CTNet: an efficient coupled transformer network for robust hyperspectral unmixing

This study introduces the coupled transformer Network (CTNet), an architecture designed to enhance the robustness and effectiveness of hyperspectral unmixing (HSU) tasks, addressing key limitations of traditional autoencoder (AE) frameworks. Traditional AEs, consisting of an encoder and a decoder, e...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	International journal of remote sensing Jg. 45; H. 17; S. 5679 - 5712
Hauptverfasser:	Meng, Fanlei, Sun, Haixin, Li, Jie, Xu, Tingfa
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	London Taylor & Francis 01.09.2024 Taylor & Francis Ltd
Schlagworte:	Abundance Artificial neural networks Coders Coupled transformer network cross-attention data collection Effectiveness Estimates image analysis Pixels Reconstruction robust hyperspectral unmixing Robustness (mathematics) spectral variability transcription loss Transformers uncertainty
ISSN:	0143-1161, 1366-5901, 1366-5901
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	This study introduces the coupled transformer Network (CTNet), an architecture designed to enhance the robustness and effectiveness of hyperspectral unmixing (HSU) tasks, addressing key limitations of traditional autoencoder (AE) frameworks. Traditional AEs, consisting of an encoder and a decoder, effectively learn and reconstruct low-dimensional abundance relationships from high-dimensional hyperspectral data but often struggle with spectral variability (SV) and spatial correlations, which can lead to uncertainty in the resulting abundance estimates. CTNet improves upon these limitations by incorporating a two-stream half-Siamese network with an additional encoder trained on pseudo-pure pixels, and further integrates a cross-attention module to leverage global information. This configuration not only guides the AE towards more accurate abundance estimates by directly addressing SV, but also enhances the network's ability to capture complex spectral information. To minimize the typical reconstruction errors associated with AEs, a transcription loss constraint is applied, which preserves essential details and material-related information often lost during pixel-level reconstruction. Experimental validation on synthetic and three widely-used datasets confirms that CTNet outperforms several state-of-the-art methods, providing a more robust and effective solution for HSU challenges.
AbstractList	This study introduces the coupled transformer Network (CTNet), an architecture designed to enhance the robustness and effectiveness of hyperspectral unmixing (HSU) tasks, addressing key limitations of traditional autoencoder (AE) frameworks. Traditional AEs, consisting of an encoder and a decoder, effectively learn and reconstruct low-dimensional abundance relationships from high-dimensional hyperspectral data but often struggle with spectral variability (SV) and spatial correlations, which can lead to uncertainty in the resulting abundance estimates. CTNet improves upon these limitations by incorporating a two-stream half-Siamese network with an additional encoder trained on pseudo-pure pixels, and further integrates a cross-attention module to leverage global information. This configuration not only guides the AE towards more accurate abundance estimates by directly addressing SV, but also enhances the network's ability to capture complex spectral information. To minimize the typical reconstruction errors associated with AEs, a transcription loss constraint is applied, which preserves essential details and material-related information often lost during pixel-level reconstruction. Experimental validation on synthetic and three widely-used datasets confirms that CTNet outperforms several state-of-the-art methods, providing a more robust and effective solution for HSU challenges.
