Spatial-Temporal Based Multihead Self-Attention for Remote Sensing Image Change Detection
The neural network-based remote sensing image change detection method faces a large amount of imaging interference and severe class imbalance problems under high-resolution conditions, which bring new challenges to the accuracy of the detection network. In this work, to address the imaging interfere...
Saved in:
| Published in | IEEE transactions on circuits and systems for video technology Vol. 32; no. 10; pp. 6615 - 6626 |
|---|---|
| Main Authors | , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
New York
IEEE
01.10.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
| ISSN | 1051-8215 1558-2205 |
| DOI | 10.1109/TCSVT.2022.3176055 |
Cover
Loading…
| Abstract | The neural network-based remote sensing image change detection method faces a large amount of imaging interference and severe class imbalance problems under high-resolution conditions, which bring new challenges to the accuracy of the detection network. In this work, to address the imaging interference caused by different imaging angles and times, the siamese strategy and multi-head self-attention mechanism are used to reduce the imaging differences between the dual-temporal images and fully exploit the inter-temporal information. Secondly, a learnable multi-part feature learning module is used to adaptively exploit features from different scales to obtain more comprehensive features. Finally, a mixed loss function strategy is used to ensure that the network converges effectively and excludes the adverse interference of a large number of negative samples to the network. Extensive experiments show that our method outperforms numerous methods on LEVIR-CD, WHU, and DSIFN datasets. |
|---|---|
| AbstractList | The neural network-based remote sensing image change detection method faces a large amount of imaging interference and severe class imbalance problems under high-resolution conditions, which bring new challenges to the accuracy of the detection network. In this work, to address the imaging interference caused by different imaging angles and times, the siamese strategy and multi-head self-attention mechanism are used to reduce the imaging differences between the dual-temporal images and fully exploit the inter-temporal information. Secondly, a learnable multi-part feature learning module is used to adaptively exploit features from different scales to obtain more comprehensive features. Finally, a mixed loss function strategy is used to ensure that the network converges effectively and excludes the adverse interference of a large number of negative samples to the network. Extensive experiments show that our method outperforms numerous methods on LEVIR-CD, WHU, and DSIFN datasets. |
| Author | Yao, Rui Wang, Fengkai Zhou, Yong Chen, Silin Zhao, Jiaqi Ma, Heping |
