{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T04:57:51Z","timestamp":1785128271341,"version":"3.55.0"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2017,11,1]],"date-time":"2017-11-01T00:00:00Z","timestamp":1509494400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China (NSFC)","doi-asserted-by":"publisher","award":["61573160"],"award-info":[{"award-number":["61573160"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China (NSFC)","doi-asserted-by":"publisher","award":["61222308"],"award-info":[{"award-number":["61222308"]}],"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":[[2017,11,1]]},"DOI":"10.1109\/tpami.2016.2646371","type":"journal-article","created":{"date-parts":[[2016,12,29]],"date-time":"2016-12-29T19:27:51Z","timestamp":1483039671000},"page":"2298-2304","source":"Crossref","is-referenced-by-count":2524,"title":["An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition"],"prefix":"10.1109","volume":"39","author":[{"given":"Baoguang","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-012-0004-6"},{"key":"ref38","article-title":"End-to-end text recognition with hybrid HMM maxout models","author":"alsharif","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref31","first-page":"1457","article-title":"End-to-end scene text recognition","author":"wang","year":"0","journal-title":"Proc IEEE Conf Comput Vis"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-004-0134-3"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.87"},{"key":"ref36","article-title":"Torch7: A Matlab-like environment for machine learning","author":"collobert","year":"0","journal-title":"NIPS Workshop BigLearn"},{"key":"ref35","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref34","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1007\/s11704-015-4488-0","article-title":"Scene text detection and recognition: Recent advances and future trends","volume":"10","author":"zhu","year":"2016","journal-title":"Frontiers Comput Sci"},{"key":"ref40","year":"2015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2339814"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0793-6"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.516"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2555080"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298914"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2353813"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301268"},{"key":"ref18","article-title":"Deep structured output learning for unconstrained text recognition","author":"jaderberg","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref19","first-page":"512","article-title":"Deep features for text spotting","author":"jaderberg","year":"0","journal-title":"Proc Euro Conf Comput Vis"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"696","DOI":"10.7551\/mitpress\/4943.003.0042","article-title":"Learning representations by back-propagating errors","author":"rumelhart","year":"1988","journal-title":"Neurocomputing Foundations of Research"},{"key":"ref4","first-page":"3304","article-title":"End-to-end text recognition with convolutional neural networks","author":"wang","year":"0","journal-title":"Proc Int Conf Pattern Recog"},{"key":"ref27","article-title":"ADADELTA: An adaptive learning rate method","volume":"abs 1212 5701","author":"zeiler","year":"0","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref29","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","author":"jaderberg","year":"0","journal-title":"NIPS *2010 Workshop on Deep Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.102"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16865-4_3"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.137"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366765"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"ref22","first-page":"115","article-title":"Learning precise timing with LSTM recurrent networks","volume":"3","author":"gers","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref42","year":"2014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref41","year":"2015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/362003.362025"},{"key":"ref25","year":"2011"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8055017\/07801919.pdf?arnumber=7801919","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T23:18:56Z","timestamp":1749856736000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7801919\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11,1]]},"references-count":42,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2016.2646371","relation":{},"ISSN":["0162-8828","2160-9292"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,11,1]]}}}