Deep Spatial-Spectral Subspace Clustering for Hyperspectral Image
Hyperspectral image (HSI) clustering is a challenging task due to the complex characteristics in HSI data, such as spatial-spectral structure, high-dimension, and large spectral variability. In this paper, we propose a novel deep spatial-spectral subspace clustering network (DS3 C -Net), which explo...
Saved in:
| Published in | IEEE transactions on circuits and systems for video technology Vol. 31; no. 7; pp. 2686 - 2697 |
|---|---|
| Main Authors | , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
New York
IEEE
01.07.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Hyperspectral image (HSI) clustering is a challenging task due to the complex characteristics in HSI data, such as spatial-spectral structure, high-dimension, and large spectral variability. In this paper, we propose a novel deep spatial-spectral subspace clustering network (DS3 C -Net), which explores spatial-spectral information via the multi-scale auto-encoder and collaborative constraint. Considering the structure correlations of HSI, the multi-scale auto-encoder is first designed to extract spatial-spectral features with different-scale pixel blocks which are selected as the inputs. Then, the collaborative constrained self-expressive layers are introduced between the encoder and decoder, to capture the self-expressive subspace structures. By designing a self-expressiveness similarity constraint, the proposed network is trained collaboratively, and the affinity matrices of the feature representation are learned in an end-to-end manner. Based on the affinity matrices, the spectral clustering algorithm is utilized to obtain the final HSI clustering result. Experimental results on three widely used hyperspectral image datasets demonstrate that the proposed method outperforms state-of-the-art methods. |
|---|---|
| AbstractList | Hyperspectral image (HSI) clustering is a challenging task due to the complex characteristics in HSI data, such as spatial-spectral structure, high-dimension, and large spectral variability. In this paper, we propose a novel deep spatial-spectral subspace clustering network (DS3C-Net), which explores spatial-spectral information via the multi-scale auto-encoder and collaborative constraint. Considering the structure correlations of HSI, the multi-scale auto-encoder is first designed to extract spatial-spectral features with different-scale pixel blocks which are selected as the inputs. Then, the collaborative constrained self-expressive layers are introduced between the encoder and decoder, to capture the self-expressive subspace structures. By designing a self-expressiveness similarity constraint, the proposed network is trained collaboratively, and the affinity matrices of the feature representation are learned in an end-to-end manner. Based on the affinity matrices, the spectral clustering algorithm is utilized to obtain the final HSI clustering result. Experimental results on three widely used hyperspectral image datasets demonstrate that the proposed method outperforms state-of-the-art