{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:16:31Z","timestamp":1755839791897,"version":"3.37.3"},"reference-count":48,"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\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012164","name":"National High Quality Program","doi-asserted-by":"publisher","award":["TC220H07D"],"award-info":[{"award-number":["TC220H07D"]}],"id":[{"id":"10.13039\/501100012164","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB2902002"],"award-info":[{"award-number":["2022YFB2902002"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3509678","type":"journal-article","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T18:41:02Z","timestamp":1733164862000},"page":"182883-182893","source":"Crossref","is-referenced-by-count":1,"title":["PuzText: Self-Supervised Learning of Permuted Texture Representation for Multilingual Text Recognition"],"prefix":"10.1109","volume":"12","author":[{"given":"Minjun","family":"Lu","sequence":"first","affiliation":[{"name":"School of Communication and Information Engineering, Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1905-6269","authenticated-orcid":false,"given":"Shugong","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Communication and Information Engineering, Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuefan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Communication and Information Engineering, Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"MaskOCR: Text recognition with masked encoder\u2013decoder pretraining","author":"Lyu","year":"2022","journal-title":"arXiv:2206.00311"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00702"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03728-5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86337-1_3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01505"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547784"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.12.023"},{"key":"ref10","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":"ref11","first-page":"4203","article-title":"Focal modulation networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Jianwei"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00986"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2646371"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04241-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_19"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3025769"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/app13031750"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-023-06450-6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-06430-2_40"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00452"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-21074-8_11"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-27818-1_12"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01709"},{"key":"ref26","article-title":"LayoutXLM: Multimodal pre-training for multilingual visually-rich document understanding","author":"Xu","year":"2021","journal-title":"arXiv:2104.08836"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref27"},{"issue":"8","key":"ref28","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00784"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3107437"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.10-7\/s10032-004-0134-3"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.76"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"ref41","article-title":"Benchmarking Chinese text recognition: Datasets, baselines, and an empirical study","author":"Yu","year":"2021","journal-title":"arXiv:2112.15093"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00130"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_9"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00281"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107980"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.01.020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01185"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10772094.pdf?arnumber=10772094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T06:35:55Z","timestamp":1733985355000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10772094\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3509678","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}