Commonality Feature Representation Learning for Unsupervised Multimodal Change Detection

The main challenge of multimodal change detection (MCD) is that multimodal bitemporal images (MBIs) cannot be compared directly to identify changes. To overcome this problem, this paper proposes a novel commonality feature representation learning (CFRL) and constructs a CFRL-based unsupervised MCD f...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on image processing Ročník 34; s. 1219 - 1233
Hlavní autori: Liu, Tongfei, Zhang, Mingyang, Gong, Maoguo, Zhang, Qingfu, Jiang, Fenlong, Zheng, Hanhong, Lu, Di
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
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 The main challenge of multimodal change detection (MCD) is that multimodal bitemporal images (MBIs) cannot be compared directly to identify changes. To overcome this problem, this paper proposes a novel commonality feature representation learning (CFRL) and constructs a CFRL-based unsupervised MCD framework. The CFRL is composed of a Siamese-based encoder and two decoders. First, the Siamese-based encoder can map original MBIs in the same feature space for extracting the representative features of each modality. Then, the two decoders are used to reconstruct the original MBIs by regressing themselves, respectively. Meanwhile, we swap the decoders to reconstruct the pseudo-MBIs to conduct modality alignment. Subsequently, all reconstructed images are input to the Siamese-based encoder again to map them in a same feature space, by which representative features are obtained. On this basis, latent commonality features between MBIs can be extracted by minimizing the distance between these representative features. These latent commonality features are comparable and can be used to identify changes. Notably, the proposed CFRL can be performed simultaneously in two modalities corresponding to MBIs. Therefore, two change magnitude images (CMIs) can be generated simultaneously by measuring the difference between the commonality features of MBIs. Finally, a simple threshold algorithm or a clustering algorithm can be employed to divide CMIs into binary change maps. Extensive experiments on six publicly available MCD datasets show that the proposed CFRL-based framework can achieve superior performance compared with other state-of-the-art approaches.
AbstractList The main challenge of multimodal change detection (MCD) is that multimodal bitemporal images (MBIs) cannot be compared directly to identify changes. To overcome this problem, this paper proposes a novel commonality feature representation learning (CFRL) and constructs a CFRL-based unsupervised MCD framework. The CFRL is composed of a Siamese-based encoder and two decoders. First, the Siamese-based encoder can map original MBIs in the same feature space for extracting the representative features of each modality. Then, the two decoders are used to reconstruct the original MBIs by regressing themselves, respectively. Meanwhile, we swap the decoders to reconstruct the pseudo-MBIs to conduct modality alignment. Subsequently, all reconstructed images are input to the Siamese-based encoder again to map them in a same feature space, by which representative features are obtained. On this basis, latent commonality features between MBIs can be extracted by minimizing the distance between these representative features. These latent commonality features are comparable and can be used to identify changes. Notably, the proposed CFRL can be performed simultaneously in two modalities corresponding to MBIs. Therefore, two change magnitude images (CMIs) can be generated simultaneously by measuring the difference between the commonality features of MBIs. Finally, a simple threshold algorithm or a clustering algorithm can be employed to divide CMIs into binary change maps. Extensive experiments on six publicly available MCD datasets show that the proposed CFRL-based framework can achieve superior performance compared with other state-of-the-art approaches.The main challenge of multimodal change detection (MCD) is that multimodal bitemporal images (MBIs) cannot be compared directly to identify changes. To overcome this problem, this paper proposes a novel commonality feature representation learning (CFRL) and constructs a CFRL-based unsupervised MCD framework. The CFRL is composed of a Siamese-based encoder and two decoders. First, the Siamese-based encoder can map original MBIs in the same feature space for extracting the representative features of each modality. Then, the two decoders are used to reconstruct the original MBIs by regressing themselves, respectively. Meanwhile, we swap the decoders to reconstruct the pseudo-MBIs to conduct modality alignment. Subsequently, all reconstructed images are input to the Siamese-based encoder again to map them in a same feature space, by which representative features are obtained. On this basis, latent commonality features between MBIs can be extracted by minimizing the distance between these representative features. These latent commonality features are comparable and can be used to identify changes. Notably, the proposed CFRL can be performed simultaneously in two modalities corresponding to MBIs. Therefore, two change magnitude images (CMIs) can be generated simultaneously by measuring the difference between the commonality features of MBIs. Finally, a simple threshold algorithm or a clustering algorithm can be employed to divide CMIs into binary change maps. Extensive experiments on six publicly available MCD datasets show that the proposed CFRL-based framework can achieve superior performance compared with other state-of-the-art approaches.
