority of the TSP-k norm and the effectiveness of both optimization methods in comparison with the existing counterparts. |
| Author | Lou, Jian Cheung, Yiu-Ming |
| Author_xml | – sequence: 1 givenname: Jian orcidid: 0000-0002-4110-2068 surname: Lou fullname: Lou, Jian email: jian.lou@emory.edu organization: Department of Computer Science, Emory University, Atlanta, GA, USA – sequence: 2 givenname: Yiu-Ming orcidid: 0000-0001-7629-4648 surname: Cheung fullname: Cheung, Yiu-Ming email: ymc@comp.hkbu.edu.hk organization: Department of Computer Science, Hong Kong Baptist University, Hong Kong |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/31634129$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kM9LwzAUgINMdJveBUFy9NKZ1yRtcpThL5hTdJ5L1iYQbZuatA796-3c5sGDpzzI970H3wgNaldrhE6ATACIvFjcPU5iAnISS5YwxvfQECSDiBAWD_qZ8DRKgclDNArhlRBgHJIDdEghoQxiOUT3T27ZhRbP3Cp6UvUbXug6OI_vbW0r-6Va62r8YRVWeK5Xu9_nRuetVyV-w9Fz1zTOt3jufHWE9o0qgz7evmP0cn21mN5Gs4ebu-nlLMqp4G20LFQiKC1AJUQKo5ZGgcmTVFNpDOGy0IVSWuZSAIt5kSpphBCcpIbRXFKgY3S-2dt4997p0GaVDbkuS1Vr14UspiRNGXDGe_Rsi3bLShdZ422l_Ge2S9ADZAPk3oXgtflFgGTryllfOVtXzraVeyX5o-S2_UnVR7Hlf-LpRrRa6987QqQ9xOg3avCIag |
| CODEN | IIPRE4 |
| CitedBy_id | crossref_primary_10_1109_ACCESS_2022_3186364 crossref_primary_10_1109_TAES_2022_3209638 crossref_primary_10_1109_TKDE_2022_3218846 crossref_primary_10_1007_s10915_021_01679_6 crossref_primary_10_1109_TGRS_2023_3277848 crossref_primary_10_1109_TIP_2022_3155949 crossref_primary_10_1016_j_sigpro_2024_109407 crossref_primary_10_1109_JSTSP_2021_3058763 crossref_primary_10_1109_LGRS_2022_3186877 crossref_primary_10_1109_TCSVT_2024_3442295 crossref_primary_10_1109_ACCESS_2020_3024635 crossref_primary_10_1109_LCOMM_2021_3097158 crossref_primary_10_1109_JIOT_2024_3451713 crossref_primary_10_1109_TETCI_2024_3425329 crossref_primary_10_1109_TIP_2024_3385284 crossref_primary_10_1080_10618600_2025_2500977 crossref_primary_10_1109_TSP_2025_3569861 crossref_primary_10_1016_j_ymeth_2024_09_015 crossref_primary_10_1109_JBHI_2022_3231908 |
| Cites_doi | 10.1007/s10851-010-0251-1 10.1109/TIP.2014.2305840 10.1109/TNNLS.2016.2611525 10.1561/2400000003 10.1007/s10107-014-0790-0 10.1109/CVPR.2017.419 10.1137/110837711 10.1561/2200000016 10.1109/TPAMI.2017.2689021 10.1109/TKDE.2013.48 10.1073/pnas.0709146104 10.1109/TIP.2016.2627803 10.1137/090771806 10.1109/TSP.2016.2639466 10.1137/130905010 10.1137/0716071 10.1137/07070111X 10.1007/s10957-012-0245-9 10.1109/CVPR.2016.567 10.1109/CVPR.2014.485 10.1137/15M101628X 10.1109/ICCV.2001.937655 10.1137/110836936 10.7146/dpb.v27i537.7070 10.1007/s10994-013-5366-3 10.1002/1099-128X(200005/06)14:3<105::AID-CEM582>3.0.CO;2-I 10.1515/9781400873173 10.1109/TGRS.2017.2786718 10.1007/BF02310791 10.1137/1.9781611972795.91 10.1109/TPAMI.2012.39 10.1109/TPAMI.2015.2465956 10.1002/nav.3800030109 10.1007/BF02289464 |
| ContentType | Journal Article |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7X8 |
| DOI | 10.1109/TIP.2019.2946445 |
| DatabaseName | IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | PubMed MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Engineering Computer Science |
