{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:14:19Z","timestamp":1784301259364,"version":"3.55.0"},"reference-count":91,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102384"],"award-info":[{"award-number":["62102384"]}],"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":["62121002"],"award-info":[{"award-number":["62121002"]}],"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":["62022076"],"award-info":[{"award-number":["62022076"]}],"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":["U1936210"],"award-info":[{"award-number":["U1936210"]}],"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":["62222212"],"award-info":[{"award-number":["62222212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,6,1]]},"DOI":"10.1109\/tpami.2022.3223908","type":"journal-article","created":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T19:57:43Z","timestamp":1669319863000},"page":"7123-7141","source":"Crossref","is-referenced-by-count":77,"title":["ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3100-3664","authenticated-orcid":false,"given":"Shancheng","family":"Fang","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5739-8126","authenticated-orcid":false,"given":"Zhendong","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6249-5315","authenticated-orcid":false,"given":"Hongtao","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0228-6220","authenticated-orcid":false,"given":"Yuxin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1204-0512","authenticated-orcid":false,"given":"Chenggang","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Automation, Hangzhou Dianzi University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366765"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01369-0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01144"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3095916"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3107437"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_34"},{"key":"ref10","article-title":"Deep structured output learning for unconstrained text recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jaderberg"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01354"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_41"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.245"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00130"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-65"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6903"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.543"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.143"},{"key":"ref24","article-title":"2D attentional irregular scene text recognizer","author":"Lyu","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"ref27","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.472"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10465"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.10.016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6735"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2937086"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6891"},{"key":"ref36","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","volume-title":"Proc. NIPS Deep Learn. Workshop","author":"Jaderberg"},{"key":"ref37","article-title":"A simple and robust convolutional-attention network for irregular text recognition","author":"Wang","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.452"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00584"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/458"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018714"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00216"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00924"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240571"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_9"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.137"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01467"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475238"},{"key":"ref50","first-page":"5144","article-title":"Non-autoregressive machine translation with disentangled context transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kasai"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.560"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.242"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00595"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00527"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00480"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3077555"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_6"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00917"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6896"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6864"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_30"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00922"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16348"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16383"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00481"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref68","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.76"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref79","article-title":"Uber-Text: A large-scale dataset for optical character recognition from street-level imagery","volume-title":"Proc. Conf. Scene Understanding Workshop - Conf. Comput. Vis. Pattern Recognit.","author":"Zhang"},{"key":"ref80","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-019-00334-z"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.02.002"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00253"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.237"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00250"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"ref88","first-page":"21285","article-title":"Towards theoretically understanding why SGD generalizes better than ADAM in deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref90","article-title":"Why ADAM beats SGD for attention models","author":"Zhang","year":"2019"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01388-x"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09960802.pdf?arnumber=9960802","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T09:28:34Z","timestamp":1726046914000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9960802\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":91,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3223908","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":[[2023,6,1]]}}}