| Author_xml | – sequence: 1 givenname: Yong orcidid: 0000-0001-6207-0299 surname: Zhou fullname: Zhou, Yong organization: School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China – sequence: 2 givenname: Fengkai orcidid: 0000-0002-3814-0274 surname: Wang fullname: Wang, Fengkai organization: School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China – sequence: 3 givenname: Jiaqi orcidid: 0000-0002-3564-5090 surname: Zhao fullname: Zhao, Jiaqi email: jiaqizhao@cumt.edu.cn organization: School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China – sequence: 4 givenname: Rui orcidid: 0000-0003-2734-915X surname: Yao fullname: Yao, Rui organization: School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China – sequence: 5 givenname: Silin surname: Chen fullname: Chen, Silin organization: School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China – sequence: 6 givenname: Heping surname: Ma fullname: Ma, Heping organization: Shanghai Royal View Company Ltd., Shanghai, China |
| BookMark | eNp9UMtOwzAQtFCRaAs_AJdInFNsx46TYwmvSkVINCBxspxk07pK7OK4B_6ehFYcOHCalXZmZ2cmaGSsAYQuCZ4RgtObPFu95zOKKZ1FRMSY8xM0JpwnIaWYj_oZcxImlPAzNOm6LcaEJUyM0cdqp7xWTZhDu7NONcGt6qAKnveN1xtQVbCCpg7n3oPx2pqgti54hdZ66Dem02YdLFq1hiDbKNPDHXgoB-Y5Oq1V08HFEafo7eE-z57C5cvjIpsvw5Km3IcJJ1Uh6oLHlOFUcAVKRKTkpKbA-zdxJZiI06KAkhUR7QmMRAmJC87SGEcsmqLrw92ds5976Lzc2r0zvaWkghJGE5wOLHpglc52nYNa7pxulfuSBMuhQvlToRwqlMcKe1HyR1Rqr4Zw3ind_C-9Okg1APx6pUL0WXD0DYoDf50 |
| CODEN | ITCTEM |
| CitedBy_id | crossref_primary_10_1109_TGRS_2024_3415618 crossref_primary_10_1109_TGRS_2025_3540864 crossref_primary_10_1109_TAI_2024_3363685 crossref_primary_10_1371_journal_pone_0306755 crossref_primary_10_3390_rs16234569 crossref_primary_10_1109_TCSVT_2023_3343881 crossref_primary_10_1109_TGRS_2023_3278739 crossref_primary_10_1109_TGRS_2023_3295992 crossref_primary_10_1109_TIM_2025_3540121 crossref_primary_10_1109_TCSVT_2023_3296745 crossref_primary_10_1109_TGRS_2024_3411714 crossref_primary_10_3390_rs15071887 crossref_primary_10_1016_j_isprsjprs_2022_07_016 crossref_primary_10_1109_TCSVT_2024_3407138 crossref_primary_10_3389_fnins_2023_1290803 crossref_primary_10_1109_MGRS_2024_3412770 crossref_primary_10_1109_TGRS_2024_3352816 crossref_primary_10_1109_TCSVT_2024_3349909 crossref_primary_10_1109_TCSVT_2024_3370668 crossref_primary_10_1109_TGRS_2024_3424532 crossref_primary_10_1016_j_ejrh_2024_102023 crossref_primary_10_1109_TCSVT_2023_3344092 crossref_primary_10_1109_TGRS_2023_3325829 crossref_primary_10_1109_TCSVT_2024_3445337 crossref_primary_10_1109_TGRS_2024_3490773 crossref_primary_10_1016_j_knosys_2024_111672 crossref_primary_10_1109_TCSVT_2024_3494820 crossref_primary_10_1109_ACCESS_2023_3333360 crossref_primary_10_1109_JSTARS_2024_3466901 crossref_primary_10_1109_TGRS_2023_3325220 crossref_primary_10_1016_j_patrec_2023_12_023 crossref_primary_10_1109_TCSVT_2024_3452135 crossref_primary_10_1109_TGRS_2025_3536473 crossref_primary_10_1016_j_eswa_2024_125505 crossref_primary_10_3390_s24031010 crossref_primary_10_3390_s23115166 crossref_primary_10_1117_1_JRS_18_044508 crossref_primary_10_3390_s25051595 crossref_primary_10_1109_JSTARS_2024_3350129 crossref_primary_10_1109_TCSVT_2023_3312321 crossref_primary_10_1109_TCSVT_2024_3502136 crossref_primary_10_1016_j_isprsjprs_2023_05_033 crossref_primary_10_1109_TCSVT_2022_3227172 crossref_primary_10_1007_s10489_024_05359_4 crossref_primary_10_1109_TCSVT_2022_3224068 crossref_primary_10_1109_TGRS_2024_3383800 crossref_primary_10_1016_j_isprsjprs_2023_07_001 crossref_primary_10_1109_TGRS_2024_3470314 |