| EISSN | 1941-0042 |
| EndPage | 2327 |
| ExternalDocumentID | 31634129 10_1109_TIP_2019_2946445 8870194 |
| Genre | orig-research Journal Article |
| GrantInformation_xml | – fundername: SZSTI grantid: JCYJ20160531194006833 – fundername: National Natural Science Foundation of China grantid: 61672444; 61272366 funderid: 10.13039/501100001809 – fundername: Faculty Research Grant of HKBU grantid: FRG2/17-18/082 – fundername: Hong Kong Baptist University grantid: RC-FNRA-IG/18-19/SCI/03 funderid: 10.13039/501100001747 – fundername: Innovation and Technology Fund grantid: ITS/339/18 funderid: 10.13039/501100010428 |
| GroupedDBID | --- -~X .DC 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABFSI ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P RIA RIE RNS TAE TN5 VH1 AAYXX CITATION NPM RIG Z5M 7X8 |
| ID | FETCH-LOGICAL-c385t-bda6833d1a6098fabfa1fc67e39ff059dedaae9c981425d7a9f888507f43c9313 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 26 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000507869900009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1057-7149 1941-0042 |
| IngestDate | Thu Oct 02 19:01:19 EDT 2025 Wed Feb 19 02:09:35 EST 2025 Tue Nov 18 22:35:26 EST 2025 Sat Nov 29 03:21:11 EST 2025 Wed Aug 27 02:40:56 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c385t-bda6833d1a6098fabfa1fc67e39ff059dedaae9c981425d7a9f888507f43c9313 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0002-4110-2068 0000-0001-7629-4648 |
| PMID | 31634129 |
| PQID | 2307741545 |
| PQPubID | 23479 |
| PageCount | 14 |
| ParticipantIDs | pubmed_primary_31634129 crossref_primary_10_1109_TIP_2019_2946445 crossref_citationtrail_10_1109_TIP_2019_2946445 proquest_miscellaneous_2307741545 ieee_primary_8870194 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-01-01 |
| PublicationDateYYYYMMDD | 2020-01-01 |
| PublicationDate_xml | – month: 01 year: 2020 text: 2020-01-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | IEEE transactions on image processing |
| PublicationTitleAbbrev | TIP |
| PublicationTitleAlternate | IEEE Trans Image Process |
| PublicationYear | 2020 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| References | ref13 ref12 jaggi (ref38) 2013 ref14 aravkin (ref46) 2016 ref11 ref10 ref17 ref18 dabov (ref49) 2007 ref45 ref48 ref47 ref42 ref41 ref44 ref43 mcdonald (ref26) 2014 ref8 boumal (ref5) 2011 ref7 ref9 ref4 ref3 ref6 yurtsever (ref31) 2015 ref40 mu (ref16) 2014 ref35 eriksson (ref25) 2015 ref34 lu (ref20) 2018 ref37 ref36 ref30 ref33 ref2 ref1 argyriou (ref24) 2012 yu (ref39) 2017; 18 ref23 ref22 hillar (ref15) 2009; 60 ref21 ref28 ref29 jiang (ref32) 2017 romera-paredes (ref19) 2013 mcdonald (ref27) 2016; 17 |
