Graph-Induced Aligned Learning on Subspaces for Hyperspectral and Multispectral Data

In this article, we have great interest in investigating a common but practical issue in remote sensing (RS)-can a limited amount of one information-rich (or high-quality) data, e.g., hyperspectral (HS) image, improve the performance of a classification task using a large amount of another informati...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on geoscience and remote sensing Vol. 59; no. 5; pp. 4407 - 4418
Main Authors:	Hong, Danfeng, Kang, Jian, Yokoya, Naoto, Chanussot, Jocelyn
Format:	Journal Article
Language:	English
Published:	New York IEEE 01.05.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Institute of Electrical and Electronics Engineers
Subjects:	Cross-modality Data Engineering Sciences fusion graph learning hyperspectral (HS) Hyperspectral imaging Image classification Image quality Kernel Labels Learning Machine learning Manifolds multispectral (MS) Optimization pseudo-labels Remote sensing remote sensing (RS) semisupervised Signal and Image processing subspace learning Subspaces Task analysis Training subspace learning fusion Cross-modality multispectral (MS) semisupervised hyperspectral (HS) remote sensing (RS) graph learning pseudo-labels
ISSN:	0196-2892, 1558-0644
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	In this article, we have great interest in investigating a common but practical issue in remote sensing (RS)-can a limited amount of one information-rich (or high-quality) data, e.g., hyperspectral (HS) image, improve the performance of a classification task using a large amount of another information-poor (low-quality) data, e.g., multispectral (MS) image? This question leads to a typical cross-modality feature learning. However, classic cross-modality representation learning approaches, e.g., manifold alignment, remain limited in effectively and efficiently handling such problems that the data from high-quality modality are largely absent. For this reason, we propose a novel graph-induced aligned learning (GiAL) framework by 1) adaptively learning a unified graph (further yielding a Laplacian matrix) from the data in order to align multimodality data (MS-HS data) into a latent shared subspace; 2) simultaneously modeling two regression behaviors with respect to labels and pseudo-labels under a multitask learning paradigm; and 3) dramatically updating the pseudo-labels according to the learned graph and refeeding the latest pseudo-labels into model learning of the next round. In addition, an optimization framework based on the alternating direction method of multipliers (ADMMs) is devised to solve the proposed GiAL model. Extensive experiments are conducted on two MS-HS RS data sets, demonstrating the superiority of the proposed GiAL compared with several state-of-the-art methods.
AbstractList	In this article, we have great interest in investigating a common but practical issue in remote sensing (RS)-can a limited amount of one information-rich (or high-quality) data, e.g., hyperspectral (HS) image, improve the performance of a classification task using a large amount of another information-poor (low-quality) data, e.g., multispectral (MS) image? This question leads to a typical cross-modality feature learning. However, classic cross-modality representation learning approaches, e.g., manifold alignment, remain limited in effectively and efficiently handling such problems that the data from high-quality modality are largely absent. For this reason, we propose a novel graph-induced aligned learning (GiAL) framework by 1) adaptively learning a unified graph (further yielding a Laplacian matrix) from the data in order to align multimodality data (MS-HS data) into a latent shared subspace; 2) simultaneously modeling two regression behaviors with respect to labels and pseudo-labels under a multitask learning paradigm; and 3) dramatically updating the pseudo-labels according to the learned graph and refeeding the latest pseudo-labels into model learning of the next round. In addition, an optimization framework based on the alternating direction method of multipliers (ADMMs) is devised to solve the proposed GiAL model. Extensive experiments are conducted on two MS-HS RS data sets, demonstrating the superiority of the proposed GiAL compared with several state-of-the-art methods.
