{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T20:28:09Z","timestamp":1773260889276,"version":"3.50.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation (IITP) Grant funded by the Korea Government Ministry of Science and ICT of South Korea (Interoperable Digital Human","award":["RS-2023-00229451"],"award-info":[{"award-number":["RS-2023-00229451"]}]},{"name":"Sookmyung Women\u2019s University Research Grants","award":["1-2303-2015"],"award-info":[{"award-number":["1-2303-2015"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3361283","type":"journal-article","created":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T18:48:40Z","timestamp":1706813320000},"page":"21723-21736","source":"Crossref","is-referenced-by-count":8,"title":["Deep Transformer Based Video Inpainting Using Fast Fourier Tokenization"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3319-7797","authenticated-orcid":false,"given":"Taewan","family":"Kim","sequence":"first","affiliation":[{"name":"Data Science Major, Dongduk Women’s University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinwoo","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0920-7281","authenticated-orcid":false,"given":"Heeseok","family":"Oh","sequence":"additional","affiliation":[{"name":"Department of Applied AI, Hansung University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7622-0817","authenticated-orcid":false,"given":"Jiwoo","family":"Kang","sequence":"additional","affiliation":[{"name":"Division of Artificial Intelligence Engineering, Sookmyung Women’s University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.330"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.141"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982398"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00916"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00594"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015232"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00451"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00450"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"8","key":"ref10","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref11","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref12","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref13","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref14","first-page":"12873","article-title":"Taming transformers for highresolution image synthesis","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Esser"},{"key":"ref15","article-title":"TransGAN: Two pure transformers can make one strong GAN, and that can scale up","author":"Jiang","year":"2021","journal-title":"arXiv:2102.07074"},{"key":"ref16","article-title":"Bridging global context interactions for high-fidelity image completion","author":"Zheng","year":"2021","journal-title":"arXiv:2104.00845"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01270"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref19","article-title":"Lite transformer with long-short range attention","author":"Wu","year":"2020","journal-title":"arXiv:2004.11886"},{"key":"ref20","article-title":"LambdaNetworks: Modeling long-range interactions without attention","author":"Bello","year":"2021","journal-title":"arXiv:2102.08602"},{"key":"ref21","first-page":"4479","article-title":"Fast Fourier convolution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chi"},{"key":"ref22","first-page":"2149","article-title":"Resolutionrobust large mask in painting with Fourier convolutions","volume-title":"Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis. (WACV)","author":"Suvorov"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344972"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1017\/S0956792502004904"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/83.935036"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531330"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5201\/ipol.2017.189"},{"issue":"4","key":"ref28","first-page":"1","article-title":"Image completion using planar structure guidance","volume":"33","author":"Huang","year":"2014","journal-title":"ACM Trans. Graph."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073659"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00158"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01162"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978501"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1901.00212"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00027"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3075039"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00778"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.833105"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.60"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2839351"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00384"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_42"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3034422"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2437111"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_31"},{"key":"ref47","article-title":"Decoupled spatial\u2013temporal transformer for video inpainting","author":"Liu","year":"2021","journal-title":"arXiv:2104.06637"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-00551-4_4"},{"key":"ref49","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref55","article-title":"Learnable gated temporal shift module for deep video inpainting","author":"Chang","year":"2019","journal-title":"arXiv:1907.01131"},{"key":"ref56","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref57","article-title":"Spectral normalization for generative adversarial networks","author":"Miyato","year":"2018","journal-title":"arXiv:1802.05957"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_5"},{"key":"ref59","article-title":"YouTube-VOS: A large-scale video object segmentation benchmark","author":"Xu","year":"2018","journal-title":"arXiv:1809.03327"},{"key":"ref60","article-title":"The 2018 Davis challenge on video object segmentation","author":"Caelles","year":"2018","journal-title":"arXiv:1803.00557"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01618"},{"key":"ref62","article-title":"Video-to-video synthesis","author":"Wang","year":"2018","journal-title":"arXiv:1808.06601"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10418237.pdf?arnumber=10418237","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T04:37:15Z","timestamp":1725079035000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10418237\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3361283","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}