| References_xml | – ident: ref42 doi: 10.1007/s10851-010-0251-1 – year: 2016 ident: ref46 article-title: Level-set methods for convex optimization publication-title: arXiv 1602 01506 – ident: ref33 doi: 10.1109/TIP.2014.2305840 – start-page: 145 year: 2007 ident: ref49 article-title: Video denoising by sparse 3d transform-domain collaborative filtering publication-title: Proc 15th Eur Signal Process Conf – year: 2018 ident: ref20 article-title: Tensor robust principal component analysis with a new tensor nuclear norm publication-title: arXiv 1804 03728 – year: 2017 ident: ref32 article-title: Exact tensor completion from sparsely corrupted observations via convex optimization publication-title: arXiv 1708 00601 – start-page: 3150 year: 2015 ident: ref31 article-title: A universal primal-dual convex optimization framework publication-title: Proc NIPS – ident: ref21 doi: 10.1109/TNNLS.2016.2611525 – ident: ref36 doi: 10.1561/2400000003 – ident: ref30 doi: 10.1007/s10107-014-0790-0 – ident: ref4 doi: 10.1109/CVPR.2017.419 – ident: ref14 doi: 10.1137/110837711 – volume: 60 start-page: 45 year: 2009 ident: ref15 article-title: Most tensor problems are NP-hard publication-title: J ACM – ident: ref29 doi: 10.1561/2200000016 – ident: ref45 doi: 10.1109/TPAMI.2017.2689021 – ident: ref7 doi: 10.1109/TKDE.2013.48 – ident: ref10 doi: 10.1073/pnas.0709146104 – ident: ref23 doi: 10.1109/TIP.2016.2627803 – ident: ref35 doi: 10.1137/090771806 – ident: ref8 doi: 10.1109/TSP.2016.2639466 – ident: ref9 doi: 10.1137/130905010 – ident: ref44 doi: 10.1137/0716071 – start-page: 3349 year: 2015 ident: ref25 article-title: The $\kappa$ -support norm and convex envelopes of cardinality and rank publication-title: Proc CVPR – ident: ref17 doi: 10.1137/07070111X – start-page: 2967 year: 2013 ident: ref19 article-title: A new convex relaxation for tensor completion publication-title: Proc NIPS – start-page: 406 year: 2011 ident: ref5 article-title: RTRMC: A Riemannian trust-region method for low-rank matrix completion publication-title: Proc NIPS – ident: ref43 doi: 10.1007/s10957-012-0245-9 – ident: ref2 doi: 10.1109/CVPR.2016.567 – ident: ref1 doi: 10.1109/CVPR.2014.485 – start-page: 427 year: 2013 ident: ref38 article-title: Revisiting Frank-Wolfe: Projection-free sparse convex optimization publication-title: Proc Int Conf Mach Learn – ident: ref40 doi: 10.1137/15M101628X – ident: ref47 doi: 10.1109/ICCV.2001.937655 – ident: ref28 doi: 10.1137/110836936 – ident: ref34 doi: 10.7146/dpb.v27i537.7070 – ident: ref18 doi: 10.1007/s10994-013-5366-3 – volume: 18 start-page: 5279 year: 2017 ident: ref39 article-title: Generalized conditional gradient for sparse estimation publication-title: J Mach Learn Res – volume: 17 start-page: 1 year: 2016 ident: ref27 article-title: New perspectives on $\kappa$ -support and cluster norms publication-title: J Mach Learn Res – start-page: 1457 year: 2012 ident: ref24 article-title: Sparse prediction with the $\kappa$ -support norm publication-title: Proc NIPS – ident: ref12 doi: 10.1002/1099-128X(200005/06)14:3<105::AID-CEM582>3.0.CO;2-I – ident: ref41 doi: 10.1515/9781400873173 – ident: ref22 doi: 10.1109/TGRS.2017.2786718 – ident: ref11 doi: 10.1007/BF02310791 – ident: ref6 doi: 10.1137/1.9781611972795.91 – ident: ref3 doi: 10.1109/TPAMI.2012.39 – start-page: 73 year: 2014 ident: ref16 article-title: Square deal: Lower bounds and improved relaxations for tensor recovery publication-title: Proc Int Conf Mach Learn – ident: ref48 doi: 10.1109/TPAMI.2015.2465956 – ident: ref37 doi: 10.1002/nav.3800030109 – start-page: 3644 year: 2014 ident: ref26 article-title: Spectral $\kappa$ -support norm regularization publication-title: Proc NIPS – ident: ref13 doi: 10.1007/BF02289464 |
