YDTR: Infrared and Visible Image Fusion via Y-Shape Dynamic Transformer

Infrared and visible image fusion is aims to generate a composite image that can simultaneously describe the salient target in the infrared image and texture details in the visible image of the same scene. Since deep learning (DL) exhibits great feature extraction ability in computer vision tasks, i...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on multimedia Ročník 25; s. 5413 - 5428
Hlavní autoři:	Tang, Wei, He, Fazhi, Liu, Yu
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Piscataway IEEE 2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Computer vision Dynamic transformer Feature extraction Image fusion Image segmentation infrared image Infrared imagery Roads Task analysis Thermal radiation Training Transformers Y-shape network
ISSN:	1520-9210, 1941-0077
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Infrared and visible image fusion is aims to generate a composite image that can simultaneously describe the salient target in the infrared image and texture details in the visible image of the same scene. Since deep learning (DL) exhibits great feature extraction ability in computer vision tasks, it has also been widely employed in handling infrared and visible image fusion issue. However, the existing DL-based methods generally extract complementary information from source images through convolutional operations, which results in limited preservation of global features. To this end, we propose a novel infrared and visible image fusion method, i.e., the Y-shape dynamic Transformer (YDTR). Specifically, a dynamic Transformer module (DTRM) is designed to acquire not only the local features but also the significant context information. Furthermore, the proposed network is devised in a Y-shape to comprehensively maintain the thermal radiation information from the infrared image and scene details from the visible image. Considering the specific information provided by the source images, we design a loss function that consists of two terms to improve fusion quality: a structural similarity (SSIM) term and a spatial frequency (SF) term. Extensive experiments on mainstream datasets illustrate that the proposed method outperforms both classical and state-of-the-art approaches in both qualitative and quantitative assessments. We further extend the YDTR to address other infrared and RGB-visible images and multi-focus images without fine-tuning, and the satisfactory fusion results demonstrate that the proposed method has good generalization capability.
AbstractList	Infrared and visible image fusion is aims to generate a composite image that can simultaneously describe the salient target in the infrared image and texture details in the visible image of the same scene. Since deep learning (DL) exhibits great feature extraction ability in computer vision tasks, it has also been widely employed in handling infrared and visible image fusion issue. However, the existing DL-based methods generally extract complementary information from source images through convolutional operations, which results in limited preservation of global features. To this end, we propose a novel infrared and visible image fusion method, i.e., the Y-shape dynamic Transformer (YDTR). Specifically, a dynamic Transformer module (DTRM) is designed to acquire not only the local features but also the significant context information. Furthermore, the proposed network is devised in a Y-shape to comprehensively maintain the thermal radiation information from the infrared image and scene details from the visible image. Considering the specific information provided by the source images, we design a loss function that consists of two terms to improve fusion quality: a structural similarity (SSIM) term and a spatial frequency (SF) term. Extensive experiments on mainstream datasets illustrate that the proposed method outperforms both classical and state-of-the-art approaches in both qualitative and quantitative assessments. We further extend the YDTR to address other infrared and RGB-visible images and multi-focus images without fine-tuning, and the satisfactory fusion results demonstrate that the proposed method has good generalization capability.