methods. Hyperspectral image (HSI) clustering is a challenging task due to the complex characteristics in HSI data, such as spatial-spectral structure, high-dimension, and large spectral variability. In this paper, we propose a novel deep spatial-spectral subspace clustering network (DS3 C -Net), which explores spatial-spectral information via the multi-scale auto-encoder and collaborative constraint. Considering the structure correlations of HSI, the multi-scale auto-encoder is first designed to extract spatial-spectral features with different-scale pixel blocks which are selected as the inputs. Then, the collaborative constrained self-expressive layers are introduced between the encoder and decoder, to capture the self-expressive subspace structures. By designing a self-expressiveness similarity constraint, the proposed network is trained collaboratively, and the affinity matrices of the feature representation are learned in an end-to-end manner. Based on the affinity matrices, the spectral clustering algorithm is utilized to obtain the final HSI clustering result. Experimental results on three widely used hyperspectral image datasets demonstrate that the proposed method outperforms state-of-the-art methods. |
| Author | Ling, Nam Huang, Qingming Li, Xinyu Lei, Jianjun Peng, Bo Fang, Leyuan |
| Author_xml | – sequence: 1 givenname: Jianjun orcidid: 0000-0003-3171-7680 surname: Lei fullname: Lei, Jianjun email: jjlei@tju.edu.cn organization: School of Electrical and Information Engineering, Tianjin University, Tianjin, China – sequence: 2 givenname: Xinyu surname: Li fullname: Li, Xinyu email: 601014361@qq.com organization: School of Electrical and Information Engineering, Tianjin University, Tianjin, China – sequence: 3 givenname: Bo orcidid: 0000-0002-6616-453X surname: Peng fullname: Peng, Bo email: bpeng@tju.edu.cn organization: School of Electrical and Information Engineering, Tianjin University, Tianjin, China – sequence: 4 givenname: Leyuan orcidid: 0000-0003-2351-4461 surname: Fang fullname: Fang, Leyuan email: fangleyuan@gmail.com organization: College of Electrical and Information Engineering, Hunan University, Changsha, China – sequence: 5 givenname: Nam orcidid: 0000-0002-5741-7937 surname: Ling fullname: Ling, Nam email: nling@scu.edu organization: Department of Computer Science and Engineering, Santa Clara University, Santa Clara, CA, USA – sequence: 6 givenname: Qingming orcidid: 0000-0001-7542-296X surname: Huang fullname: Huang, Qingming email: qmhuang@ucas.ac.cn organization: School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China |
| BookMark | eNp9kD1PwzAQhi1UJFrgD8ASiTnFdvw5VuGjlSoxpLBaTnKpUqVJsJOh_x6XFgYGprvhfe7VPTM0absWELojeE4I1o-bNPvYzCmmeJ5gKgURF2hKOFcxpZhPwo45iRUl_ArNvN9hTJhicooWTwB9lPV2qG0TZz0Ug7NNlI25720BUdqMfgBXt9uo6ly0PPTg_E9qtbdbuEGXlW083J7nNXp_ed6ky3j99rpKF-u4oJoPMc0lVQnVBZG4tIlOcsKkrqQsWVlKXVoZpioFY9xqzq3NC1VRLThQbZXOk2v0cLrbu-5zBD-YXTe6NlQaypkUjBAhQoqeUoXrvHdQmd7Ve-sOhmBzVGW-VZmjKnNWFSD1ByrqIRjp2vBm3fyP3p_QGgB-uzTFSmidfAEVAHhc |
| CODEN | ITCTEM |