| SSID | ssj0014516 |
| Score | 2.4728894 |
| Snippet | Recently, based on a new tensor algebraic framework for third-order tensors, the tensor singular value decomposition (t-SVD) and its associated tubal rank... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 2314 |
| SubjectTerms | alternating direction method of multipliers Computational modeling Computer science Computer vision conditional gradient descent Minimization Optimization proximal algorithm Robust low-rank tensor minimization Task analysis tensor robust principal component analysis tensor singular value decomposition (t-SVD) |
| Title | Robust Low-Rank Tensor Minimization via a New Tensor Spectral k -Support Norm |
| URI | https://ieeexplore.ieee.org/document/8870194 https://www.ncbi.nlm.nih.gov/pubmed/31634129 https://www.proquest.com/docview/2307741545 |
| Volume | 29 |
| WOSCitedRecordID | wos000507869900009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1941-0042 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014516 issn: 1057-7149 databaseCode: RIE dateStart: 19920101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB60eNCD9W19EcGLYGxr0s3mKKIoaBGp0Nsym2ShVHelD_37TvaFggreljyWJV9m881Mkg_ghCiq7DkT8ljGmksMDNfaOp4oaVGRdXVEITah-v1wONSPC3BWn4VxzuWbz9y5f8xz-TYzcx8qa5NBECORi7CoVFCc1aozBl5wNs9s9hRXRPurlGRHtwd3j34Plz6_0JKW_963JSjXVPmdXubLzE3zfx-4BqslnWSXBf7rsODSDWiW1JKVhjulokq9oSrbgJUvVxFuwsNTFs-nM3afffAnTMdsQP5tNmEPo3T0Wp7VZO8jZMjov1jVevV6HyphY8a9PihxedYnFrwFzzfXg6tbXkotcCPC3ozHFoNQCNvFoKPDBOMEu4kJlBM6SYiBWWcRnTY67JKRW4U6IdeZuGQihdGiK7ahkWap2wUWo8BAUTViIA3G5NBZY7WMQ-m5jmxBuxr9yJT3kHs5jJco90c6OiK8Io9XVOLVgtO6x1txB8cfbTc9LHW7EpEWHFcAR2Q_PimCqcvm08hvhPesynfdKZCvOwsiq5II0d7PL92H5QvvfecBmQNozCZzdwhL5n02mk6OaJIOw6N8kn4Cc1Th-g |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlZ3fS-QwEMcH9QTPB3-ft96dRvBFMO6uybbN43GcKLe7iKzgW5kmKSzetbI_vH_fmW5aPFDh3kqalNLJNJ_JJPkCnBCi6p63icx0ZqTGyEpjnJd5rB3G5F0dtRCbiIfD5P7e3CzBWbMXxntfLT7z53xZ5fJdaec8VdYmhyAi0cvwgZWzwm6tJmfAkrNVbrMXy5jAv05Kdkx7dH3Dq7jM-YXRBAC9fwahSlXlbcCsBprLzf97xS3YCEApvi96wDYs-WIHNgNciuC6Uyqq9Rvqsh1Yf3EY4S4MbstsPp2JfvlX3mLxIEYU4ZYTMRgX4z9ht6Z4GqNAQX_G-i7r1_NkiXgQkhVCiebFkDh4D-4uf45-XMkgtiCtSnozmTmMEqVcF6OOSXLMcuzmNoq9MnlODOa8Q_TGmqRLbu5iNDkFz0STuVbWqK76BCtFWfjPIDJUGMV0GzHSFjMK6Zx1RmeJZtrRLWjXXz-14SRyFsT4nVYRScekZK-U7ZUGe7XgtGnxuDiF4526u2yWpl6wSAuOawOn5EGcFsHCl_Npykvhmau46f7C8k1jRbiqCYkOXn_oEaxdjQb9tH89_PUFPl5wLF5Nz3yFldlk7r_Bqn2ajaeTw6qrPgML-uRb |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Robust+Low-Rank+Tensor+Minimization+via+a+New+Tensor+Spectral+k-Support+Norm&rft.jtitle=IEEE+transactions+on+image+processing&rft.au=Lou%2C+Jian&rft.au=Cheung%2C+Yiu-Ming&rft.date=2020-01-01&rft.issn=1941-0042&rft.eissn=1941-0042&rft_id=info:doi/10.1109%2FTIP.2019.2946445&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1057-7149&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1057-7149&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1057-7149&client=summon |