Author	Xu, Tingfa Sun, Haixin Meng, Fanlei Li, Jie
Author_xml	– sequence: 1 givenname: Fanlei orcidid: 0000-0002-1014-3019 surname: Meng fullname: Meng, Fanlei organization: Changchun University – sequence: 2 givenname: Haixin orcidid: 0000-0002-6339-6589 surname: Sun fullname: Sun, Haixin organization: Changchun University – sequence: 3 givenname: Jie surname: Li fullname: Li, Jie organization: Changchun University – sequence: 4 givenname: Tingfa surname: Xu fullname: Xu, Tingfa email: ciom_xtf1@bit.edu.cn organization: Beijing Institute of Technology
BookMark	eNqFkE1r3DAQhkVIoZuPn1AQ9NKLN_qwZLu9tCxpEwgpgeQsZHmUKPFKriTT7L-PzCaXHNrTMMPzDjPPETr0wQNCnyhZU9KSM0JrTqmka0ZYvWa8KdP6AK0ol7ISHaGHaLUw1QJ9REcpPRJCZCOaFbrZ3F5D_oq1x2CtMw58xibM0wgDzlH7ZEPcQsQe8t8Qn3BpcQz9nDJ-2E0Q0wSmcCOe_dY9O39_gj5YPSY4fa3H6O7n-e3morr6_ety8-OqMuXAXAGjlDQwkMZK3VMxsI5ZYXTfd1ILa_teDtAOfGgbIckAvaDcshZ0x0wtNPBj9GW_d4rhzwwpq61LBsZRewhzUpwK3khZs6agn9-hj2GOvlynOOkK1lImCyX2lIkhpQhWTdFtddwpStQiWr2JVoto9Sq65L69yxmXdXbBFy9u_G_6-z7t_GJaF8njoLLejSHa4t-45ZV_rngBE_SZTg
CitedBy_id	crossref_primary_10_1109_JSTARS_2025_3593531 crossref_primary_10_3390_rs17050869
Cites_doi	10.1109/MSP.2013.2279274 10.1109/TGRS.2011.2162098 10.1109/TIP.2016.2579259 10.1109/TGRS.2005.844293 10.1109/MGRS.2021.3071158 10.1109/ICCV48922.2021.00061 10.1109/TCI.2019.2948726 10.1109/79.974727 10.1109/TGRS.2012.2191590 10.1109/TGRS.2020.3041157 10.1109/IGARSS39084.2020.9324087 10.1109/JSTARS.2014.2375342 10.1109/TGRS.2017.2753847 10.1109/ICASSP.2011.5946577 10.1109/TGRS.2013.2240001 10.1109/IGARSS39084.2020.9324546 10.1109/36.911111 10.1109/TGRS.2010.2098414 10.1109/MGRS.2020.2979764 10.1109/MGRS.2021.3064051 10.1109/TPAMI.2012.120 10.1109/LGRS.2020.3011941 10.1109/IGARSS.2019.8900297 10.1109/ICASSP.2018.8462214 10.1109/ACCESS.2018.2818280 10.1109/WHISPERS.2010.5594963 10.1109/RAST.2013.6581194 10.1109/JSTARS.2014.2320576 10.1109/TGRS.2018.2861992 10.1109/TGRS.2021.3094884 10.1109/MNET.001.1900550 10.1109/ICIP.2017.8296278 10.1109/JSTARS.2012.2194696 10.1016/j.neucom.2017.11.052 10.1109/TNNLS.2021.3082289 10.1109/TCI.2023.3321985 10.1109/MNET.011.2000168 10.1109/TSP.2015.2486746 10.1109/TGRS.2008.2002882 10.1109/ICASSP39728.2021.9414810 10.1109/TGRS.2018.2868690 10.1109/WHISPERS.2015.8075378 10.1109/TGRS.2022.3196057 10.1109/TGRS.2011.2155070 10.1109/IGARSS.2019.8898410 10.1109/IGARSS.2019.8899865 10.1109/TGRS.2019.2907567 10.1109/TGRS.2021.3064958 10.1109/MSP.2013.2279177 10.1021/acs.joc.5b00892
ContentType	Journal Article
Copyright	2024 Informa UK Limited, trading as Taylor & Francis Group 2024 2024 Informa UK Limited, trading as Taylor & Francis Group
Copyright_xml	– notice: 2024 Informa UK Limited, trading as Taylor & Francis Group 2024 – notice: 2024 Informa UK Limited, trading as Taylor & Francis Group
DBID	AAYXX CITATION 7TG 7TN 8FD F1W FR3 H8D H96 KL. KR7 L.G L7M 7S9 L.6