Author	He, Fazhi Tang, Wei Liu, Yu
Author_xml	– sequence: 1 givenname: Wei orcidid: 0000-0001-8995-705X surname: Tang fullname: Tang, Wei email: weitang2021@whu.edu.cn organization: School of Computer Science, Wuhan University, Wuhan, China – sequence: 2 givenname: Fazhi orcidid: 0000-0001-7016-3698 surname: He fullname: He, Fazhi email: fzhe@whu.edu.cn organization: School of Computer Science, Wuhan University, Wuhan, China – sequence: 3 givenname: Yu orcidid: 0000-0003-2211-3535 surname: Liu fullname: Liu, Yu email: yuliu@hfut.edu.cn organization: Department of Biomedical Engineering, Hefei University of Technology, Hefei, China
BookMark	eNp9kEFLAzEQRoNUsK3eBS8Bz1tnkt1N4k1aWwstgq5CT0t2m9WUNluTrdB_75YWDx68zMzhezPM65GOq50h5BphgAjqLpvPBwwYG3BULE3xjHRRxRgBCNFp54RBpBjCBemFsALAOAHRJZPFKHu5p1NXee3Nkmq3pO822GJt6HSjPwwd74KtHf22mi6i10-9NXS0d3pjS5p57UJV-43xl-S80utgrk69T97Gj9nwKZo9T6bDh1lUMoVNhLIAVSSqiBG0SnSqQEJapFyJZcolK4RQBgEqNIqLoihLqRhrS4UoRCl4n9we9259_bUzoclX9c679mTOpIyl4inINpUeU6WvQ_Cmykvb6Kb9o_HarnOE_CAtb6XlB2n5SVoLwh9w6-1G-_1_yM0RscaY37iSPEYu-A8JI3ZI
CODEN	ITMUF8
CitedBy_id	crossref_primary_10_1007_s00354_025_00292_7 crossref_primary_10_1016_j_neucom_2025_130062 crossref_primary_10_1016_j_patcog_2025_111468 crossref_primary_10_1109_TGRS_2024_3355968 crossref_primary_10_1016_j_patcog_2024_110774 crossref_primary_10_3390_s23167097 crossref_primary_10_1016_j_jvcir_2024_104350 crossref_primary_10_1109_JSEN_2025_3571945 crossref_primary_10_1109_LSP_2025_3578250 crossref_primary_10_1016_j_cosrev_2025_100804 crossref_primary_10_3390_app131910891 crossref_primary_10_1016_j_imavis_2025_105709 crossref_primary_10_1109_TITS_2024_3426539 crossref_primary_10_1109_TPAMI_2024_3521416 crossref_primary_10_1016_j_ins_2024_121291 crossref_primary_10_1109_TGRS_2024_3389976 crossref_primary_10_1109_TPAMI_2025_3572599 crossref_primary_10_1016_j_engappai_2024_109521 crossref_primary_10_1109_TMM_2025_3543053 crossref_primary_10_1016_j_optlastec_2024_111396 crossref_primary_10_1016_j_optlastec_2025_112763 crossref_primary_10_1109_JSEN_2024_3426274 crossref_primary_10_1109_LSP_2024_3509341 crossref_primary_10_1109_TIM_2025_3527616 crossref_primary_10_3390_s22249739 crossref_primary_10_3390_electronics12132773 crossref_primary_10_1016_j_neucom_2025_129592 crossref_primary_10_3390_rs16173136 crossref_primary_10_1016_j_inffus_2025_103433 crossref_primary_10_1007_s00371_023_02811_3 crossref_primary_10_1016_j_bspc_2025_107890 crossref_primary_10_1109_TIM_2023_3328710 crossref_primary_10_1007_s00371_025_03840_w crossref_primary_10_1016_j_infrared_2025_105804 crossref_primary_10_3390_s24082466 crossref_primary_10_1007_s00371_024_03422_2 crossref_primary_10_1109_ACCESS_2024_3488315 crossref_primary_10_1016_j_measurement_2024_114977 crossref_primary_10_1016_j_patcog_2024_110822 crossref_primary_10_1016_j_inffus_2025_103031 crossref_primary_10_1016_j_imavis_2025_105566 crossref_primary_10_1016_j_displa_2025_103118 crossref_primary_10_1364_PRJ_559833 crossref_primary_10_1016_j_infrared_2025_106052 crossref_primary_10_1109_TMM_2024_3410113 crossref_primary_10_1109_TPAMI_2025_3535617 crossref_primary_10_1145_3665893 crossref_primary_10_1007_s00371_023_02827_9 crossref_primary_10_1007_s10489_023_04576_7 crossref_primary_10_1109_TETCI_2025_3542146 crossref_primary_10_3390_ai6090229 crossref_primary_10_3389_fnbot_2024_1521603 