{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:20:41Z","timestamp":1772907641178,"version":"3.50.1"},"reference-count":82,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tpami.2022.3230962","type":"journal-article","created":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T18:37:51Z","timestamp":1675967871000},"page":"1-14","source":"Crossref","is-referenced-by-count":17,"title":["Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3562-3094","authenticated-orcid":false,"given":"Chuhui","family":"Xue","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8681-0471","authenticated-orcid":false,"given":"Jiaxing","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}]},{"given":"Wenqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Bytedance Inc., China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6766-2506","authenticated-orcid":false,"given":"Shijian","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8373-2597","authenticated-orcid":false,"given":"Changhu","family":"Wang","sequence":"additional","affiliation":[{"name":"Bytedance Inc., China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2570-9118","authenticated-orcid":false,"given":"Song","family":"Bai","sequence":"additional","affiliation":[{"name":"Bytedance Inc., China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref2","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","author":"Jaderberg","year":"2014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_16"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00377"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1402_1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16865-4_3"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10465"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00163"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00670"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.245"},{"key":"ref16","article-title":"Scene text recognition with sliding convolutional character models","author":"Yin","year":"2017"},{"key":"ref17","article-title":"Reading scene text with attention convolutional sequence modeling","author":"Gao","year":"2017"},{"key":"ref18","article-title":"Spatial transformer networks","author":"Jaderberg","year":"2015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/34.24792"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.43"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.452"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00216"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00924"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12252"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00584"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01198"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.010"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2937086"},{"key":"ref30","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01354"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01144"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00285"},{"key":"ref36","first-page":"158","article-title":"PlugNet: Degradation aware scene text recognition supervised by a pluggable super-resolution unit","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Yan"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_38"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01467"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01468"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6891"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018714"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/458"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12246"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054135"},{"key":"ref46","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"ref47","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref48","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref49","first-page":"10 347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref51","article-title":"All tokens matter: Token labeling for training better vision transformers","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref54","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"ref57","article-title":"Pix2seq: A language modeling framework for object detection","author":"Chen","year":"2021"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref59","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00583"},{"key":"ref62","article-title":"Colorization transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kumar"},{"key":"ref63","first-page":"4055","article-title":"Image transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parmar"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_44"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00481"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.157"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.02.002"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.76"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247990"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.10-7\/s10032-004-0134-3"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.58837\/chula.the.2019.160"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00035"},{"key":"ref80","article-title":"2D attentional irregular scene text recognizer","author":"Lyu","year":"2019"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6903"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_36"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/10041804.pdf?arnumber=10041804","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T19:17:25Z","timestamp":1709407045000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10041804\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3230962","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]]}}}