The main challenge of multimodal change detection (MCD) is that multimodal bitemporal images (MBIs) cannot be compared directly to identify changes. To overcome this problem, this paper proposes a novel commonality feature representation learning (CFRL) and constructs a CFRL-based unsupervised MCD framework. The CFRL is composed of a Siamese-based encoder and two decoders. First, the Siamese-based encoder can map original MBIs in the same feature space for extracting the representative features of each modality. Then, the two decoders are used to reconstruct the original MBIs by regressing themselves, respectively. Meanwhile, we swap the decoders to reconstruct the pseudo-MBIs to conduct modality alignment. Subsequently, all reconstructed images are input to the Siamese-based encoder again to map them in a same feature space, by which representative features are obtained. On this basis, latent commonality features between MBIs can be extracted by minimizing the distance between these representative features. These latent commonality features are comparable and can be used to identify changes. Notably, the proposed CFRL can be performed simultaneously in two modalities corresponding to MBIs. Therefore, two change magnitude images (CMIs) can be generated simultaneously by measuring the difference between the commonality features of MBIs. Finally, a simple threshold algorithm or a clustering algorithm can be employed to divide CMIs into binary change maps. Extensive experiments on six publicly available MCD datasets show that the proposed CFRL-based framework can achieve superior performance compared with other state-of-the-art approaches.
Author Lu, Di
Zheng, Hanhong
Zhang, Qingfu
Gong, Maoguo
Zhang, Mingyang
Liu, Tongfei
Jiang, Fenlong
Author_xml – sequence: 1
  givenname: Tongfei
  orcidid: 0000-0003-1394-4724
  surname: Liu
  fullname: Liu, Tongfei
  email: liutongfei_home@hotmail.com
  organization: Shaanxi Joint Laboratory of Artificial Intelligence, Shaanxi University of Science and Technology, Xi'an, China
– sequence: 2
  givenname: Mingyang
  orcidid: 0000-0002-9768-516X
  surname: Zhang
  fullname: Zhang, Mingyang
  email: OMEGAZhangMY@gmail.com
  organization: Key Laboratory of Collaborative Intelligent Systems, Ministry of Education, Xidian University, Xi'an, China
– sequence: 3
  givenname: Maoguo
  orcidid: 0000-0002-0415-8556
  surname: Gong
  fullname: Gong, Maoguo
  email: gong@ieee.org
  organization: Key Laboratory of Collaborative Intelligent Systems, Ministry of Education, Xidian University, Xi'an, China
– sequence: 4
  givenname: Qingfu
  orcidid: 0000-0003-0786-0671
  surname: Zhang
  fullname: Zhang, Qingfu
  email: qingfu.zhang@cityu.edu.hk
  organization: Department of Computer Science, City University of Hong Kong, Hong Kong, China
– sequence: 5
  givenname: Fenlong