DOI	10.1080/01431161.2024.2371084
DatabaseName	CrossRef Meteorological & Geoastrophysical Abstracts Oceanic Abstracts Technology Research Database ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Meteorological & Geoastrophysical Abstracts - Academic Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Advanced Technologies Database with Aerospace AGRICOLA AGRICOLA - Academic
DatabaseTitle	CrossRef Aerospace Database Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Meteorological & Geoastrophysical Abstracts Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Oceanic Abstracts Technology Research Database ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Meteorological & Geoastrophysical Abstracts - Academic AGRICOLA AGRICOLA - Academic
DatabaseTitleList	Aerospace Database AGRICOLA
DeliveryMethod	fulltext_linktorsrc
Discipline	Geography
EISSN	1366-5901
EndPage	5712
ExternalDocumentID	10_1080_01431161_2024_2371084 2371084
Genre	Research Article
GrantInformation_xml	– fundername: Education Department of Jilin Province – fundername: National Natural Science Foundations of China grantid: 41730422
GroupedDBID	-~X .7F .DC .QJ 0BK 0R~ 29J 30N 4.4 5GY 5VS AAENE AAGDL AAHBH AAHIA AAJMT AALDU AAMIU AAPUL AAQRR ABCCY ABFIM ABHAV ABJNI ABLIJ ABLJU ABPAQ ABPEM ABRLO ABUFD ABXUL ABXYU ACGEJ ACGFS ACIWK ACTIO ADCVX ADGTB ADXPE AEISY AENEX AEOZL AEPSL AEXLP AEYOC AFKVX AFRVT AGDLA AGMYJ AHDZW AIJEM AIYEW AJWEG AKBVH AKOOK ALMA_UNASSIGNED_HOLDINGS ALQZU AQRUH AQTUD AVBZW AWYRJ BLEHA CCCUG CE4 CS3 DGEBU DKSSO DU5 EBS E~A E~B F5P H13 HF~ IPNFZ J.P KYCEM LJTGL M4Z P2P RIG RNANH ROSJB RTWRZ S-T SNACF TASJS TBQAZ TDBHL TEN TFL TFT TFW TN5 TNC TQWBC TTHFI TUROJ TWF UPT UT5 UU3 ZGOLN ~02 ~S~ 07I 1TA 4B5 6TJ AAYXX ABDPE ABFMO ACFTK ACTTO ADXEU AEHZU AEZBV AFBWG AFION AGBLW AGVKY AGWUF AGYFW AI. AIDBO AKHJE AKMBP ALRRR ALXIB BGSSV BWMZZ C0- C5H CAG CITATION COF CYRSC DAOYK DEXXA EJD FETWF H~9 IFELN L8C OPCYK TAJZE TAP UB6 VH1 VOH ZY4 7TG 7TN 8FD F1W FR3 H8D H96 KL. KR7 L.G L7M 7S9 L.6
ID	FETCH-LOGICAL-c371t-e21107ed07f6ab15d292f5cabb96a5ffbb6de8d3d87560deb513f28ea92c45ae3
IEDL.DBID	TFW
ISICitedReferencesCount	2
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001281673400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0143-1161 1366-5901
IngestDate	Thu Sep 04 16:25:02 EDT 2025 Wed Aug 13 09:13:15 EDT 2025 Tue Nov 18 22:31:17 EST 2025 Sat Nov 29 06:13:51 EST 2025 Mon Oct 20 23:47:49 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	17
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c371t-e21107ed07f6ab15d292f5cabb96a5ffbb6de8d3d87560deb513f28ea92c45ae3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-6339-6589 0000-0002-1014-3019
PQID	3095378126
PQPubID	2045515
PageCount	34