| CitedBy_id | crossref_primary_10_1109_TIP_2022_3203213 crossref_primary_10_1007_s11042_022_12151_4 crossref_primary_10_1109_TGRS_2022_3202865 crossref_primary_10_1007_s00371_023_03226_w crossref_primary_10_1049_ipr2_12371 crossref_primary_10_1145_3596445 crossref_primary_10_1109_TCSVT_2023_3294521 crossref_primary_10_3390_app12136475 crossref_primary_10_1016_j_inffus_2023_102192 crossref_primary_10_1109_TIP_2021_3055617 crossref_primary_10_32604_cmc_2024_049360 crossref_primary_10_1007_s42979_024_03293_3 crossref_primary_10_1109_TIP_2022_3183436 crossref_primary_10_1109_TGRS_2022_3179637 crossref_primary_10_1007_s11042_021_11212_4 crossref_primary_10_1016_j_imavis_2024_105235 crossref_primary_10_1109_TCSVT_2024_3456480 crossref_primary_10_1109_TGRS_2022_3203481 crossref_primary_10_1109_TGRS_2022_3177216 crossref_primary_10_3390_app13116799 crossref_primary_10_1109_TMM_2024_3394975 crossref_primary_10_1109_TGRS_2023_3278529 crossref_primary_10_1038_s41598_024_54547_2 crossref_primary_10_1109_TGRS_2024_3370633 crossref_primary_10_1109_LGRS_2023_3246633 crossref_primary_10_1109_TCSVT_2024_3409421 crossref_primary_10_1109_TGRS_2022_3198842 crossref_primary_10_1109_TGRS_2024_3375922 crossref_primary_10_1007_s11042_021_11470_2 crossref_primary_10_1109_JBHI_2021_3082541 crossref_primary_10_3390_app12157384 crossref_primary_10_1109_LGRS_2022_3178168 crossref_primary_10_1007_s12145_023_01031_6 crossref_primary_10_1109_TCSVT_2021_3089480 crossref_primary_10_3390_rs13214418 crossref_primary_10_1109_TNSRE_2022_3173724 crossref_primary_10_1109_TGRS_2021_3127536 crossref_primary_10_1109_TIM_2023_3344142 crossref_primary_10_3390_s22155906 crossref_primary_10_1109_TCSVT_2021_3078559 crossref_primary_10_1109_JSTARS_2021_3136599 crossref_primary_10_3390_electronics13224372 crossref_primary_10_3390_rs15112832 crossref_primary_10_1109_TCSVT_2022_3211839 crossref_primary_10_1109_TCSVT_2022_3220412 crossref_primary_10_1109_TIM_2023_3271762 crossref_primary_10_1109_TCSVT_2024_3399821 crossref_primary_10_1109_TCSVT_2022_3190916 crossref_primary_10_1109_TMM_2023_3260620 crossref_primary_10_1109_JSTARS_2021_3132856 crossref_primary_10_1109_TCSVT_2023_3312979 crossref_primary_10_3390_electronics13163199 crossref_primary_10_1109_TCYB_2022_3191121 crossref_primary_10_1080_2150704X_2022_2132122 crossref_primary_10_1109_JSTARS_2023_3294623 crossref_primary_10_1109_TII_2022_3210589 crossref_primary_10_1109_TCSVT_2022_3148257 crossref_primary_10_1109_JSTARS_2025_3542766 crossref_primary_10_1109_LGRS_2021_3112603 crossref_primary_10_1109_LSP_2024_3521714 crossref_primary_10_1109_TCSVT_2023_3241172 crossref_primary_10_1109_TCSVT_2024_3439369 crossref_primary_10_1109_LSP_2021_3086692 crossref_primary_10_1109_TCSVT_2023_3268178 crossref_primary_10_1109_JSTARS_2022_3198137 crossref_primary_10_1109_TGRS_2022_3189633 crossref_primary_10_1109_TCSVT_2022_3161103 crossref_primary_10_3390_app12146962 crossref_primary_10_1109_TCSVT_2024_3388461 crossref_primary_10_1109_TCSVT_2021_3095250 crossref_primary_10_1109_TCSVT_2022_3218284 crossref_primary_10_3390_make5010008 crossref_primary_10_1109_TCYB_2024_3475034 crossref_primary_10_1109_JSTARS_2024_3374813 crossref_primary_10_1109_TCSVT_2022_3213515 crossref_primary_10_1109_TCSII_2023_3259689 crossref_primary_10_1007_s11042_022_13344_7 |