  orcidid: 0000-0002-3714-0600
  surname: Jiang
  fullname: Jiang, Fenlong
  email: jiangfenlong@outlook.com
  organization: Key Laboratory of Collaborative Intelligent Systems, Ministry of Education, Xidian University, Xi'an, China
– sequence: 6
  givenname: Hanhong
  orcidid: 0000-0001-7693-051X
  surname: Zheng
  fullname: Zheng, Hanhong
  email: Hanhong_Zheng@163.com
  organization: Key Laboratory of Collaborative Intelligent Systems, Ministry of Education, Xidian University, Xi'an, China
– sequence: 7
  givenname: Di
  orcidid: 0000-0002-1417-9553
  surname: Lu
  fullname: Lu, Di
  email: Di_Lu@stu.xidian.edu.cn
  organization: Key Laboratory of Collaborative Intelligent Systems, Ministry of Education, Xidian University, Xi'an, China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/40031527$$D View this record in MEDLINE/PubMed
BookMark eNp9kU1rGzEQhkVIaeK09xxCWOgll3U0-vBKx-I2rcGlISTQ26LdnXUUdiVH0hb877OOnVB86Gnm8DwzzLwTcuy8Q0LOgU4BqL6-X9xOGWVyyiXXYgZH5BS0gJxSwY7HnsoiL0DoEzKJ8YlSEBJmH8mJoJSDZMUp-TP3fe-d6WzaZDdo0hAwu8N1wIgumWS9y5ZogrNulbU-ZA8uDmsMf23EJvs1dMn2vjFdNn80boXZN0xYb61P5ENruoif9_WMPNx8v5__zJe_fyzmX5d5zYVKuZRMsxZZ01aKMzCqUlLPjG5qrjUyUVeMKWgqqZuiagGLhkrdaiU5Y21tKn5GrnZz18E_DxhT2dtYY9cZh36IJYeCCyoUhRH9coA--SGMt79SIJRWvBipyz01VD025TrY3oRN-fazEaA7oA4-xoDtOwK03MZSjrGU21jKfSyjMjtQart7bgrGdv8TL3aiRcR_9igNnGn-AgeLmYg
CODEN IIPRE4
CitedBy_id crossref_primary_10_1109_TGRS_2025_3583166
crossref_primary_10_1109_TGRS_2025_3584234
crossref_primary_10_3390_s25123740
crossref_primary_10_1109_TGRS_2025_3570653
crossref_primary_10_3390_rs17122011
crossref_primary_10_1109_TGRS_2025_3566399
crossref_primary_10_1109_TGRS_2025_3576200
crossref_primary_10_1109_TGRS_2025_3584073
Cites_doi 10.1109/TNNLS.2016.2636227
10.1109/TNNLS.2022.3172183
10.1109/TGRS.2017.2739800
10.1109/TGRS.2021.3061686
10.1109/TGRS.2021.3056196
10.1109/TIP.2017.2784560
10.1109/TNNLS.2021.3056238
10.1016/j.cviu.2019.102817
10.1109/TSMC.1979.4310076
10.1109/TCYB.2019.2950560
10.1145/3439950
10.1109/TIP.2014.2387013
10.1109/LGRS.2013.2250908
10.1109/TGRS.2019.2930348
10.1016/j.isprsjprs.2021.07.007
10.1109/TIP.2010.2040763
10.1109/LGRS.2020.3037930
10.1007/978-3-319-11469-9_10
10.1109/TGRS.2021.3097717
10.1016/j.isprsjprs.2022.01.004
10.1109/CVPRW56347.2022.00141
10.1109/TIP.2012.2219547
10.1109/TGRS.2020.3013673
10.3390/rs12172683
10.1109/LGRS.2018.2868704
10.1109/TGRS.2022.3229027
10.1109/LGRS.2022.3173300
10.1109/TGRS.2021.3130940
10.1109/TGRS.2020.2986239
10.1109/TGRS.2020.3000296
10.1109/TIP.2021.3093766
10.1109/TGRS.2022.3168126
10.1109/TGRS.2021.3139077
10.1109/JSTARS.2020.2964409
10.1109/TGRS.2021.3110998
10.3390/rs11202377
10.1016/j.isprsjprs.2021.05.001
10.1109/TIP.2011.2170702
10.1109/TNNLS.2022.3184414
10.1109/TNNLS.2015.2435783
10.1016/j.engappai.2023.105835
10.3390/rs13183750
10.1109/MGRS.2021.3088865
10.1080/17538947.2022.2092658