| Cites_doi | 10.1080/01431161.2011.648285 10.1016/j.isprsjprs.2021.05.001 10.5555/3045118.3045336 10.1016/j.neucom.2021.06.059 10.1109/CVPR46437.2021.00863 10.1109/TIP.2020.3031173 10.1109/TGRS.2022.3160007 10.1109/CVPR.2018.00636 10.1109/TCSVT.2019.2950526 10.1109/TGRS.2021.3095166 10.1109/TCSVT.2020.2975671 10.3390/rs11111292 10.1109/TCYB.2021.3086884 10.1109/ICIP.2018.8451652 10.1109/CVPR.2017.106 10.1109/LGRS.2019.2948660 10.1109/JSTARS.2019.2929514 10.1109/LGRS.2019.2916601 10.1109/SMC.2018.00289 10.1109/CVPRW.2019.00062 10.1109/TCSVT.2021.3066675 10.1109/LGRS.2017.2738149 10.1109/TCSVT.2022.3142771 10.1109/ICCV.2019.00200 10.1109/JSTARS.2021.3077545 10.3390/rs12121933 10.1109/Multi-Temp.2019.8866971 10.1109/LGRS.2019.2945906 10.1109/Multi-Temp.2019.8866947 10.1109/LGRS.2019.2955309 10.1016/j.jag.2019.102011 10.1109/ICCV.2017.324 10.1109/IGARSS.2019.8898146 10.1016/j.isprsjprs.2020.06.003 10.1016/j.neucom.2019.10.022 10.1109/TCSVT.2018.2875449 10.1109/JSTARS.2020.3037893 10.3390/rs12020205 10.1109/CVPR.2016.90 10.1109/3DV.2016.79 10.1109/LGRS.2020.2988032 10.1016/j.neucom.2021.01.030 10.1109/TGRS.2022.3168331 10.1109/LGRS.2018.2868704 10.1016/j.rse.2015.01.006 10.1109/TIP.2021.3089361 10.1016/j.isprsjprs.2021.05.002 10.1007/978-3-030-58452-8_13 10.1109/TGRS.2018.2858817 10.3390/rs12060901 10.1109/LGRS.2021.3056416 10.1016/j.jag.2021.102348 10.3390/rs12101662 10.1109/TGRS.2019.2956756 10.1109/LGRS.2019.2953754 10.1016/j.isprsjprs.2021.03.005 10.1109/TGRS.2019.2948659 10.3390/rs12030484 10.1109/TPAMI.2021.3050918 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022 |
| DBID | 97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D |
| DOI | 10.1109/TCSVT.2022.3176055 |
| DatabaseName | IEEE Xplore (IEEE) 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 | 6626 |
| ExternalDocumentID | 10_1109_TCSVT_2022_3176055 9777690 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: Natural Science Foundation of Jiangsu Province grantid: BK20201346; BK20180639 funderid: 10.13039/501100004608 – fundername: National Natural Science Foundation of China grantid: 61806206; 62172417 funderid: 10.13039/501100001809 – fundername: Six Talent Peaks Project in Jiangsu Province grantid: 2015-DZXX-010; 2018-XYDXX-044 funderid: 10.13039/501100010014 |
| 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-851db7fb56240975aea731c51f2e50010d74769bbec4b3275a413816b54960343 |
| IEDL.DBID | RIE |
| ISSN | 1051-8215 |
| IngestDate | Sun Jun 29 16:57:06 EDT 2025 Tue Jul 01 00:41:17 EDT 2025 Thu Apr 24 22:57:04 EDT 2025 Wed Aug 27 02:14:17 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 10 |
| 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-851db7fb56240975aea731c51f2e50010d74769bbec4b3275a413816b54960343 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0003-2734-915X 0000-0002-3814-0274 0000-0002-3564-5090 0000-0001-6207-0299 |
| PQID | 2721428094 |
| PQPubID | 85433 |
| PageCount | 12 |
| ParticipantIDs | crossref_citationtrail_10_1109_TCSVT_2022_3176055 proquest_journals_2721428094 crossref_primary_10_1109_TCSVT_2022_3176055 ieee_primary_9777690 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2022-10-01 |
| PublicationDateYYYYMMDD | 2022-10-01 |
| PublicationDate_xml | – month: 10 year: 2022 text: 2022-10-01 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 | 2022 |