Author	Chanussot, Jocelyn Yokoya, Naoto Hong, Danfeng Kang, Jian
Author_xml	– sequence: 1 givenname: Danfeng orcidid: 0000-0002-3212-9584 surname: Hong fullname: Hong, Danfeng email: hongdanfeng1989@gmail.com organization: CNRS, Grenoble INP, GIPSA-Lab, Univ. Grenoble Alpes, Grenoble, France – sequence: 2 givenname: Jian orcidid: 0000-0001-6284-3044 surname: Kang fullname: Kang, Jian email: kangjian_1991@outlook.com organization: School of Electronic and Information Engineering, Soochow University, Suzhou, China – sequence: 3 givenname: Naoto orcidid: 0000-0002-7321-4590 surname: Yokoya fullname: Yokoya, Naoto email: naoto.yokoya@riken.jp organization: Graduate School of Frontier Sciences, The University of Tokyo, Chiba, Japan – sequence: 4 givenname: Jocelyn orcidid: 0000-0003-4817-2875 surname: Chanussot fullname: Chanussot, Jocelyn email: jocelyn@hi.is organization: INRIA, CNRS, Grenoble INP, LJK, Univ. Grenoble Alpes, Grenoble, France
BackLink	https://hal.science/hal-03429646$$DView record in HAL
BookMark	eNp9kE9L5EAQxZtFYUfdD7B4CexpDxmrOv0nOQ6uzggjgo7npqdT0ZbYyXYngt_eDCNz8ODpweO9V8XvhB2FLhBjvxHmiFBdbJb3D3MOHOYFcEQBP9gMpSxzUEIcsRlgpXJeVvwnO0npBQCFRD1jm2W0_XN-E-rRUZ0tWv8UJl2TjcGHp6wL2cO4Tb11lLKmi9nqvaeYenJDtG1mQ53dju3gD84_O9gzdtzYNtGvTz1lj9dXm8tVvr5b3lwu1rkThRpyAulA1nzrkPNKVeQECOVK3TQlNspSqUHqRhZa1wVJbYXdCl7IydOlVlScsr_73Wfbmj76VxvfTWe9WS3WZudBIaZhod5wyv7ZZ_vY_R8pDealG2OY3jNcoiwlB9RTCvcpF7uUIjWHWQSzA212oM0OtPkEPXX0l47zgx18FyYgvv22eb5veiI6XKo4CKGw-AD_GYs8
CODEN	IGRSD2
CitedBy_id	crossref_primary_10_1109_MGRS_2021_3064051 crossref_primary_10_1109_TGRS_2021_3124913 crossref_primary_10_1016_j_isprsjprs_2021_10_010 crossref_primary_10_1080_01431161_2025_2487231 crossref_primary_10_1109_JSTARS_2021_3124308 crossref_primary_10_1371_journal_pone_0316900 crossref_primary_10_1371_journal_pone_0304999 crossref_primary_10_3390_app14125061 crossref_primary_10_1109_TIP_2022_3162964 crossref_primary_10_1080_01431161_2024_2370502 crossref_primary_10_1109_TGRS_2023_3326153 crossref_primary_10_1111_phor_70014
Cites_doi	10.1109/JSTARS.2017.2771482 10.1109/TGRS.2019.2957251 10.1109/TKDE.2009.191 10.1109/TGRS.2014.2317499 10.1109/TGRS.2013.2246837 10.1109/LGRS.2019.2919755 10.1109/TGRS.2020.2964617 10.1007/s11554-017-0742-z 10.1109/JSTARS.2017.2682189 10.1109/TGRS.2019.2936486 10.1109/CVPR.2017.421 10.1109/JSTSP.2018.2877497 10.1016/j.isprsjprs.2020.06.014 10.1016/j.isprsjprs.2019.09.008 10.1016/j.isprsjprs.2016.07.004 10.1109/TGRS.2019.2953069 10.1109/CVPR.2017.608 10.1038/nature14539 10.1109/TGRS.2019.2897139 10.1109/TGRS.2020.3000684 10.1109/TGRS.2018.2890705 10.1109/TIP.2018.2878958 10.1109/MGRS.2015.2440094 10.1109/MGRS.2016.2637824 10.1109/MC.2016.113 10.1109/TKDE.2013.111 10.1145/2647868.2654902 10.1016/j.isprsjprs.2018.10.006 10.1109/TGRS.2019.2899129 10.1162/NECO_a_00801 10.1109/CVPR.2015.7299149 10.1109/TGRS.2019.2907310 10.1109/TNN.2010.2091281 10.1109/TPAMI.2016.2640292 10.1109/LGRS.2017.2755061 10.1109/ICCV.2013.261 10.1145/1961189.1961199 10.1016/j.isprsjprs.2018.02.006 10.1109/MGRS.2020.2979764 10.1109/TNNLS.2020.2979546
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 Attribution
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 – notice: Attribution
DBID	97E RIA RIE AAYXX CITATION 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M 1XC VOOES
DOI	10.1109/TGRS.2020.3021140