crossref_primary_10_3390_electronics13122365 crossref_primary_10_1007_s00371_023_02784_3 crossref_primary_10_1007_s11760_025_04549_y crossref_primary_10_1016_j_ultrasmedbio_2025_02_001 crossref_primary_10_1109_TMM_2024_3366150 crossref_primary_10_1016_j_neucom_2022_12_042 crossref_primary_10_1109_TMM_2025_3535291 crossref_primary_10_3390_math12142189 crossref_primary_10_1007_s00371_023_03003_9 crossref_primary_10_1016_j_infrared_2025_105728 crossref_primary_10_1109_TIM_2023_3318709 crossref_primary_10_1109_ACCESS_2024_3412157 crossref_primary_10_1007_s10489_023_04607_3 crossref_primary_10_1016_j_engappai_2023_106112 crossref_primary_10_1016_j_infrared_2024_105209 crossref_primary_10_1016_j_optlastec_2025_112612 crossref_primary_10_1109_LSP_2023_3309153 crossref_primary_10_1016_j_dsp_2025_105200 crossref_primary_10_1109_TGRS_2025_3527515 crossref_primary_10_1109_ACCESS_2025_3577033 crossref_primary_10_3390_s25030791 crossref_primary_10_1016_j_measurement_2024_115092 crossref_primary_10_1016_j_optlastec_2025_112971 crossref_primary_10_1016_j_optlastec_2025_113544 crossref_primary_10_1109_TMM_2024_3521752 crossref_primary_10_1145_3737646 crossref_primary_10_1109_TMM_2024_3521751 crossref_primary_10_1109_TMM_2025_3535284 crossref_primary_10_1109_TIM_2023_3342223 crossref_primary_10_1016_j_eswa_2025_128895 crossref_primary_10_1109_JIOT_2025_3569573 crossref_primary_10_1109_TCE_2023_3341852 crossref_primary_10_1016_j_imavis_2024_105161 crossref_primary_10_1109_TIP_2024_3512365 crossref_primary_10_1109_JSEN_2024_3371056 crossref_primary_10_1016_j_knosys_2024_111949 crossref_primary_10_1109_TIP_2025_3593775 crossref_primary_10_1016_j_aei_2025_103251 crossref_primary_10_1109_TCSVT_2024_3412743 crossref_primary_10_1109_TCSVT_2023_3234340 crossref_primary_10_32604_cmc_2024_053708 crossref_primary_10_1016_j_infrared_2022_104466 crossref_primary_10_1016_j_infrared_2025_106005 crossref_primary_10_1007_s40747_025_02046_w crossref_primary_10_1109_TIM_2024_3457951 crossref_primary_10_1016_j_knosys_2025_114027 crossref_primary_10_1016_j_optlastec_2025_113895 crossref_primary_10_1109_TCSVT_2024_3449638 crossref_primary_10_1109_TMM_2024_3521840 crossref_primary_10_3233_ICA_230700 crossref_primary_10_1007_s00371_022_02727_4 crossref_primary_10_1016_j_sigpro_2025_110073 crossref_primary_10_3390_bdcc9040092 crossref_primary_10_1109_ACCESS_2022_3226564 crossref_primary_10_1109_JSEN_2023_3263336 crossref_primary_10_1109_TCE_2025_3565680 crossref_primary_10_3934_era_2025245 crossref_primary_10_1016_j_ipm_2023_103612 crossref_primary_10_1016_j_eswa_2025_127229 crossref_primary_10_1007_s00371_025_03841_9 crossref_primary_10_1109_ACCESS_2025_3540007 crossref_primary_10_1371_journal_pone_0282909 crossref_primary_10_1016_j_inffus_2025_103754 crossref_primary_10_1016_j_infrared_2025_106012 crossref_primary_10_1109_TMM_2024_3521848 crossref_primary_10_1049_ipr2_70086 crossref_primary_10_1109_TMM_2025_3543002 crossref_primary_10_1016_j_engappai_2025_111123 crossref_primary_10_1109_JAS_2022_106082 crossref_primary_10_3390_app13052907 crossref_primary_10_1109_TGRS_2025_3591809 crossref_primary_10_1109_TMM_2025_3535341 crossref_primary_10_1007_s00530_025_01908_0 crossref_primary_10_3390_s24248217 crossref_primary_10_1016_j_optlaseng_2025_109287 crossref_primary_10_1109_JSEN_2024_3410387 crossref_primary_10_1007_s11263_023_01924_5 