{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T18:37:26Z","timestamp":1775932646521,"version":"3.50.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2018YFB1004600"],"award-info":[{"award-number":["2018YFB1004600"]}]},{"name":"National Key R&D Program of China","award":["NSFC 61733007"],"award-info":[{"award-number":["NSFC 61733007"]}]},{"name":"National Key R&D Program of China","award":["NSFC 61573160"],"award-info":[{"award-number":["NSFC 61573160"]}]},{"name":"National Program for Support of Top-notch Young Professionals"},{"name":"HUST Academic Frontier Youth Team"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2019,9,1]]},"DOI":"10.1109\/tpami.2018.2848939","type":"journal-article","created":{"date-parts":[[2018,6,25]],"date-time":"2018-06-25T23:38:05Z","timestamp":1529969885000},"page":"2035-2048","source":"Crossref","is-referenced-by-count":685,"title":["ASTER: An Attentional Scene Text Recognizer with Flexible Rectification"],"prefix":"10.1109","volume":"41","author":[{"given":"Baoguang","family":"Shi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6078-6100","authenticated-orcid":false,"given":"Mingkun","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Xinggang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Pengyuan","family":"Lyu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6564-4796","authenticated-orcid":false,"given":"Cong","family":"Yao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3449-5940","authenticated-orcid":false,"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-015-4488-0"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.451"},{"key":"ref39","first-page":"21","article-title":"SSD: single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref38","first-page":"4161","article-title":"TextBoxes: A fast text detector with a single deep neural network","author":"liao","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref33","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref30","first-page":"148","article-title":"Perspective correction methods for camera based document analysis","author":"jagannathan","year":"2005","journal-title":"Proc Int Workshop Camera-Based Document Anal Recognit"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.560"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.245"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.516"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref60","first-page":"1457","article-title":"End-to-end scene text recognition","author":"wang","year":"2011","journal-title":"Int Conf Comput Vis IEEE Int Conf Comput Vis"},{"key":"ref62","first-page":"3304","article-title":"End-to-end text recognition with convolutional neural networks","author":"wang","year":"2012","journal-title":"Proc Int Conf Pattern Recognit"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_43"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.126"},{"key":"ref28","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/458"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2353813"},{"key":"ref66","first-page":"1083","article-title":"Detecting texts of arbitrary orientations in natural images","author":"yao","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref29","first-page":"512","article-title":"Deep features for text spotting","author":"jaderberg","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.515"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366765"},{"key":"ref69","article-title":"ADADELTA: An adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"arXiv preprint arXiv 1212 5701"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2339814"},{"key":"ref1","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc 12th USENIX Symp Operating Syst Des Implementation"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref21","first-page":"3501","article-title":"Reading scene text in deep convolutional sequences","author":"he","year":"2016","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref24","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","author":"jaderberg","year":"2014","journal-title":"NIPS Deep Learning Workshop"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref25","article-title":"Deep structured output learning for unconstrained text recognition","author":"jaderberg","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"ref59","first-page":"334","article-title":"Gated recurrent convolution neural network for OCR","author":"wang","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref58","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"NIPS"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.10.016"},{"key":"ref56","first-page":"35","article-title":"Accurate scene text recognition based on recurrent neural network","author":"su","year":"2014","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.452"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0793-6"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/34.506792"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.543"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2005.01.003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref13","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc Advances Neural Inform Process Syst (NIPS)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"ref15","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298914"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.137"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12242","article-title":"SEE: Towards semi-supervised end-to-end scene text recognition","author":"bartz","year":"2018","journal-title":"Proc Thirty-Second (AAAI) Conf Artificial Intelligence"},{"key":"ref3","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/34.993558"},{"key":"ref5","article-title":"STN-OCR: A single neural network for text detection and text recognition","author":"bartz","year":"2017","journal-title":"arXiv preprint arXiv 1707 08385"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/34.24792"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.102"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.76"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.242"},{"key":"ref46","first-page":"770","article-title":"A method for text localization and recognition in real-world images","author":"neumann","year":"2010","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.01.002"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2496234"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-004-0134-3"},{"key":"ref41","first-page":"971","article-title":"Document flattening through grid modeling and regularization","author":"lu","year":"2006","journal-title":"Proc 18th Int Conf Pattern Recognit"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247990"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2004.02.006"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8787855\/08395027.pdf?arnumber=8395027","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T10:05:51Z","timestamp":1661508351000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8395027\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,1]]},"references-count":72,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2018.2848939","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":[[2019,9,1]]}}}