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library (IEL) CrossRef Water Resources Abstracts Technology Research Database Environmental Sciences and Pollution Management ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Advanced Technologies Database with Aerospace Hyper Article en Ligne (HAL) Hyper Article en Ligne (HAL) (Open Access)
DatabaseTitle	CrossRef Aerospace Database Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Technology Research Database ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Water Resources Abstracts Environmental Sciences and Pollution Management
DatabaseTitleList	Aerospace Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Physics
EISSN	1558-0644
EndPage	4418
ExternalDocumentID	oai:HAL:hal-03429646v1 10_1109_TGRS_2020_3021140 9204461
Genre	orig-research
GrantInformation_xml	– fundername: AXA Research Fund funderid: 10.13039/501100001961 – fundername: Japan Society for the Promotion of Science (JSPS) grantid: KAKENHI 18K18067 funderid: 10.13039/501100001691
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AETIX AFRAH AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IBMZZ ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TN5 VH1 Y6R AAYXX CITATION 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M 1XC VOOES
ID	FETCH-LOGICAL-c436t-e05c05d2bc122969ec4046c87ff81f6ae87057f5377d3e57a4ab423557f7876e3
IEDL.DBID	RIE
ISICitedReferencesCount	12
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000642096400055&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0196-2892
IngestDate	Tue Oct 14 20:52:14 EDT 2025 Mon Jun 30 10:14:52 EDT 2025 Sat Nov 29 02:50:08 EST 2025 Tue Nov 18 22:22:13 EST 2025 Wed Aug 27 02:30:54 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	5
Keywords	subspace learning fusion Cross-modality multispectral (MS) semisupervised hyperspectral (HS) remote sensing (RS) graph learning pseudo-labels
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 Attribution: http://creativecommons.org/licenses/by
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c436t-e05c05d2bc122969ec4046c87ff81f6ae87057f5377d3e57a4ab423557f7876e3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-6284-3044 0000-0002-3212-9584 0000-0002-7321-4590 0000-0003-4817-2875
OpenAccessLink	https://hal.science/hal-03429646
PQID	2515852017
PQPubID	85465
PageCount	12
ParticipantIDs	proquest_journals_2515852017 hal_primary_oai_HAL_hal_03429646v1 ieee_primary_9204461 crossref_primary_10_1109_TGRS_2020_3021140 crossref_citationtrail_10_1109_TGRS_2020_3021140
PublicationCentury	2000
PublicationDate	2021-05-01
PublicationDateYYYYMMDD	2021-05-01
PublicationDate_xml	– month: 05 year: 2021 text: 2021-05-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on geoscience and remote sensing
PublicationTitleAbbrev	TGRS
PublicationYear	2021
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Institute of Electrical and Electronics Engineers
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) – name: Institute of Electrical and Electronics Engineers
References	ref13 ref12 ref15 ref14 ref10 ref17 ref16 ref18 yao (ref19) 2020 ref46 ref45 ref47 ref42 ref44 ref43 ref49 yokoya (ref48) 2016 ref7 ref9 ref4 ref3 ref6 ref5 hong (ref23) 2020 ref40 ref35 ref37 ref30 wang (ref8) 2011 ref33 hong (ref11) 2020 ref2 ref1 ref39 ref38 chang (ref36) 2017 ref24 ref26 ref25 ref20 ref22 ref21 ngiam (ref32) 2011 ref28 ref27 lecun (ref31) 2015; 521 ji (ref41) 2009 ref29 zhu (ref34) 2003
