{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T09:50:47Z","timestamp":1780653047262,"version":"3.54.1"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korean Government [Ministry of Science and ICT (MSIT)]","award":["2022R1F1A1074402"],"award-info":[{"award-number":["2022R1F1A1074402"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tcsvt.2023.3289170","type":"journal-article","created":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T18:53:47Z","timestamp":1687805627000},"page":"770-785","source":"Crossref","is-referenced-by-count":160,"title":["Cross-Modal Transformers for Infrared and Visible Image Fusion"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5690-7125","authenticated-orcid":false,"given":"Seonghyun","family":"Park","sequence":"first","affiliation":[{"name":"Department of Multimedia Engineering, Dongguk University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0067-0285","authenticated-orcid":false,"given":"An Gia","family":"Vien","sequence":"additional","affiliation":[{"name":"Department of Multimedia Engineering, Dongguk University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9329-7365","authenticated-orcid":false,"given":"Chul","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Multimedia Engineering, Dongguk University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.02.004"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2021.108036"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00060"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3075747"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.06.008"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2010.03.002"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2354534"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2015.11.003"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.08.066"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2019.2956873"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71607-7_59"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2975984"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2012.2217493"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2014.09.019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.09.010"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2014.09.004"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2015.07.003"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2022.3151472"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.10.007"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2020.2965304"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2020.3022438"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3056645"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2021.3100986"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/487"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3109895"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2887342"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.02.023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3012548"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3056725"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3075745"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3043125"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3109818"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3226564"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.09.004"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3054584"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3206807"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2977573"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2021.3119954"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00571"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2997127"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01107"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3175055"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3263113"},{"key":"ref45","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformer for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105686"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3191664"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3192661"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897280"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897993"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3234340"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.02.008"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref54","first-page":"28522","article-title":"ViTAE: Vision transformer advanced by exploring intrinsic inductive bias","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xu"},{"key":"ref55","article-title":"CMX: Cross-modal fusion for RGB-X semantic segmentation with transformers","author":"Zhang","year":"2022","journal-title":"arXiv:2203.04838"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3241196"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3202563"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67070-2_2"},{"key":"ref59","first-page":"3","article-title":"Attention is all you need","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00769"},{"key":"ref61","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Nagrani"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.08.022"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"ref64","volume-title":"TNO Image Fusion Dataset","author":"Toet","year":"2014"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3063604"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref67","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref68","first-page":"7537","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Tancik"},{"key":"ref69","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1049\/el:20000267"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICAICT.2014.7036000"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2442920"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.aeue.2015.09.004"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"issue":"1","key":"ref76","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1023\/A:1014573219977","article-title":"A taxonomy and evaluation of dense twoframe stereo correspondence algorithms","volume":"47","author":"Scharstein","year":"2002","journal-title":"Int. J. Comput. Vis."},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00262"},{"key":"ref78","first-page":"10096","article-title":"EfficientNetv2: Smaller models and faster training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref79","article-title":"YOLOv4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020","journal-title":"arXiv:2004.10934"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10422872\/10163247.pdf?arnumber=10163247","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:10:05Z","timestamp":1736453405000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10163247\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":81,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3289170","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}