ParticipantIDs	informaworld_taylorfrancis_310_1080_01431161_2024_2371084 proquest_miscellaneous_3153766427 proquest_journals_3095378126 crossref_primary_10_1080_01431161_2024_2371084 crossref_citationtrail_10_1080_01431161_2024_2371084
PublicationCentury	2000
PublicationDate	2024-09-01
PublicationDateYYYYMMDD	2024-09-01
PublicationDate_xml	– month: 09 year: 2024 text: 2024-09-01 day: 01
PublicationDecade	2020
PublicationPlace	London
PublicationPlace_xml	– name: London
PublicationTitle	International journal of remote sensing
PublicationYear	2024
Publisher	Taylor & Francis Taylor & Francis Ltd
Publisher_xml	– name: Taylor & Francis – name: Taylor & Francis Ltd
References	e_1_3_3_52_1 e_1_3_3_50_1 Vaswani A. (e_1_3_3_51_1) 2017 e_1_3_3_18_1 e_1_3_3_39_1 e_1_3_3_14_1 e_1_3_3_37_1 e_1_3_3_16_1 e_1_3_3_35_1 Kingma D. (e_1_3_3_38_1) 2014 e_1_3_3_10_1 e_1_3_3_33_1 e_1_3_3_56_1 e_1_3_3_12_1 e_1_3_3_31_1 e_1_3_3_54_1 e_1_3_3_40_1 Bhatt J. S. (e_1_3_3_6_1) 2018 e_1_3_3_7_1 e_1_3_3_9_1 e_1_3_3_29_1 e_1_3_3_25_1 e_1_3_3_48_1 e_1_3_3_27_1 e_1_3_3_46_1 e_1_3_3_3_1 e_1_3_3_21_1 e_1_3_3_44_1 e_1_3_3_5_1 e_1_3_3_23_1 e_1_3_3_42_1 e_1_3_3_30_1 Dosovitskiy A. (e_1_3_3_13_1) 2020 e_1_3_3_17_1 e_1_3_3_19_1 e_1_3_3_15_1 e_1_3_3_36_1 Ba J. (e_1_3_3_4_1) 2016 e_1_3_3_34_1 e_1_3_3_55_1 e_1_3_3_11_1 e_1_3_3_32_1 e_1_3_3_53_1 e_1_3_3_41_1 e_1_3_3_8_1 e_1_3_3_28_1 e_1_3_3_24_1 e_1_3_3_49_1 e_1_3_3_26_1 e_1_3_3_47_1 e_1_3_3_2_1 e_1_3_3_20_1 e_1_3_3_45_1 e_1_3_3_22_1 e_1_3_3_43_1
References_xml	– ident: e_1_3_3_12_1 doi: 10.1109/MSP.2013.2279274 – ident: e_1_3_3_39_1 doi: 10.1109/TGRS.2011.2162098 – ident: e_1_3_3_14_1 doi: 10.1109/TIP.2016.2579259 – ident: e_1_3_3_42_1 doi: 10.1109/TGRS.2005.844293 – ident: e_1_3_3_10_1 doi: 10.1109/MGRS.2021.3071158 – ident: e_1_3_3_52_1 doi: 10.1109/ICCV48922.2021.00061 – ident: e_1_3_3_11_1 doi: 10.1109/TCI.2019.2948726 – ident: e_1_3_3_37_1 doi: 10.1109/79.974727 – ident: e_1_3_3_31_1 doi: 10.1109/TGRS.2012.2191590 – ident: e_1_3_3_47_1 doi: 10.1109/TGRS.2020.3041157 – ident: e_1_3_3_48_1 doi: 10.1109/IGARSS39084.2020.9324087 – ident: e_1_3_3_23_1 doi: 10.1109/JSTARS.2014.2375342 – ident: e_1_3_3_54_1 doi: 10.1109/TGRS.2017.2753847 – ident: e_1_3_3_3_1 doi: 10.1109/ICASSP.2011.5946577 – ident: e_1_3_3_30_1 doi: 10.1109/TGRS.2013.2240001 – ident: e_1_3_3_5_1 doi: 10.1109/IGARSS39084.2020.9324546 – ident: e_1_3_3_20_1 doi: 10.1109/36.911111 – ident: e_1_3_3_18_1 doi: 10.1109/TGRS.2010.2098414 – ident: e_1_3_3_46_1 doi: 10.1109/MGRS.2020.2979764 – ident: e_1_3_3_26_1 doi: 10.1109/MGRS.2021.3064051 – ident: e_1_3_3_2_1 doi: 10.1109/TPAMI.2012.120 – ident: e_1_3_3_19_1 doi: 10.1109/LGRS.2020.3011941 – ident: e_1_3_3_43_1 doi: 10.1109/IGARSS.2019.8900297 – ident: e_1_3_3_28_1 doi: 10.1109/ICASSP.2018.8462214 – volume-title: NIPS 2016 Deep Learning Symposium year: 2016 ident: e_1_3_3_4_1 – ident: e_1_3_3_44_1 doi: 10.1109/ACCESS.2018.2818280 – ident: e_1_3_3_7_1 doi: 