| Cites_doi | 10.1109/TSMCB.2004.831165 10.1109/TGRS.2019.2907932 10.1109/TGRS.2018.2852708 10.1109/TGRS.2016.2524557 10.1109/JPROC.2012.2197589 10.1080/01431161.2010.502155 10.1109/TPAMI.2013.57 10.1109/CVPR.2009.5206547 10.1109/TGRS.2018.2869723 10.1109/LGRS.2019.2943001 10.1016/j.patrec.2018.10.003 10.1109/TGRS.2019.2909695 10.1109/LGRS.2016.2625200 10.1109/TIP.2018.2869691 10.1109/JSTARS.2013.2240655 10.1126/science.1242072 10.1142/S0218001419550036 10.1109/TGRS.2018.2853178 10.1109/CIS.2019.00052 10.1214/12-AOS1034 10.1109/TCSVT.2018.2889514 10.1109/TCSVT.2020.2975936 10.1109/TCSVT.2020.2975566 10.1109/TGRS.2016.2517242 10.1109/WHISPERS.2018.8747108 10.1109/TGRS.2018.2868796 10.1109/TGRS.2019.2959342 10.1109/TGRS.2017.2690445 10.1609/aaai.v33i01.33014610 10.1109/IGARSS.2019.8898947 10.1109/TGRS.2017.2702061 10.2307/2346830 10.1109/TGRS.2018.2849225 10.1109/TCSVT.2019.2946723 10.1109/IGARSS.2017.8127678 10.1109/TGRS.2018.2865953 10.1109/TIP.2018.2809606 10.1109/LGRS.2017.2723763 10.1109/ICCV.2017.626 10.1109/TGRS.2009.2023666 10.1109/TGRS.2020.2968802 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
| DBID | 97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D |
| DOI | 10.1109/TCSVT.2020.3027616 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Technology Research Database |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1558-2205 |
| EndPage | 2697 |
| ExternalDocumentID | 10_1109_TCSVT_2020_3027616 9208699 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 61722112; 61922029; 61620106009; U1636214 funderid: 10.13039/501100001809 – fundername: Natural Science Foundation of Tianjin grantid: 18ZXZNGX00110; 18JCJQJC45800 funderid: 10.13039/501100006606 |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT 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 EBS EJD HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TN5 VH1 AAYXX CITATION RIG 7SC 7SP 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c295t-2b728329c170da393b1479f77d4dd79da74dd8d6445a955aabc8f2965e29a89b3 |
| IEDL.DBID | RIE |
| ISSN | 1051-8215 |
| IngestDate | Sun Jun 29 12:21:14 EDT 2025 Tue Jul 01 00:41:14 EDT 2025 Thu Apr 24 22:57:33 EDT 2025 Wed Aug 27 02:26:41 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 7 |
| 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-c295t-2b728329c170da393b1479f77d4dd79da74dd8d6445a955aabc8f2965e29a89b3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0003-2351-4461 0000-0002-5741-7937 0000-0003-3171-7680 0000-0002-6616-453X 0000-0001-7542-296X |
| PQID | 2547641166 |
| PQPubID | 85433 |
| PageCount | 12 |
| ParticipantIDs | crossref_primary_10_1109_TCSVT_2020_3027616 proquest_journals_2547641166 crossref_citationtrail_10_1109_TCSVT_2020_3027616 ieee_primary_9208699 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2021-07-01 |
| PublicationDateYYYYMMDD | 2021-07-01 |
| PublicationDate_xml | – month: 07 year: 2021 text: 2021-07-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on circuits and systems for video technology |