10.1109/TIP.2019.2933747
10.1109/TGRS.2008.916476
10.1080/01431161.2018.1547934
10.1109/JPROC.2022.3219376
10.1109/LGRS.2018.2843385
10.1016/j.patcog.2020.107598
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID 97E
RIA
RIE
AAYXX
CITATION
NPM
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
DOI 10.1109/TIP.2025.3539461
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
PubMed
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
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
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
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
Technology Research Database

PubMed
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
EISSN 1941-0042
EndPage 1233
ExternalDocumentID 40031527
10_1109_TIP_2025_3539461
10891329
Genre orig-research
Journal Article
GrantInformation_xml – fundername: Key Research and Development Projects of Shaanxi Province; Key Research and Development Program of Shaanxi
  grantid: 2024GX-YBXM-121
  funderid: 10.13039/501100015401
– fundername: National Natural Science Foundation of China
  grantid: 62036006; 62376205; 62271296; 61861024
  funderid: 10.13039/501100001809
– fundername: Shaanxi Provincial Education Department
  grantid: 23JP022; 23JP014
  funderid: 10.13039/501100010228
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
AAYOK
NPM
RIG
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
ID FETCH-LOGICAL-c348t-55292fe2dfb8321a8b8596a9dc399e24cb2281db59d7bf1e7d059f985322fcab3
IEDL.DBID RIE
ISICitedReferencesCount 14
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001433275600003&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 Sat Sep 27 17:19:16 EDT 2025
Mon Jun 30 12:21:26 EDT 2025
Sun Apr 06 01:21:48 EDT 2025
Tue Nov 18 22:05:35 EST 2025
Sat Nov 29 08:17:57 EST 2025
Wed Aug 27 01:49:26 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-c348t-55292fe2dfb8321a8b8596a9dc399e24cb2281db59d7bf1e7d059f985322fcab3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0002-9768-516X
0000-0002-0415-8556
0000-0003-1394-4724
0000-0003-0786-0671
0000-0002-3714-0600
0000-0001-7693-051X
0000-0002-1417-9553
PMID 40031527
PQID 3171489837
PQPubID 85429
PageCount 15
ParticipantIDs crossref_primary_10_1109_TIP_2025_3539461
pubmed_primary_40031527
ieee_primary_10891329
proquest_journals_3171489837
proquest_miscellaneous_3173404801
crossref_citationtrail_10_1109_TIP_2025_3539461
PublicationCentury 2000
PublicationDate 20250000
2025-00-00
20250101
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – year: 2025
  text: 20250000
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: New York
PublicationTitle IEEE transactions on image processing
PublicationTitleAbbrev TIP
PublicationTitleAlternate IEEE Trans Image Process
PublicationYear 2025
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 ref13
ref12