10.1109/WHISPERS.2010.5594963 – ident: e_1_3_3_49_1 doi: 10.1109/RAST.2013.6581194 – ident: e_1_3_3_22_1 doi: 10.1109/JSTARS.2014.2320576 – start-page: 6980 volume-title: International Conference on Learning Representations (ICLR) year: 2014 ident: e_1_3_3_38_1 – ident: e_1_3_3_33_1 doi: 10.1109/TGRS.2018.2861992 – ident: e_1_3_3_36_1 doi: 10.1109/TGRS.2021.3094884 – start-page: 1 volume-title: 9th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS) year: 2018 ident: e_1_3_3_6_1 – ident: e_1_3_3_55_1 doi: 10.1109/MNET.001.1900550 – ident: e_1_3_3_27_1 doi: 10.1109/ICIP.2017.8296278 – ident: e_1_3_3_8_1 doi: 10.1109/JSTARS.2012.2194696 – ident: e_1_3_3_41_1 doi: 10.1016/j.neucom.2017.11.052 – ident: e_1_3_3_25_1 doi: 10.1109/TNNLS.2021.3082289 – ident: e_1_3_3_9_1 doi: 10.1109/TCI.2023.3321985 – ident: e_1_3_3_40_1 doi: 10.1109/MNET.011.2000168 – ident: e_1_3_3_50_1 doi: 10.1109/TSP.2015.2486746 – ident: e_1_3_3_32_1 doi: 10.1109/TGRS.2008.2002882 – ident: e_1_3_3_35_1 doi: 10.1109/ICASSP39728.2021.9414810 – ident: e_1_3_3_45_1 doi: 10.1109/TGRS.2018.2868690 – ident: e_1_3_3_17_1 doi: 10.1109/WHISPERS.2015.8075378 – ident: e_1_3_3_16_1 doi: 10.1109/TGRS.2022.3196057 – ident: e_1_3_3_21_1 doi: 10.1109/TGRS.2011.2155070 – ident: e_1_3_3_34_1 doi: 10.1109/IGARSS.2019.8898410 – volume-title: International Conference on Learning Representations year: 2020 ident: e_1_3_3_13_1 – ident: e_1_3_3_24_1 doi: 10.1109/IGARSS.2019.8899865 – ident: e_1_3_3_53_1 doi: 10.1109/TGRS.2019.2907567 – start-page: 6000 volume-title: International Conference on Neural Information Processing Systems year: 2017 ident: e_1_3_3_51_1 – ident: e_1_3_3_15_1 doi: 10.1109/TGRS.2021.3064958 – ident: e_1_3_3_56_1 doi: 10.1109/MSP.2013.2279177 – ident: e_1_3_3_29_1 doi: 10.1021/acs.joc.5b00892
SSID	ssj0006757
Score	2.454857
Snippet	This study introduces the coupled transformer Network (CTNet), an architecture designed to enhance the robustness and effectiveness of hyperspectral unmixing...
SourceID	proquest crossref informaworld
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	5679
SubjectTerms	Abundance Artificial neural networks Coders Coupled transformer network cross-attention data collection Effectiveness Estimates image analysis Pixels Reconstruction robust hyperspectral unmixing Robustness (mathematics) spectral variability transcription loss Transformers uncertainty
Title	CTNet: an efficient coupled transformer network for robust hyperspectral unmixing
URI	https://www.tandfonline.com/doi/abs/10.1080/01431161.2024.2371084 https://www.proquest.com/docview/3095378126 https://www.proquest.com/docview/3153766427
Volume	45
WOSCitedRecordID	wos001281673400001&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: PRVAWR databaseName: Taylor & Francis Online Journals customDbUrl: eissn: 1366-5901 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0006757 issn: 0143-1161 databaseCode: TFW dateStart: 19800101 isFulltext: true titleUrlDefault: https://www.tandfonline.com providerName: Taylor & Francis
