{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T04:57:31Z","timestamp":1769921851931,"version":"3.49.0"},"reference-count":100,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Artificial Intelligence Institute at Shanghai Jiao Tong University"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322604"],"award-info":[{"award-number":["62322604"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176159"],"award-info":[{"award-number":["62176159"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tpami.2025.3533737","type":"journal-article","created":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T18:40:04Z","timestamp":1739472004000},"page":"3546-3562","source":"Crossref","is-referenced-by-count":2,"title":["CCDPlus: Towards Accurate Character to Character Distillation for Text Recognition"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3346-8315","authenticated-orcid":false,"given":"Tongkun","family":"Guan","sequence":"first","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1235-598X","authenticated-orcid":false,"given":"Wei","family":"Shen","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-3322","authenticated-orcid":false,"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72967-6_16"},{"key":"ref2","article-title":"Qwen-VL: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01479"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.543"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6891"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19971"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01467"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6903"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_27"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_18"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01198"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00281"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110244"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3156390"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412914"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00313"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547784"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01505"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20062"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_24"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01784"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2024.01.008"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01372"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02679"},{"key":"ref34","article-title":"How control information influences multilingual text image generation and editing?","author":"Zhang","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref36","article-title":"A critical analysis of self-supervision, or what we can learn from a single image","author":"Asano","year":"2019"},{"key":"ref37","first-page":"4182","article-title":"Data-efficient image recognition with contrastive predictive coding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Henaff"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref39","first-page":"1","article-title":"Image BERT pre-training with online tokenizer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00111"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01467"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.102"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.264"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.49"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.01.020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00924"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16442"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_9"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2023.3237002"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00582"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475469"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_12"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475238"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.05.014"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1090\/psapm\/040\/1059485"},{"key":"ref64","article-title":"MaskOCR: Scene text recognition with masked vision-language pre-training","author":"Lyu","year":"2022","journal-title":"arXiv:2206.00311"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/85"},{"key":"ref66","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","author":"Jaderberg","year":"2014"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.76"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01878"},{"key":"ref74","article-title":"Benchmarking chinese text recognition: Datasets, baselines, and an empirical study","author":"Yu","year":"2021"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01187"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref77","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00481"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00035"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00102"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_20"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28575"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20245"},{"key":"ref84","first-page":"322","article-title":"Levenshtein OCR","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Cheng"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28402"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00130"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_26"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/124"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01880-0"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/189"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01354"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01097"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681390"},{"key":"ref94","article-title":"COCO-text: Dataset and benchmark for text detection and recognition in natural images","author":"Veit","year":"2016"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.02.002"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.157"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4235-6"},{"key":"ref98","article-title":"GPT-4V(ision) system card","year":"2023"},{"key":"ref99","article-title":"Exploring OCR capabilities of GPT-4v(ision): A quantitative and in-depth evaluation","author":"Shi","year":"2023"},{"key":"ref100","article-title":"Platypus: A generalized specialist model for reading text in various forms","author":"Wang","year":"2024"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10958761\/10887029.pdf?arnumber=10887029","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T17:13:58Z","timestamp":1744305238000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887029\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":100,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3533737","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}