References_xml	– ident: ref6 doi: 10.1109/JSTARS.2017.2771482 – ident: ref14 doi: 10.1109/TGRS.2019.2957251 – ident: ref4 doi: 10.1109/TKDE.2009.191 – ident: ref28 doi: 10.1109/TGRS.2014.2317499 – ident: ref24 doi: 10.1109/TGRS.2013.2246837 – ident: ref7 doi: 10.1109/LGRS.2019.2919755 – ident: ref40 doi: 10.1109/TGRS.2020.2964617 – ident: ref25 doi: 10.1007/s11554-017-0742-z – ident: ref10 doi: 10.1109/JSTARS.2017.2682189 – ident: ref16 doi: 10.1109/TGRS.2019.2936486 – start-page: 1763 year: 2017 ident: ref36 article-title: Cross-domain kernel induction for transfer learning publication-title: Proc AAAI – ident: ref29 doi: 10.1109/CVPR.2017.421 – ident: ref38 doi: 10.1109/JSTSP.2018.2877497 – ident: ref3 doi: 10.1016/j.isprsjprs.2020.06.014 – ident: ref43 doi: 10.1016/j.isprsjprs.2019.09.008 – start-page: 1077 year: 2009 ident: ref41 article-title: Linear dimensionality reduction for multi-label classification publication-title: Proc IJCAI – ident: ref21 doi: 10.1016/j.isprsjprs.2016.07.004 – ident: ref39 doi: 10.1109/TGRS.2019.2953069 – ident: ref42 doi: 10.1109/CVPR.2017.608 – volume: 521 start-page: 436 year: 2015 ident: ref31 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – ident: ref26 doi: 10.1109/TGRS.2019.2897139 – ident: ref18 doi: 10.1109/TGRS.2020.3000684 – start-page: 912 year: 2003 ident: ref34 article-title: Semi-supervised learning using Gaussian fields and harmonic functions publication-title: Proc ICML – start-page: 689 year: 2011 ident: ref32 article-title: Multimodal deep learning publication-title: Proc ICML – ident: ref5 doi: 10.1109/TGRS.2018.2890705 – ident: ref1 doi: 10.1109/TIP.2018.2878958 – ident: ref46 doi: 10.1109/MGRS.2015.2440094 – ident: ref47 doi: 10.1109/MGRS.2016.2637824 – year: 2020 ident: ref23 article-title: More diverse means better: Multimodal deep learning meets remote-sensing imagery classification publication-title: IEEE Trans Geosci Remote Sens – ident: ref15 doi: 10.1109/MC.2016.113 – ident: ref35 doi: 10.1109/TKDE.2013.111 – start-page: 1541 year: 2011 ident: ref8 article-title: Heterogeneous domain adaptation using manifold alignment publication-title: Proc IJCAI – year: 2020 ident: ref11 article-title: Graph convolutional networks for hyperspectral image classification publication-title: IEEE Trans Geosci Remote Sens – ident: ref20 doi: 10.1145/2647868.2654902 – ident: ref37 doi: 10.1016/j.isprsjprs.2018.10.006 – ident: ref12 doi: 10.1109/TGRS.2019.2899129 – ident: ref33 doi: 10.1162/NECO_a_00801 – ident: ref44 doi: 10.1109/CVPR.2015.7299149 – ident: ref17 doi: 10.1109/TGRS.2019.2907310 – ident: ref9 doi: 10.1109/TNN.2010.2091281 – ident: ref30 doi: 10.1109/TPAMI.2016.2640292 – ident: ref2 doi: 10.1109/LGRS.2017.2755061 – ident: ref27 doi: 10.1109/ICCV.2013.261 – ident: ref49 doi: 10.1145/1961189.1961199 – ident: ref22 doi: 10.1016/j.isprsjprs.2018.02.006 – year: 2020 ident: ref19 article-title: Cross-attention in coupled unmixing nets for unsupervised hyperspectral super-resolution publication-title: arXiv 2007 05230 – year: 2016 ident: ref48 article-title: Airborne hyperspectral data over Chikusei – ident: ref13 doi: 10.1109/MGRS.2020.2979764 – ident: ref45 doi: 10.1109/TNNLS.2020.2979546
SSID	ssj0014517
Score	2.4251251
Snippet	In this article, we have great interest in investigating a common but practical issue in remote sensing (RS)-can a limited amount of one information-rich (or... In this article, we have great interest in investigating a common but practical issue in remote sensing (RS)—can a limited amount of one information-rich (or...