ref15
ref14
ref11
ref10
ref17
ref16
ref19
ref18
ref51
ref50
ref46
ref45
ref48
ref47
ref42
ref41
ref44
ref43
ref49
ref8
ref7
ref9
ref4
ref6
ref5
ref40
ref35
ref34
ref37
ref36
ref31
ref30
ref33
ref32
ref2
ref1
ref39
ref38
ref24
ref23
ref26
ref25
ref20
ref22
ref21
ref28
ref27
ref29
Zhang (ref3) 2018
References_xml – ident: ref38
  doi: 10.1109/TNNLS.2016.2636227
– ident: ref21
  doi: 10.1109/TNNLS.2022.3172183
– ident: ref39
  doi: 10.1109/TGRS.2017.2739800
– ident: ref48
  doi: 10.1109/TGRS.2021.3061686
– ident: ref20
  doi: 10.1109/TGRS.2021.3056196
– ident: ref30
  doi: 10.1109/TIP.2017.2784560
– ident: ref22
  doi: 10.1109/TNNLS.2021.3056238
– ident: ref32
  doi: 10.1016/j.cviu.2019.102817
– ident: ref49
  doi: 10.1109/TSMC.1979.4310076
– ident: ref26
  doi: 10.1109/TCYB.2019.2950560
– year: 2018
  ident: ref3
  article-title: Change detection between multimodal remote sensing data using Siamese CNN
  publication-title: arXiv:1807.09562
– ident: ref25
  doi: 10.1145/3439950
– ident: ref29
  doi: 10.1109/TIP.2014.2387013
– ident: ref31
  doi: 10.1109/LGRS.2013.2250908
– ident: ref13
  doi: 10.1109/TGRS.2019.2930348
– ident: ref43
  doi: 10.1016/j.isprsjprs.2021.07.007
– ident: ref50
  doi: 10.1109/TIP.2010.2040763
– ident: ref35
  doi: 10.1109/LGRS.2020.3037930
– ident: ref4
  doi: 10.1007/978-3-319-11469-9_10
– ident: ref14
  doi: 10.1109/TGRS.2021.3097717
– ident: ref37
  doi: 10.1016/j.isprsjprs.2022.01.004
– ident: ref23
  doi: 10.1109/CVPRW56347.2022.00141
– ident: ref51
  doi: 10.1109/TIP.2012.2219547
– ident: ref16
  doi: 10.1109/TGRS.2020.3013673
– ident: ref33
  doi: 10.3390/rs12172683
– ident: ref41
  doi: 10.1109/LGRS.2018.2868704
– ident: ref45
  doi: 10.1109/TGRS.2022.3229027
– ident: ref47
  doi: 10.1109/LGRS.2022.3173300
– ident: ref7
  doi: 10.1109/TGRS.2021.3130940
– ident: ref12
  doi: 10.1109/TGRS.2020.2986239
– ident: ref10
  doi: 10.1109/TGRS.2020.3000296
– ident: ref18
  doi: 10.1109/TIP.2021.3093766
– ident: ref34
  doi: 10.1109/TGRS.2022.3168126
– ident: ref8
  doi: 10.1109/TGRS.2021.3139077
– ident: ref40
  doi: 10.1109/JSTARS.2020.2964409
– ident: ref36
  doi: 10.1109/TGRS.2021.3110998
– ident: ref28
  doi: 10.3390/rs11202377
– ident: ref9
  doi: 10.1016/j.isprsjprs.2021.05.001
– ident: ref5
  doi: 10.1109/TIP.2011.2170702
– ident: ref19
  doi: 10.1109/TNNLS.2022.3184414
– ident: ref11
  doi: 10.1109/TNNLS.2015.2435783
– ident: ref24
  doi: 10.1016/j.engappai.2023.105835
– ident: ref46
  doi: 10.3390/rs13183750
– ident: ref6
  doi: 10.1109/MGRS.2021.3088865
– ident: ref44
  doi: 10.1080/17538947.2022.2092658
– ident: ref2
  doi: 10.1109/TIP.2019.2933747
– ident: ref27
  doi: 10.1109/TGRS.2008.916476
– ident: ref42
  doi: 10.1080/01431161.2018.1547934
– ident: ref1
  doi: 10.1109/JPROC.2022.3219376
– ident: ref15
  doi: 10.1109/LGRS.2018.2843385
– ident: ref17