crossref_primary_10_1109_JSEN_2023_3262775 crossref_primary_10_1109_TPAMI_2024_3475485 crossref_primary_10_1016_j_inffus_2025_103025 crossref_primary_10_1016_j_patcog_2025_111843 crossref_primary_10_3390_s24010020 crossref_primary_10_1109_TIM_2024_3398115 crossref_primary_10_1109_TCSVT_2025_3544746 crossref_primary_10_1109_TGRS_2025_3583579 crossref_primary_10_32604_cmc_2024_048136 crossref_primary_10_1016_j_infrared_2025_106067 crossref_primary_10_1109_TMM_2023_3347099 crossref_primary_10_1016_j_infrared_2025_105895 crossref_primary_10_1016_j_optlastec_2025_112823 crossref_primary_10_1016_j_optlastec_2025_113075 crossref_primary_10_1007_s11263_025_02409_3 crossref_primary_10_1109_TCI_2024_3436716 crossref_primary_10_1016_j_ipm_2024_103687 crossref_primary_10_1016_j_knosys_2023_110303 crossref_primary_10_1007_s00371_022_02649_1 crossref_primary_10_1109_TNNLS_2024_3454811 crossref_primary_10_1007_s00371_024_03347_w crossref_primary_10_1016_j_patcog_2024_110728 crossref_primary_10_3390_s25165083 crossref_primary_10_1109_TIM_2024_3374294 crossref_primary_10_1109_TMM_2025_3543019 crossref_primary_10_1007_s11042_024_19659_x crossref_primary_10_1002_mp_17607 crossref_primary_10_1109_TPAMI_2024_3523364 crossref_primary_10_1109_TIM_2025_3527542 crossref_primary_10_1109_JSEN_2025_3575460 crossref_primary_10_1109_LSP_2024_3486113 crossref_primary_10_1088_1361_6501_ae0147 crossref_primary_10_1016_j_optlaseng_2025_109265 crossref_primary_10_1109_JAS_2024_124878 crossref_primary_10_1016_j_ipm_2023_103304 crossref_primary_10_1016_j_patcog_2025_111391
Cites_doi	10.1016/j.inffus.2021.02.023 10.1016/j.inffus.2005.10.001 10.1155/2019/5450373 10.1007/s11263-006-6655-0 10.1016/0167-8655(89)90003-2 10.1016/j.patcog.2010.08.006 10.1049/el:20081754 10.1016/j.inffus.2014.09.004 10.1109/CVPR46437.2021.00863 10.1109/ACSSC.2003.1292216 10.1016/j.inffus.2018.09.004 10.1016/j.inffus.2006.02.001 10.1016/j.inffus.2016.05.004 10.1016/j.inffus.2017.10.007 10.1109/CVPR46437.2021.00681 10.1109/TIM.2020.3029360 10.48550/arXiv.2102.04306 10.1109/TIP.2020.2977573 10.1109/TCSVT.2021.3075745 10.1016/j.inffus.2012.01.008 10.1109/TMM.2020.3016123 10.1142/S0219691318500182 10.1109/TMM.2020.3020695 10.1016/j.inffus.2018.02.004 10.1109/TCI.2021.3083965 10.18653/v1/P19-1285 10.1109/TMM.2020.2997127 10.1016/j.inffus.2019.12.014 10.1016/j.optcom.2014.12.048 10.1109/TMM.2017.2760100 10.1109/TIP.2009.2025006 10.1109/ICMIPE53131.2021.9698938 10.1609/aaai.v34i07.6936 10.1609/aaai.v34i07.6975 10.1109/TPAMI.2020.3015691 10.1016/j.inffus.2022.03.007 10.48550/ARXIV.1706.03762 10.1109/ICITBE54178.2021.00025 10.1109/TMM.2009.2017640 10.1109/TIM.2020.3038013 10.1016/j.inffus.2021.06.008 10.1016/j.physd.2004.11.001 10.1109/TIP.2003.819861 10.1109/26.477498 10.1109/TPAMI.2011.109 10.1109/TCI.2021.3100986 10.1109/TIP.2018.2887342 10.1109/TCSVT.2021.3056725 10.1016/j.inffus.2008.08.008 10.1109/TMM.2020.2978640 10.1109/TPAMI.2020.3012548 10.1109/TMM.2020.3037526 10.1016/j.ins.2017.09.010 10.1016/j.inffus.2017.05.006
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/TMM.2022.3192661
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://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	1941-0077
EndPage	5428
ExternalDocumentID	10_1109_TMM_2022_3192661 9834137
Genre	orig-research