SourceID	hal proquest crossref ieee
SourceType	Open Access Repository Aggregation Database Enrichment Source Index Database Publisher
StartPage	4407
SubjectTerms	Cross-modality Data Engineering Sciences fusion graph learning hyperspectral (HS) Hyperspectral imaging Image classification Image quality Kernel Labels Learning Machine learning Manifolds multispectral (MS) Optimization pseudo-labels Remote sensing remote sensing (RS) semisupervised Signal and Image processing subspace learning Subspaces Task analysis Training
Title	Graph-Induced Aligned Learning on Subspaces for Hyperspectral and Multispectral Data
URI	https://ieeexplore.ieee.org/document/9204461 https://www.proquest.com/docview/2515852017 https://hal.science/hal-03429646
Volume	59
WOSCitedRecordID	wos000642096400055&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: 1558-0644 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014517 issn: 0196-2892 databaseCode: RIE dateStart: 19800101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB5UFPTgW1xfBPEkRtu0Sdrj4msPIqIreCsxSVdBurKu_n5nsrEIiuCthISGTpN8X2bmG4ADpxzyBpNxi_CX57IU3CRKcFtkLkucwjO5CMUm9PV18fBQ3kzBUZsL470PwWf-mB6DL98N7TtdlZ2UgtyPyHWmtdaTXK3WY5DLNKZGK44kQkQPZpqUJ_3L2ztkggIJKp5oKd1zfDuDpp8oAjKUVvmxH4dD5mLpf9NbhsUIJll3Yv0VmPLNKix8kxhchbkQ4mnf1qB_SdrUnGp1WO9Y9-V5gFssiwKrAzZsGO0irxSjxRDKsh5S1Ekm5ghfYhrHQrZu23JmxmYd7i_O-6c9HmsqcJtnasx9Im0inXi0qRClKr3NkSHbQtd1kdbKeFy_Utcy09plXmqTm0dEXBLbcGkrn23ATDNs_CYwndbWKIeAl1TQLCFJh2ADSa-j-upFB5Kvr1zZKDhOdS9eqkA8krIiw1RkmCoapgOH7ZDXidrGX5330XRtP9LJ7nWvKmojXcNS5eoj7cAaGartFW3UgZ0vS1dx0b5VgmYtERHprd9HbcO8oJCWEO-4AzPj0bvfhVn7gd9-tBf-x09Zv9j5
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fSxwxEB6stWgf_NnSq7YG8Uka3c1usruPh1ZPPA_RE3wLMclaQfbkPP37ncnFRVAKvi0hYcN-m2S-zMw3ANtOOeQNJuMWzV-ey0pwkyjBbZm5LHEKz-QyFJsoBoPy6qo6m4E_bS6M9z4En_ldegy-fDeyj3RVtlcJcj8i1_ks81yk02yt1meQyzQmRyuONEJEH2aaVHvDo_ML5IICKSqeaSnddLw6hT79oxjIUFzlzY4cjpnDpY9NcBkWoznJulP8V2DGN6vw9ZXI4Cp8CUGe9mENhkekTs2pWof1jnXvbm9wk2VRYvWGjRpG-8g9RWkxNGZZD0nqNBdzjC8xjWMhX7dtOTAT8w0uD_8O93s8VlXgNs_UhPtE2kQ6cW1TISpVeZsjR7ZlUddlWivjcQXLopZZUbjMy8Lk5hptLoltuLiVz77DbDNq_A9gRVpboxyavKSDZsmWdGhuIO11VGG97EDy8pW1jZLjVPniTgfqkVSagNEEjI7AdGCnHXI_1dv4X-cthK7tR0rZvW5fUxspG1YqV09pB9YIqLZXxKgDGy9I67hsH7SgWUu0iYqf74_ahPne8LSv-8eDk3VYEBTgEqIfN2B2Mn70v2DOPiEO49_h33wGzTLcQA
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=Graph-Induced+Aligned+Learning+on+Subspaces+for+Hyperspectral+and+Multispectral+Data&rft.jtitle=IEEE+transactions+on+geoscience+and+remote+sensing&rft.au=Hong%2C+Danfeng&rft.au=Yokoya%2C+Naoto&rft.au=Chanussot%2C+Jocelyn&rft.au=Kang%2C+Jian&rft.date=2021-05-01&rft.pub=Institute+of+Electrical+and+Electronics+Engineers&rft.issn=0196-2892&rft.volume=59&rft.issue=5&rft.spage=4407&rft.epage=4418&rft_id=info:doi/10.1109%2FTGRS.2020.3021140&rft.externalDBID=HAS_PDF_LINK&rft.externalDocID=oai%3AHAL%3Ahal-03429646v1
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0196-2892&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0196-2892&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0196-2892&client=summon