{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T23:52:24Z","timestamp":1771458744423,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1109\/icip.2019.8803203","type":"proceedings-article","created":{"date-parts":[[2019,8,26]],"date-time":"2019-08-26T19:32:48Z","timestamp":1566847968000},"page":"1945-1949","source":"Crossref","is-referenced-by-count":20,"title":["Text Recognition in Images Based on Transformer with Hierarchical Attention"],"prefix":"10.1109","author":[{"given":"Yiwei","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shilin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition","author":"shi","year":"2016","journal-title":"IEEE TPAMI"},{"key":"ref11","first-page":"3501","article-title":"Reading Scene Text in Deep Convolutional Sequences","author":"he","year":"2016","journal-title":"AAAI"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref13","first-page":"2017","article-title":"Spatial Transformer Networks","author":"jaderberg","year":"2015","journal-title":"NIPS"},{"key":"ref14","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"devlin","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","article-title":"An Efficient End-to-End Neural Model for Handwritten Text Recognition","author":"chowdhury","year":"2018"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref18","first-page":"1457","article-title":"End-to-end scene text recognition","author":"wang","year":"2011","journal-title":"ICCV"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.245"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.452"},{"key":"ref27","article-title":"Deep Structured Output Learning for Unconstrained Text Recognition","author":"jaderberg","year":"2015","journal-title":"ICLRE"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00584"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.543"},{"key":"ref5","article-title":"ASTER: An Attentional Scene Text Recognizer with Flexible Rectification","author":"shi","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref8","first-page":"591","article-title":"Word Spotting in the Wild","author":"wang","year":"2010","journal-title":"ECCV"},{"key":"ref7","first-page":"1457","article-title":"End-to-end scene text recognition","author":"wang","year":"2011","journal-title":"ICCV"},{"key":"ref2","article-title":"Neural Machine Translation by Jointly Learning to Align and Translate","author":"bahdanau","year":"2015","journal-title":"ICLRE"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"ref1","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","first-page":"682","article-title":"S. Wong, and R. Young. ICDAR 2003 robust reading competitions","author":"lucas","year":"2003","journal-title":"ICDAR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.76"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref25","article-title":"Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition","author":"jaderberg","year":"2014"}],"event":{"name":"2019 IEEE International Conference on Image Processing (ICIP)","location":"Taipei, Taiwan","start":{"date-parts":[[2019,9,22]]},"end":{"date-parts":[[2019,9,25]]}},"container-title":["2019 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8791230\/8799366\/08803203.pdf?arnumber=8803203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:48:49Z","timestamp":1658155729000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8803203\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icip.2019.8803203","relation":{},"subject":[],"published":{"date-parts":[[2019,9]]}}}