GrantInformation_xml	– fundername: Science and Technology Major Project of Hubei Province – fundername: National Natural Science Foundation of China grantid: 62072348; 62176081 funderid: 10.13039/501100001809 – fundername: Next-Generation AI Technologies grantid: 2019AEA170 – fundername: National Key Research and Development Program of China; National Key R&D Program of China grantid: 2018AAA0101104 funderid: 10.13039/501100012166
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 ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P PQQKQ RIA RIE RNS TN5 VH1 ZY4 AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c291t-18b09b59b410a95a690806b6397d6382b779e100f1e937bbcc8922c89f1177c73
IEDL.DBID	RIE
ISICitedReferencesCount	272
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001097340300057&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1520-9210
IngestDate	Mon Jun 30 03:11:38 EDT 2025 Tue Nov 18 22:12:49 EST 2025 Sat Nov 29 08:06:07 EST 2025 Wed Aug 27 01:39:09 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-c291t-18b09b59b410a95a690806b6397d6382b779e100f1e937bbcc8922c89f1177c73
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-2211-3535 0000-0001-7016-3698 0000-0001-8995-705X
PQID	2884893608
PQPubID	75737
PageCount	16
ParticipantIDs	crossref_citationtrail_10_1109_TMM_2022_3192661 crossref_primary_10_1109_TMM_2022_3192661 ieee_primary_9834137 proquest_journals_2884893608
PublicationCentury	2000
PublicationDate	20230000 2023-00-00 20230101
PublicationDateYYYYMMDD	2023-01-01
PublicationDate_xml	– year: 2023 text: 20230000
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE transactions on multimedia
PublicationTitleAbbrev	TMM
PublicationYear	2023
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 Devlin (ref38) 2018 ref52 ref11 ref55 ref10 ref17 ref16 ref19 ref18 Fu (ref32) 2021 ref46 ref45 ref47 ref42 ref44 ref49 Tang (ref54) 2019; 2019 ref8 ref7 VS (ref30) 2021 ref9 ref4 Zhao (ref48) 2007; 3 ref3 ref6 ref5 ref40 Wang (ref43) 2021 ref35 ref34 ref37 ref36 ref31 Chen (ref50) 2007; 8 Rao (ref33) 2022 ref2 ref1 Dosovitskiy (ref41) 2020 Kingma (ref58) 2014 Xiao (ref51) 2021; 34 Li (ref63) 2015; 342 Li (ref62) 2017 ref24 ref23 ref26 ref25 ref20 ref64 ref22 ref21 Eskicioglu (ref53) 1995; 43 ref65 Yang (ref39) 2019; 32 ref28 ref27 ref29 ref60 ref61
References_xml	– ident: ref23 doi: 10.1016/j.inffus.2021.02.023 – volume: 8 start-page: 193 year: 2007 ident: ref50 article-title: A human perception inspired quality metric for image fusion based on regional information publication-title: Inf. Fusion doi: 10.1016/j.inffus.2005.10.001 – volume: 2019 year: 2019 ident: ref54 article-title: Green fluorescent protein and phase-contrast image fusion via generative adversarial networks publication-title: Comput. Math. Methods Med. doi: 10.1155/2019/5450373 – year: 2014 ident: ref58 article-title: Adam: A method for stochastic optimization publication-title: arXiv:1412.6980 – ident: ref6 doi: 10.1007/s11263-006-6655-0 – ident: ref8 doi: 10.1016/0167-8655(89)90003-2 – ident: ref7 doi: 10.1016/j.patcog.2010.08.006 – ident: ref46 doi: 10.1049/el:20081754 – ident: ref13 doi: 10.1016/j.inffus.2014.09.004 – ident: ref45 doi: 10.1109/CVPR46437.2021.00863 – ident: ref49 doi: 10.1109/ACSSC.2003.1292216 – volume: 34 start-page: 1 year: 2021 ident: ref51 article-title: Early convolutions help transformers see better publication-title: Proc. Adv. Neural Inf. Process. Syst. – ident: