{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T16:19:08Z","timestamp":1762273148703,"version":"3.37.3"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Chung-Ang University Graduate Research Scholarship in 2022"},{"DOI":"10.13039\/501100003725","name":"Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education","doi-asserted-by":"publisher","award":["NRF-2022R1C1C1008534"],"award-info":[{"award-number":["NRF-2022R1C1C1008534"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute for Information and Communications Technology Planning and Evaluation (IITP) through the Korea Government (MSIT)","award":["2021-0-01341"],"award-info":[{"award-number":["2021-0-01341"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3324545","type":"journal-article","created":{"date-parts":[[2023,10,13]],"date-time":"2023-10-13T18:07:33Z","timestamp":1697220453000},"page":"115644-115653","source":"Crossref","is-referenced-by-count":3,"title":["Domain-Adaptive Vision Transformers for Generalizing Across Visual Domains"],"prefix":"10.1109","volume":"11","author":[{"given":"Yunsung","family":"Cho","sequence":"first","affiliation":[{"name":"Graduate School of Advanced Imaging Science, Multimedia and Film, Chung-Ang University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jungmin","family":"Yun","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Chung-Ang University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junehyoung","family":"Kwon","sequence":"additional","affiliation":[{"name":"Graduate School of Advanced Imaging Science, Multimedia and Film, Chung-Ang University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2114-0120","authenticated-orcid":false,"given":"Youngbin","family":"Kim","sequence":"additional","affiliation":[{"name":"Graduate School of Advanced Imaging Science, Multimedia and Film, Chung-Ang University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3157441"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00621"},{"key":"ref56","article-title":"CAT: Cross attention in vision transformer","author":"lin","year":"2021","journal-title":"arXiv 2106 05786"},{"key":"ref15","first-page":"666","article-title":"Domain generalization using shape representation","author":"nazari","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00682"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2967597"},{"key":"ref53","first-page":"13165","article-title":"MST: Masked self-supervised transformer for visual representation","volume":"34","author":"li","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref52","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","author":"zhang","year":"2022","journal-title":"arXiv 2203 03605"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.09.046"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref10","first-page":"9638","article-title":"Aggregating from multiple target-shifted sources","author":"shui","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref17","article-title":"Frustratingly simple domain generalization via image stylization","author":"somavarapu","year":"2020","journal-title":"arXiv 2006 11207"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00876"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00024"},{"key":"ref18","first-page":"23519","article-title":"Towards a theoretical framework of out-of-distribution generalization","volume":"34","author":"ye","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","article-title":"Image as a foreign language: BEiT pretraining for all vision and vision-language tasks","author":"wang","year":"2022","journal-title":"arXiv 2208 10442"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5615"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-12939-2_14"},{"key":"ref45","first-page":"16096","article-title":"Domain generalization via entropy regularization","volume":"33","author":"zhao","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref48","article-title":"In search of lost domain generalization","author":"gulrajani","year":"2020","journal-title":"arXiv 2007 01434"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475434"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2988928"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3360309"},{"key":"ref49","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00948"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794443"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06080-w"},{"key":"ref4","article-title":"SeMask: Semantically masked transformers for semantic segmentation","author":"jain","year":"2021","journal-title":"arXiv 2112 12782"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00210"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.534"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01303"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00583"},{"key":"ref79","article-title":"Gradient matching for domain generalization","author":"shi","year":"2021","journal-title":"arXiv 2104 09937"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87234-2_10"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01739-w"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref31","article-title":"End-to-end open-domain question answering with BERTserini","author":"yang","year":"2019","journal-title":"arXiv 1902 01718"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.498"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.591"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"ref32","article-title":"An image is worth 16 × 16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.572"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_5"},{"key":"ref1","first-page":"3965","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","volume":"34","author":"dai","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref70","first-page":"642","article-title":"UniLMv2: Pseudo-masked language models for unified language model pre-training","author":"bao","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref73","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"goyal","year":"2017","journal-title":"arXiv 1706 02677"},{"key":"ref72","first-page":"1","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3178128"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref23","first-page":"25878","article-title":"Generalization bounds for meta-learning: An information-theoretic analysis","volume":"34","author":"chen","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref67","article-title":"Layer normalization","author":"lei ba","year":"2016","journal-title":"arXiv 1607 06450"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"radford","key":"ref26"},{"key":"ref25","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3104379"},{"key":"ref64","first-page":"12992","article-title":"Glance-and-gaze vision transformer","volume":"34","author":"yu","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746053"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109115"},{"key":"ref66","first-page":"15908","article-title":"Transformer in transformer","volume":"34","author":"han","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.609"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"ref28","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"brown","year":"2020","journal-title":"Proc Adv Neur Inf Process Sys"},{"key":"ref27","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref29","article-title":"Incorporating BERT into neural machine translation","author":"zhu","year":"2020","journal-title":"arXiv 2002 06823"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108499"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10285058.pdf?arnumber=10285058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:40:24Z","timestamp":1699904424000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10285058\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3324545","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2023]]}}}