| PublicationTitleAbbrev | TCSVT |
| PublicationYear | 2021 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref35 ref13 ref12 ref37 ref36 ref14 ref33 ref11 ref32 ref10 ref2 ref1 ref39 ref17 bezdek (ref18) 2013 ref38 ref16 ji (ref46) 2014 pan (ref31) 2017 ref24 xie (ref30) 2016 chen (ref34) 2016 ref45 ref23 ref26 ref47 ref25 ref20 ref42 ref41 ref22 ref44 ref21 ref43 ref28 rodriguez (ref15) 2014; 344 ref27 ref29 ref8 maggioni (ref19) 2019; 20 ref7 ref9 ref4 ref3 ref6 ref5 ref40 |
| References_xml | – ident: ref22 doi: 10.1109/TSMCB.2004.831165 – ident: ref11 doi: 10.1109/TGRS.2019.2907932 – ident: ref39 doi: 10.1109/TGRS.2018.2852708 – ident: ref26 doi: 10.1109/TGRS.2016.2524557 – ident: ref2 doi: 10.1109/JPROC.2012.2197589 – year: 2013 ident: ref18 publication-title: Pattern Recognition with Fuzzy Objective Function Algorithms – ident: ref20 doi: 10.1080/01431161.2010.502155 – ident: ref25 doi: 10.1109/TPAMI.2013.57 – ident: ref45 doi: 10.1109/CVPR.2009.5206547 – ident: ref24 doi: 10.1109/TGRS.2018.2869723 – ident: ref36 doi: 10.1109/LGRS.2019.2943001 – ident: ref9 doi: 10.1016/j.patrec.2018.10.003 – ident: ref7 doi: 10.1109/TGRS.2019.2909695 – start-page: 2172 year: 2016 ident: ref34 article-title: InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets publication-title: Proc Adv Neural Inf Process Syst – ident: ref27 doi: 10.1109/LGRS.2016.2625200 – ident: ref10 doi: 10.1109/TIP.2018.2869691 – ident: ref21 doi: 10.1109/JSTARS.2013.2240655 – volume: 344 start-page: 1492 year: 2014 ident: ref15 article-title: Clustering by fast search and find of density peaks publication-title: Science doi: 10.1126/science.1242072 – ident: ref43 doi: 10.1142/S0218001419550036 – ident: ref5 doi: 10.1109/TGRS.2018.2853178 – ident: ref29 doi: 10.1109/CIS.2019.00052 – ident: ref44 doi: 10.1214/12-AOS1034 – ident: ref16 doi: 10.1109/TCSVT.2018.2889514 – ident: ref8 doi: 10.1109/TCSVT.2020.2975936 – ident: ref1 doi: 10.1109/TCSVT.2020.2975566 – ident: ref38 doi: 10.1109/TGRS.2016.2517242 – ident: ref28 doi: 10.1109/WHISPERS.2018.8747108 – ident: ref40 doi: 10.1109/TGRS.2018.2868796 – ident: ref41 doi: 10.1109/TGRS.2019.2959342 – ident: ref3 doi: 10.1109/TGRS.2017.2690445 – ident: ref33 doi: 10.1609/aaai.v33i01.33014610 – volume: 20 start-page: 1 year: 2019 ident: ref19 article-title: Learning by unsupervised nonlinear diffusion publication-title: J Mach Learn Res – ident: ref35 doi: 10.1109/IGARSS.2019.8898947 – start-page: 24 year: 2017 ident: ref31 article-title: Deep subspace clustering networks publication-title: Proc Int Conf Neural Inf Process – ident: ref37 doi: 10.1109/TGRS.2017.2702061 – ident: ref17 doi: 10.2307/2346830 – ident: ref47 doi: 10.1109/TGRS.2018.2849225 – start-page: 461 year: 2014 ident: ref46 article-title: Efficient dense subspace clustering publication-title: Proc IEEE Winter Conf Appl Comput Vis – ident: ref6 doi: 10.1109/TCSVT.2019.2946723 – ident: ref42 doi: 10.1109/IGARSS.2017.8127678 – ident: ref12 doi: 10.1109/TGRS.2018.2865953 – ident: ref13 doi: 10.1109/TIP.2018.2809606 – ident: ref23 doi: 10.1109/LGRS.2017.2723763 – ident: ref32 doi: 10.1109/ICCV.2017.626 – start-page: 478 year: 2016 ident: ref30 article-title: Unsupervised deep embedding for clustering analysis publication-title: Proc Int Conf Mach Learn – ident: ref14 doi: 10.1109/TGRS.2009.2023666 – ident: ref4 doi: 10.1109/TGRS.2020.2968802 |