ref19 doi: 10.1016/j.inffus.2018.09.004 – ident: ref9 doi: 10.1016/j.inffus.2006.02.001 – ident: ref34 doi: 10.1016/j.inffus.2016.05.004 – year: 2021 ident: ref30 article-title: Image fusion transformer publication-title: arXiv:2107.09011 – ident: ref35 doi: 10.1016/j.inffus.2017.10.007 – ident: ref42 doi: 10.1109/CVPR46437.2021.00681 – ident: ref27 doi: 10.1109/TIM.2020.3029360 – start-page: 568 volume-title: Proc. IEEE/CVF Int. Conf. Comput. Vis. year: 2021 ident: ref43 article-title: Pyramid vision transformer: A versatile backbone for dense prediction without convolutions – ident: ref44 doi: 10.48550/arXiv.2102.04306 – ident: ref21 doi: 10.1109/TIP.2020.2977573 – ident: ref26 doi: 10.1109/TCSVT.2021.3075745 – ident: ref12 doi: 10.1016/j.inffus.2012.01.008 – start-page: 675 volume-title: Proc. Int. Conf. Image Graph. year: 2017 ident: ref62 article-title: Multi-focus image fusion using dictionary learning and low-rank representation – ident: ref22 doi: 10.1109/TMM.2020.3016123 – ident: ref25 doi: 10.1142/S0219691318500182 – ident: ref17 doi: 10.1109/TMM.2020.3020695 – ident: ref3 doi: 10.1016/j.inffus.2018.02.004 – ident: ref55 doi: 10.1109/TCI.2021.3083965 – ident: ref40 doi: 10.18653/v1/P19-1285 – ident: ref2 doi: 10.1109/TMM.2020.2997127 – ident: ref5 doi: 10.1016/j.inffus.2019.12.014 – volume: 342 start-page: 1 year: 2015 ident: ref63 article-title: Multi-focus image fusion based on sparse feature matrix decomposition and morphological filtering publication-title: Opt. Commun. doi: 10.1016/j.optcom.2014.12.048 – ident: ref14 doi: 10.1109/TMM.2017.2760100 – ident: ref10 doi: 10.1109/TIP.2009.2025006 – ident: ref61 doi: 10.1109/ICMIPE53131.2021.9698938 – ident: ref65 doi: 10.1609/aaai.v34i07.6936 – ident: ref64 doi: 10.1609/aaai.v34i07.6975 – ident: ref57 doi: 10.1109/TPAMI.2020.3015691 – ident: ref60 doi: 10.1016/j.inffus.2022.03.007 – ident: ref37 doi: 10.48550/ARXIV.1706.03762 – ident: ref31 doi: 10.1109/ICITBE54178.2021.00025 – volume: 3 start-page: 1433 issue: 6 year: 2007 ident: ref48 article-title: Performance assessment of combinative pixel-level image fusion based on an absolute feature measurement publication-title: Int. J. Innov. Comput. Inf. Control – year: 2021 ident: ref32 article-title: PPT fusion: Pyramid patch transformer for a case study in image fusion publication-title: arXiv:2107.13967 – ident: ref11 doi: 10.1109/TMM.2009.2017640 – ident: ref24 doi: 10.1109/TIM.2020.3038013 – year: 2020 ident: ref41 article-title: An image is worth $16\times 16$ words: Transformers for image recognition at scale publication-title: arXiv:2010.11929 – ident: ref36 doi: 10.1016/j.inffus.2021.06.008 – ident: ref47 doi: 10.1016/j.physd.2004.11.001 – volume: 32 start-page: 1 year: 2019 ident: ref39 article-title: XLNet: Generalized autoregressive pretraining for language understanding publication-title: Proc. Adv. Neural Inf. Process. Syst. – ident: ref52 doi: 10.1109/TIP.2003.819861 – volume: 43 start-page: 2959 issue: 12 year: 1995 ident: ref53 article-title: Image quality measures and their performance publication-title: IEEE Trans. Commun. doi: 10.1109/26.477498 – ident: ref59 doi: 10.1109/TPAMI.2011.109 – ident: ref29 doi: 10.1109/TCI.2021.3100986 – ident: ref18 doi: 10.1109/TIP.2018.2887342 – ident: ref28 doi: 10.1109/TCSVT.2021.3056725 – year: 2022 ident: ref33 article-title: TGFuse: An infrared and visible image fusion approach based on transformer and generative adversarial network publication-title: arXiv:2201.10147 – ident: ref4 doi: 10.1016/j.inffus.2008.08.008 – ident: ref1 doi: 10.1109/TMM.2020.2978640 – ident: ref20 doi: 10.1109/TPAMI.2020.3012548 – year: 2018 ident: ref38 article-title: BERT: Pre-training of deep bidirectional transformers for language understanding publication-title: arXiv:1810.04805 – ident: ref56 doi: 10.1109/TMM.2020.3037526 – ident: ref16 doi: 10.1016/j.ins.2017.09.010 – ident: ref15 doi: 10.1016/j.inffus.2017.05.006
SSID	ssj0014507
Score	2.7041419
Snippet	Infrared and visible image fusion is aims to generate a composite image that can simultaneously describe the salient target in the infrared image and texture...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	5413
SubjectTerms	Computer vision Dynamic transformer Feature extraction Image fusion Image segmentation infrared image Infrared imagery Roads Task analysis Thermal radiation Training Transformers Y-shape network
Title	YDTR: Infrared and Visible Image Fusion via Y-Shape Dynamic Transformer
URI	https://ieeexplore.ieee.org/document/9834137 https://www.proquest.com/docview/2884893608
Volume	25
WOSCitedRecordID	wos001097340300057&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: 1941-0077 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014507 issn: 1520-9210 databaseCode: RIE dateStart: 19990101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB5q8aAHq61itcoevAjGbtIku-tNrNUeWkSrtKeQTXaxUNPS1-93No-iKIKXkMMuhPkyr52d-QAuqEaf4cUScxPBLVcz1xLc8y3GEWPZotrVcUo2wfp9PhyKpxJcbXphlFLp5TN1bV7TWn48jVbmqKwpuLG5bAu2GGNZr9amYuB6aWs0uiNqCcxjipIkFc1Br4eJoONgfiqMP_rmglJOlR-GOPUuncr_vmsf9vIoktxmsB9ASSVVqBQMDSRX2Crsfhk3WIOHUXvwfEO6iZ6ba-ckTGLyNkadmCjS_UDDQjorc3hG1uOQjKyX93CmSDujrCeDIsJV80N47dwP7h6tnEjBihxhLy0bBS-kJ6Rr01B4IWbEnPrS1PRi1D9HMiaUTam2FUYrUkYRF46DD21KuhFrHUE5mSbqGAiX3OMIooy0j7qvQ9-NlQ69luKhF8e6Ds1CtkGUTxk3ZBeTIM02qAgQjcCgEeRo1OFys2OWTdj4Y23NSH-zLhd8HRoFfEGugovA4dwM1vEpP_l91ynsGO747DylAeXlfKXOYDtaL8eL-Xn6d30C3pnJug
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB7qA9SDj6pYn3vwIhi7SbPJrjdRa4u2iEZpTyGb7GKhRqltf7-zeRRFEbyEHHYhzJd57ezMB3BMNfoMlkjMTQS3XO27luDMs3yOGMsG1a5OMrIJv9vlvZ64r8DprBdGKZVdPlNn5jWr5Sdv8cQcldUFNzbXn4MF5rqOnXdrzWoGLsuao9EhUUtgJlMWJamoB50OpoKOgxmqMB7pmxPKWFV-mOLMvzTX_vdl67BaxJHkIgd-AyoqrcJaydFACpWtwsqXgYObcNO_Ch7OSTvVI3PxnERpQp4HqBVDRdqvaFpIc2KOz8h0EJG-9fgSvStylZPWk6CMcdVoC56a18FlyyqoFKzYEfbYslH0QjIhXZtGgkWYE3PqSVPVS1ADHen7QtmUalthvCJlHHPhOPjQpqgb-41tmE_fUrUDhEvOOMIoY-2h9uvIcxOlI9ZQPGJJomtQL2UbxsWccUN3MQyzfIOKENEIDRphgUYNTmY73vMZG3-s3TTSn60rBF-D_RK-sFDCj9Dh3IzW8Sjf_X3XESy1gs5deNfu3u7BsmGSz09X9mF-PJqoA1iMp-PBx-gw-9M-AYmGzQE
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=YDTR%3A+Infrared+and+Visible+Image+Fusion+via+Y-Shape+Dynamic+Transformer&rft.jtitle=IEEE+transactions+on+multimedia&rft.au=Tang%2C+Wei&rft.au=He%2C+Fazhi&rft.au=Liu%2C+Yu&rft.date=2023&rft.issn=1520-9210&rft.eissn=1941-0077&rft.volume=25&rft.spage=5413&rft.epage=5428&rft_id=info:doi/10.1109%2FTMM.2022.3192661&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TMM_2022_3192661
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1520-9210&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1520-9210&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1520-9210&client=summon