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1JS8NAFB6kCHpxF-vGCF5Tm5nJ5k3E4kGKQl1uYVZaqElJE9F_75tkUhSRHvQYwpsZ3izf95I330PoPFRCAkoFXkgN8xhQZI_D0vAMV1JZgSVVyxc_3UXDYfzykty7bMK5S6u0MbRphCLqs9pubi7mbUbchZWk84GpQHRHWI9QAMnYKoICs7dJfaPB8-IsBjrcXJi2Qpxg0t7h-a2Vb-j0Tbv0x1ldA9Bg8x-GvoU2HPvEV81y2UYrOttBa64Q-vhjFz1cj4a6vMQ8w7oWlwBMwjKvZlOtcNmSXF3grEkfx_CIi1xU8xKPIaRtbm4W0EeVvU7eARf30OPgZnR967mqC56E4ZSerkNCrfqRCbnwA0USYgLJhUhCHhgjRKh0rKiCSCfsKy0CnxoSa54QyQKu6T7qZHmmDxCOJDE-CQ3jPmVcypgBYPZNJGgsCVWsi1jr7VQ6SXJbGWOa-q1yqfNXav2VOn91UW9hNms0OZYZJF-nMi3rjyGmqVyS0iW2x-28p257g4lV6YuAG4VddLZ4DRvT_m3hmc4r26xVyoHwLjr8Q_dHaN0-Nlltx6hTFpU-QavyrZzMi9N6sX8CfpH5oA
linkProvider	Taylor & Francis
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1ZS8QwEB68QF-8xfWM4Gt1m6SXbyIuiuuCsB5vJScK2pXaiv57Jz0WRcQHfSxhkjA5Zr505huA_VBLhVYq8EJmucfRRfYEbg3PCq20I1jSFX3xTT8aDOK7u-RzLowLq3QY2tZEEdVd7Q63e4xuQ-IOHSedj64KwjvKDyhDKxnzSZh21ekcABv2bse3MTrEdcq0o-JEmTaL56duvtinL-yl327rygT1Fv5j8osw3zig5LjeMUswYbJlmG1qod-_r8DVyXBgiiMiMmIqfgk0S0SNyudHo0nR-rkmJ1kdQU7wk-QjWb4U5B5RbZ28meMYZfb08IamcRWue6fDkzOvKbzgKZxO4ZkKFRrdjWwopB9omlAbKCFlEorAWilDbWLNNIKdsKuNDHxmaWxEQhUPhGFrMJWNMrMOJFLU-jS0XPiMC6VijjazayPJYkWZ5h3grbpT1bCSu-IYj6nfkpc2-kqdvtJGXx04GIs917Qcvwkkn9cyLar3EFsXL0nZL7Jb7cKnzQlHEUfUF6F7FHZgb9yMZ9P9cBGZGZWuW0eWgwgv2vjD8Lsweza87Kf988HFJsy5pjrIbQumirw02zCjXouHl3yn2vkfQXb9ww
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT9wwEB4BrSiXllfVBQpG6jWwsZ0XN0S7AoFWIG0Lt8hPLRLNrrIJov-eceKsQAhxoMfIGtsajz3fxONvAH7EWir0UlEQM8sDjhA5EGgagRVaaUewpBv64j8XyXCY3txklz6bcObTKl0MbVuiiOasdpt7qm2XEXfoKOlCRCoY3VF-QBk6yZQvwgeEzpEz7NHgen4YIx5uX0w7Jk6U6R7xvNbNM_f0jLz0xWHdeKDBl_8w91X47OEnOW7tZQ0WTLEOn3wl9PG_Dbg6GQ1NdUREQUzDLoFOiahJPb0zmlQdyjUlKdr8cYKfpJzIelaRMca07dPNEseoi7-3D-gYN-H34Nfo5DTwZRcChdOpAtPEhEb3ExsLGUaaZtRGSkiZxSKyVspYm1QzjaFO3NdGRiGzNDUio4pHwrCvsFRMCvMNSKKoDWlsuQgZF0qlHD1m3yaSpYoyzXvAO23nynOSu9IYd3nYUZd6feVOX7nXVw8O5mLTlpTjLYHs6VLmVfM3xLalS3L2huxOt-65398o4mj6EgRHcQ_25824M911iyjMpHbdOqocjO-SrXcMvwfLlz8H-cXZ8HwbVlxLm-G2A0tVWZvv8FHdV7ezcrex-0c9cPx1
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=CTNet%3A+an+efficient+coupled+transformer+network+for+robust+hyperspectral+unmixing&rft.jtitle=International+journal+of+remote+sensing&rft.au=Meng%2C+Fanlei&rft.au=Sun%2C+Haixin&rft.au=Li%2C+Jie&rft.au=Xu%2C+Tingfa&rft.date=2024-09-01&rft.issn=1366-5901&rft.volume=45&rft.issue=17+p.5679-5712&rft.spage=5679&rft.epage=5712&rft_id=info:doi/10.1080%2F01431161.2024.2371084&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0143-1161&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0143-1161&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0143-1161&client=summon