| 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 ref57 ref12 ref56 ref15 ref59 ref14 ref58 ref53 ref52 ref11 ref55 ref10 ref54 Weber (ref5) 2020 ref17 ref16 ref19 ref18 ref51 ref50 ref46 ref45 ref48 ref47 ref42 ref41 ref44 ref43 ref49 ref8 ref7 ref9 ref3 ref6 ref40 Goodfellow (ref20); 27 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref2 ref1 ref39 ref38 ref24 ref26 ref25 ref64 ref63 ref22 ref21 ref28 ref27 ref29 Xu (ref4) 2019 Vaswani (ref23) ref60 ref62 ref61 Dai (ref35) 2021 |
| References_xml | – ident: ref2 doi: 10.1080/01431161.2011.648285 – ident: ref48 doi: 10.1016/j.isprsjprs.2021.05.001 – ident: ref59 doi: 10.5555/3045118.3045336 – volume: 27 start-page: 1 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref20 article-title: Generative adversarial nets – ident: ref53 doi: 10.1016/j.neucom.2021.06.059 – year: 2019 ident: ref4 article-title: Building damage detection in satellite imagery using convolutional neural networks publication-title: arXiv:1910.06444 – ident: ref34 doi: 10.1109/CVPR46437.2021.00863 – ident: ref62 doi: 10.1109/TIP.2020.3031173 – ident: ref57 doi: 10.1109/TGRS.2022.3160007 – ident: ref60 doi: 10.1109/CVPR.2018.00636 – ident: ref39 doi: 10.1109/TCSVT.2019.2950526 – ident: ref64 doi: 10.1109/TGRS.2021.3095166 – ident: ref36 doi: 10.1109/TCSVT.2020.2975671 – ident: ref14 doi: 10.3390/rs11111292 – ident: ref19 doi: 10.1109/TCYB.2021.3086884 – ident: ref22 doi: 10.1109/ICIP.2018.8451652 – ident: ref37 doi: 10.1109/CVPR.2017.106 – ident: ref29 doi: 10.1109/LGRS.2019.2948660 – ident: ref49 doi: 10.1109/JSTARS.2019.2929514 – ident: ref9 doi: 10.1109/LGRS.2019.2916601 – ident: ref38 doi: 10.1109/SMC.2018.00289 – ident: ref6 doi: 10.1109/CVPRW.2019.00062 – ident: ref40 doi: 10.1109/TCSVT.2021.3066675 – ident: ref11 doi: 10.1109/LGRS.2017.2738149 – ident: ref32 doi: 10.1109/TCSVT.2022.3142771 – ident: ref61 doi: 10.1109/ICCV.2019.00200 – ident: ref26 doi: 10.1109/JSTARS.2021.3077545 – ident: ref50 doi: 10.3390/rs12121933 – ident: ref3 doi: 10.1109/Multi-Temp.2019.8866971 – ident: ref13 doi: 10.1109/LGRS.2019.2945906 – ident: ref43 doi: 10.1109/Multi-Temp.2019.8866947 – ident: ref44 doi: 10.1109/LGRS.2019.2955309 – start-page: 5998 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref23 article-title: Attention is all you need – ident: ref8 doi: 10.1016/j.jag.2019.102011 – ident: ref51 doi: 10.1109/ICCV.2017.324 – year: 2020 ident: ref5 article-title: Building disaster damage assessment in satellite imagery with multi-temporal fusion publication-title: arXiv:2004.05525 – ident: ref10 doi: 10.1109/IGARSS.2019.8898146 – ident: ref25 doi: 10.1016/j.isprsjprs.2020.06.003 – ident: ref45 doi: 10.1016/j.neucom.2019.10.022 – ident: ref42 doi: 10.1109/TCSVT.2018.2875449 – ident: ref24 doi: 10.1109/JSTARS.2020.3037893 – ident: ref18 doi: 10.3390/rs12020205 – ident: ref58 doi: 10.1109/CVPR.2016.90 – ident: ref52 doi: 10.1109/3DV.2016.79 – ident: ref54 doi: 10.1109/LGRS.2020.2988032 – ident: ref46 doi: 10.1016/j.neucom.2021.01.030 – ident: ref56 doi: 10.1109/TGRS.2022.3168331 – ident: ref21 doi: 10.1109/LGRS.2018.2868704 – ident: ref1 doi: 10.1016/j.rse.2015.01.006 – ident: ref41 doi: 10.1109/TIP.2021.3089361 – ident: ref28 doi: 10.1016/j.isprsjprs.2021.05.002 – ident: ref33 doi: 10.1007/978-3-030-58452-8_13 – ident: ref63 doi: 10.1109/TGRS.2018.2858817 – ident: ref7 doi: 10.3390/rs12060901 – ident: ref55 doi: 10.1109/LGRS.2021.3056416 – ident: ref27 doi: 10.1016/j.jag.2021.102348 – ident: ref17 doi: 10.3390/rs12101662 – ident: ref15 doi: 10.1109/TGRS.2019.2956756 – ident: ref12 doi: 10.1109/LGRS.2019.2953754 – ident: ref47 doi: 10.1016/j.isprsjprs.2021.03.005 – ident: ref16 doi: 10.1109/TGRS.2019.2948659 – year: 2021 ident: ref35 article-title: CoAtNet: Marrying convolution and attention for all data sizes publication-title: arXiv:2106.04803 – ident: ref30 doi: 10.3390/rs12030484 – ident: ref31 doi: 10.1109/TPAMI.2021.3050918 |
| SSID | ssj0014847 |
| Score | 2.5819314 |
| Snippet | The neural network-based remote sensing image change detection method faces a large amount of imaging interference and severe class imbalance problems under... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 6615 |
| SubjectTerms | attention mechanism Building change detection Change detection Computer vision deep learning Feature extraction Imaging Interference multi-scale Neural networks Remote sensing Task analysis Transformers |
| Title | Spatial-Temporal Based Multihead Self-Attention for Remote Sensing Image Change Detection |
| URI | https://ieeexplore.ieee.org/document/9777690 https://www.proquest.com/docview/2721428094 |
| Volume | 32 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV07T8MwED61nWDgVRCFgjywgdvGifMYS6EqSGWgKSpTFMfOQkkRpAu_nrPzEC8htkixI8vn-L7PvvsO4CyVWmWfpzRgaUoddLhUMCaoSm2f88SVrtLnHdM7dzJ3bhd80YCLOhdGKWWCz1RPP5q7fLlK1vqorI9YxUM214QmErciV6u-MXB8U0wM4YJFffRjVYLMIOiHo9lDiFSQMWSoHuJ3_sUJmaoqP7Zi41_G2zCtRlaElTz11rnoJe_fRBv_O_Qd2CqBJhkWK2MXGirbg81P8oNteNT1iHH90bDQp1qSS_RpkpikXNykJZmpZUqHeV7ERBIEuOReoXEVvsn0KQO5ecYNiRQ5CuRK5SayK9uH-fg6HE1oWWqBJizgOUXcJYWXCkRDWgCLxyr2bCvhVsoU17xRIu1wA4EWd4TNsAE6P99yBdJLd2A79gG0slWmDoEM4iDgUtoxdjFRVL4bI-myY-RmnuR-B6xq7qOk1CHX5TCWkeEjgyAy9oq0vaLSXh04r_u8FCocf7ZuawPULcu570C3MnFU_qhvEfOM5hyS3KPfex3Dhv52Eb_XhVb-ulYniENycWoW4AdBMtbm |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3JTsMwEB1BOQAHtoIoqw_cwCVx4ixHVpWlPdAUwSmKY-dCSRGkF76esbOITYhbpNiK5ed45tkzbwAOMqlV9nlGQ5Zl1EWDSwVjgqrMCThPPekpfd7RH3i9kXv9wB9m4KjJhVFKmeAz1dWP5i5fTtKpPio7Rl_FRzY3C3No992wzNZq7gzcwJQTQ4fBpgFasjpFxgqPo7PhfYRkkDHkqD568PyLGTJ1VX5sxsbCXC5Dvx5bGVjy1J0Wopu-f5Nt_O_gV2CpcjXJSbk2VmFG5Wuw-EmAsA2PuiIxrkAalQpVY3KKVk0Sk5aL27QkQzXO6ElRlFGRBF1ccqcQXoVvcn3OQK6ecUsiZZYCOVeFie3K12F0eRGd9WhVbIGmLOQFRc9LCj8T6A9pCSyeqMR37JTbGVNcM0eJxMMLBWLuCodhAzR_ge0JBMKzHNfZgFY-ydUmECsJQy6lk2AXE0cVeAnSLidBduZLHnTAruc-Tislcl0QYxwbRmKFscEr1njFFV4dOGz6vJQ6HH-2bmsAmpbV3Hdgp4Y4rn7Vt5j5RnUOae7W7732Yb4X9W_j26vBzTYs6O-U0Xw70Cpep2oXvZJC7JnF-AG2Tdo2 |
| 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=Spatial-Temporal+Based+Multihead+Self-Attention+for+Remote+Sensing+Image+Change+Detection&rft.jtitle=IEEE+transactions+on+circuits+and+systems+for+video+technology&rft.au=Zhou%2C+Yong&rft.au=Wang%2C+Fengkai&rft.au=Zhao%2C+Jiaqi&rft.au=Yao%2C+Rui&rft.date=2022-10-01&rft.pub=IEEE&rft.issn=1051-8215&rft.volume=32&rft.issue=10&rft.spage=6615&rft.epage=6626&rft_id=info:doi/10.1109%2FTCSVT.2022.3176055&rft.externalDocID=9777690 |
| 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 |