  doi: 10.1016/j.patcog.2020.107598
SSID ssj0014516
Score 2.5331366
Snippet The main challenge of multimodal change detection (MCD) is that multimodal bitemporal images (MBIs) cannot be compared directly to identify changes. To...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 1219
SubjectTerms Algorithms
Autoencoders
Change detection
Clustering
Clustering algorithms
Coders
Commonality
commonality feature
Data mining
Decoders
Decoding
Electronic mail
Feature extraction
heterogeneous images
Image reconstruction
Image sensors
Learning
Multimodal change detection
Representation learning
Representations
Training
unsupervised change detection
Title Commonality Feature Representation Learning for Unsupervised Multimodal Change Detection
URI https://ieeexplore.ieee.org/document/10891329
https://www.ncbi.nlm.nih.gov/pubmed/40031527
https://www.proquest.com/docview/3171489837
https://www.proquest.com/docview/3173404801
Volume 34
WOSCitedRecordID wos001433275600003&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/eLvHCXMwlV1Lb9QwEB61VQ9woFAKBNrKSFw4pN2149hzREBVLlWFWmlvUfwIQqLZarPh9zPjeFflUCRukeLYVmbG843nBfBhrjoZWvYwYm3LyitX2mB0icrP2jgL84BTswlzdWUXC7zOyeopFybGmILP4hk_Jl9-WPqRr8pIwtmpJnEXdo2pp2StrcuAO84m16Y2pSHcv_FJzvD85ts1WYJSnymtsKrnf-mg1FTlcXyZ9MzFwX_u8Dk8y4BSfJo44AXsxP4QDjK4FFl0h0N4-qDy4EtYcGJIBuGCYeC4iuJ7iorNyUi9yKVXfwjCteK2H8Z7PlcGmjVl7d4tA607ZSeIL3GdYrr6I7i9-Hrz-bLMTRZKryq7LrWWKLsoQ-e4aVFrndVYtxg8QZcoK--kJEzrNAbjunk0gQBZh6Tlpex869Qr2OuXfXwDgvQt1_o2NRJoUNLY2riarFQMLqCOroDzzW9vfK5Azo0wfjXJEplhQ4RqmFBNJlQBH7df3E_VN_4x9ojp8WDcRIoCjjekbbJ8Do3ivu8WyTov4P32NUkWu0vaPi7HNEZVqbxOAa8nlthOXvFhqKV5-8ii7-AJ7226qzmGvfVqjCew73-vfw6rU2LfhT1N7PsH4eTrZw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT9wwEB0VWqn0AC2FNgWKK_XSQyBrx3HmiGgRCFihapH2FsUfQUhtFm02_f31ON4VPVCJW6Q4tpXxeN74eWYAvo5Ew21NDCMWZZobodPSKpmiMFntMjuyOBSbUONxOZ3iTQxWD7Ewzrlw-cwd0WPg8u3M9HRU5jWcSDWOa_BS5jnPhnCtFWlANWcDuSlVqjzyX7KSGR5PLm68L8jlkZAC82L0jxUKZVWeRpjB0pxtPXOOb2EzQkp2MqyBd_DCtduwFeEli8rbbcObR7kH38OUQkMiDGcEBPu5Yz_DvdgYjtSymHz1jnlky27brn-gnaXzvYa43d8z68cd4hPYd7cIt7raHbg9-zE5PU9jmYXUiLxcpFJy5I3jttFUtqgudSmxqNEaD14cz43m3KNaLdEq3Yycsh6SNejtPOeNqbXYhfV21rqPwLzFpWzfqkAPGwRXZaF04f1UtNqidDqB4-Vvr0zMQU6lMH5VwRfJsPKCqkhQVRRUAt9WXzwM-Tf-03aH5PGo3SCKBPaXoq2ihnaVoMrvJXr_PIEvq9det4gwqVs360MbkYcEOwl8GJbEqvOctkPJ1acnBj2E1-eT66vq6mJ8uQcbNM_h5GYf1hfz3h3AK_Nncd_NP4dF_Be3J-3G
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=Commonality+Feature+Representation+Learning+for+Unsupervised+Multimodal+Change+Detection&rft.jtitle=IEEE+transactions+on+image+processing&rft.au=Liu%2C+Tongfei&rft.au=Zhang%2C+Mingyang&rft.au=Gong%2C+Maoguo&rft.au=Zhang%2C+Qingfu&rft.date=2025&rft.eissn=1941-0042&rft.volume=34&rft.spage=1219&rft_id=info:doi/10.1109%2FTIP.2025.3539461&rft_id=info%3Apmid%2F40031527&rft.externalDocID=40031527
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