| SSID | ssj0014847 |
| Score | 2.605682 |
| Snippet | Hyperspectral image (HSI) clustering is a challenging task due to the complex characteristics in HSI data, such as spatial-spectral structure, high-dimension,... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 2686 |
| SubjectTerms | Affinity Algorithms Clustering Clustering algorithms Clustering methods Coders Collaboration Constraints Data mining deep learning deep subspace clustering Feature extraction Hyperspectral image clustering Hyperspectral imaging Kernel multi-scale auto-encoder self-expressiveness similarity constraint Spectra Subspaces Task analysis |
| Title | Deep Spatial-Spectral Subspace Clustering for Hyperspectral Image |
| URI | https://ieeexplore.ieee.org/document/9208699 https://www.proquest.com/docview/2547641166 |
| Volume | 31 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV09T8MwED2VTjDwVRCFgjKwQdrGTeJ4rApVQSoLLeoW2fFlobQVJAu_nrPzoQoQYkqGs2T5nLv3HN89gGvCCBGzFT0Jpq5PScSVComlaMk1TyMRpea8Y_oUTub-4yJYNOC2roVBRHv5DLvm1f7L1-skN0dlPcEIgAuxAztE3IparfqPgR9ZMTGCC54bUR6rCmT6ojcbPb_MiAoyYqjEwkKjbb6VhKyqyo9QbPPL-ACm1cyKayWv3TxT3eTzW9PG_079EPZLoOkMi51xBA1cHcPeVvvBFgzvEDeOESWmTegaJXpz7OGYWEJMGp3RMjdtFMjWIWjrTIiyFpWZxurhjSLRCczH97PRxC0lFdyEiSBzmeJGm0gkHu9rORAD5flcpJxrX2suyEH0jDSBpECKIJBSJVHKRBggEzISanAKzdV6hWfgIBKWQcGssz1PKaZSChCU_rVUgeRt8Ko1jpOy37iRvVjGlnf0RWz9Ehu_xKVf2nBTj9kU3Tb-tG6Zha4tyzVuQ6dyZVx-kB8x8WAe0jTD8Pz3URewy8x1FXsTtwPN7D3HS8IbmbqyG-0LbLnQDw |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwzV07T8MwED7xGICBV0GUZwaYUErjJnE8MFQtqOW10KJuwY4vC1CqPoTgt_BX-G-cnbRCgNgqMSWDHSW-y9332fcAOCSMEDGb0ZNg6vrkRFypkFiKllzzNBJRavY7rm_CRtu_6ASdGXif5MIgog0-w5K5tWf5-jkZma2yE8EIgAuRh1Be4usLEbTBabNO0jxi7PysVWu4eQ8BN2EiGLpMcdOMRyQeL2tZERXl-VyknGtfay7ojegaaUIFgRRBIKVKopSJMEAmZCRUhZ47C_OEMwKWZYdNzij8yLYvI4DiuRF5znFKTlmctGq3dy0in4w4MfG-0HRT_-L2bB-XH8bferTzFfgYr0UWyPJQGg1VKXn7Vibyvy7WKiznUNqpZrq_BjPYXYelLwUWC1CtI_Yc03aZfjP31mSV9mmKsZY9maBTexyZQhE01iHw7jSIlGe5p2ZU84ls7Qa0p_INmzDXfe7iFjiIhNZQMKvOnqcUUymZQAI4WqpA8iJ4Y5nGSV5R3TT2eIwtsyqL2OpBbPQgzvWgCMeTOb2snsifowtGsJORuUyLsDtWnTg3OYOYmD4P6TXDcPv3WQew0GhdX8VXzZvLHVhkJjjHxh3vwtywP8I9QldDtW-V3IH7aSvKJ4HBLSs |
| 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=Deep+Spatial-Spectral+Subspace+Clustering+for+Hyperspectral+Image&rft.jtitle=IEEE+transactions+on+circuits+and+systems+for+video+technology&rft.au=Lei%2C+Jianjun&rft.au=Li%2C+Xinyu&rft.au=Peng%2C+Bo&rft.au=Fang%2C+Leyuan&rft.date=2021-07-01&rft.pub=IEEE&rft.issn=1051-8215&rft.volume=31&rft.issue=7&rft.spage=2686&rft.epage=2697&rft_id=info:doi/10.1109%2FTCSVT.2020.3027616&rft.externalDocID=9208699 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1051-8215&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1051-8215&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1051-8215&client=summon |