{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T17:56:29Z","timestamp":1793123789738,"version":"4.5.0"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62272059"],"award-info":[{"award-number":["62272059"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF0904800"],"award-info":[{"award-number":["2023YFF0904800"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20230484406"],"award-info":[{"award-number":["20230484406"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Innovation Research Group Project of NSFC","doi-asserted-by":"publisher","award":["61921003"],"award-info":[{"award-number":["61921003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"111 Project","doi-asserted-by":"publisher","award":["B18008"],"award-info":[{"award-number":["B18008"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tcsvt.2024.3353932","type":"journal-article","created":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T16:35:52Z","timestamp":1705336552000},"page":"5546-5559","source":"Crossref","is-referenced-by-count":19,"title":["SwinIT: Hierarchical Image-to-Image Translation Framework Without Cycle Consistency"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5078-3302","authenticated-orcid":false,"given":"Jin","family":"Liu","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5276-4366","authenticated-orcid":false,"given":"Huiyuan","family":"Fu","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8639-3818","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Stony Brook University, Stony Brook, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7199-5047","authenticated-orcid":false,"given":"Huadong","family":"Ma","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3130158"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3206807"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2988895"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3071191"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3188433"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3078560"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01104"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3072171"},{"key":"ref11","article-title":"VCGAN: Video colorization with hybrid generative adversarial network","author":"Zhao","year":"2021","journal-title":"arXiv:2104.12357"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.310"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3005311"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01284-z"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01585"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01171"},{"key":"ref21","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref23","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01778"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_13"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413656"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2938347"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00319"},{"key":"ref32","article-title":"U-GAT-IT: Unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation","author":"Kim","year":"2019","journal-title":"arXiv:1907.10830"},{"key":"ref33","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014","journal-title":"arXiv:1411.1784"},{"key":"ref34","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arjovsky"},{"key":"ref35","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford","year":"2015","journal-title":"arXiv:1511.06434"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00583"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2970104"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00243"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00909"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073703"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2976573"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00938"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475608"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00753"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3048629"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00600"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00658"},{"key":"ref50","first-page":"465","article-title":"Toward multimodal image-to-image translation","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5555\/3305381"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref54","first-page":"1","article-title":"Multi-mapping image-to-image translation via learning disentanglement","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00380"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2950198"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3037528"},{"key":"ref59","first-page":"4055","article-title":"Image transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parmar"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref61","article-title":"Transgan: Two pure transformers can make one strong gan, and that can scale up","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01102"},{"key":"ref63","article-title":"InstaGAN: Instance-aware image-to-image translation","author":"Mo","year":"2018","journal-title":"arXiv:1812.10889"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01557-6"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01775"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19924"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530736"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.168"},{"key":"ref72","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref73","article-title":"Spectral normalization for generative adversarial networks","author":"Miyato","year":"2018","journal-title":"arXiv:1802.05957"},{"key":"ref74","article-title":"BDD100K: A diverse driving dataset for heterogeneous multitask learning","author":"Yu","year":"2018","journal-title":"arXiv:1805.04687"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40602-7_39"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref78","first-page":"1","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref80","first-page":"2234","article-title":"Improved techniques for training GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Salimans"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref82","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10582818\/10399932.pdf?arnumber=10399932","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T14:01:26Z","timestamp":1722348086000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10399932\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":84,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3353932","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}