{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:22:52Z","timestamp":1730265772471,"version":"3.28.0"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"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":[[2019,7]]},"DOI":"10.1109\/ijcnn.2019.8852010","type":"proceedings-article","created":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T03:44:32Z","timestamp":1569901472000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["Ensemble Attention For Text Recognition In Natural Images"],"prefix":"10.1109","author":[{"given":"Hongchao","family":"Gao","sequence":"first","affiliation":[]},{"given":"Yujia","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xi","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jizhong","family":"Han","sequence":"additional","affiliation":[]},{"given":"Ruixuan","family":"Li","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-004-0134-3"},{"journal-title":"Layer normalization","year":"0","author":"ba","key":"ref38"},{"key":"ref33","article-title":"Fots: Fast oriented text spotting with a uni ed network","author":"liu","year":"0","journal-title":"IEEE Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00584"},{"journal-title":"Image transformer","year":"0","author":"parmar","key":"ref37"},{"journal-title":"Non-local neural networks","year":"0","author":"wang","key":"ref36"},{"journal-title":"Effective Approaches to Attention-based Neural Machine Translation","year":"0","author":"luong","key":"ref35"},{"journal-title":"Self-attention generative adversarial networks","year":"0","author":"zhang","key":"ref34"},{"journal-title":"Reading scene text with attention convolutional sequence modeling","year":"0","author":"gao","key":"ref28"},{"journal-title":"Convolutional sequence to sequence learning","year":"0","author":"gehring","key":"ref27"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00527"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366765"},{"journal-title":"Language Modeling with Gated Convolutional Networks[J]","year":"0","author":"n","key":"ref20"},{"key":"ref22","first-page":"35","article-title":"Accurate recognition of words in scenes without character segmentation using recurrent neural network","volume":"63","author":"su","year":"2014","journal-title":"Asian Conference on Computer Vision"},{"journal-title":"WaveNet A Generative Model for Raw Audio","year":"0","author":"den oord aaron","key":"ref21"},{"key":"ref24","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Advances in Neural Information Processing Systems(NIPS)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.10.016"},{"journal-title":"A structured self-attentive sentence embedding","year":"0","author":"lin","key":"ref26"},{"journal-title":"Neural machine translation by jointly learning to align and translate","year":"0","author":"bahdanau","key":"ref25"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"ref51","first-page":"22312239","article-title":"Recursive recurrent nets with attention modeling for ocr in the wild","author":"liu","year":"2018","journal-title":"CVPR"},{"key":"ref53","article-title":"Aster: An attentional scene text recognizer with flexible rectification","author":"shi","year":"2018","journal-title":"IEEE PAMI"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/458"},{"key":"ref10","article-title":"See: Towards semi-supervised end-to-end scene text recognition","author":"bartz","year":"0","journal-title":"The 32th AAAI Conference on Artificial Intelligence (AAAI-18) 1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.03.070"},{"key":"ref40","first-page":"1484","article-title":"Icdar 2013 robust reading competition, Document Analysis and Recognition (ICDAR)","author":"karatzas","year":"2013","journal-title":"2013 12th International Conference on"},{"key":"ref12","first-page":"2687","article-title":"Top-down and bottom-up cues for scene text recognition, Computer Vision and Pattern Recognition (CVPR)","author":"mishra","year":"2012","journal-title":"2012 IEEE Conference on"},{"key":"ref13","first-page":"1024","article-title":"A gradient vector flow-based method for video character segmentation, Document Analysis and Recognition (ICDAR)","author":"phan","year":"2011","journal-title":"2011 International Conference on"},{"key":"ref14","first-page":"512","author":"jaderberg","year":"2014","journal-title":"Deep features for text spotting European conference on computer vision"},{"key":"ref15","first-page":"785","article-title":"Photoocr: Reading text in uncontrolled conditions, Computer Vision (ICCV)","author":"bissacco","year":"2013","journal-title":"2013 IEEE International Conference on"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.515"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.516"},{"key":"ref18","first-page":"3501","article-title":"Reading scene text in deep convolutional sequences","volume":"1","author":"he","year":"2016","journal-title":"Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI'16)"},{"key":"ref19","first-page":"6000","author":"vaswani","year":"2017","journal-title":"Attention is all you need Advances in Neural Information Processing Systems(NIPS)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref3","article-title":"Char-net: A character-aware neural network for distorted scene text recognition","author":"liu","year":"0","journal-title":"The 32nd AAAI Conference on Artificial Intelligence (AAAI-18)"},{"key":"ref6","first-page":"334","author":"wang","year":"0","journal-title":"Gated recurrent convolution neural network for ocr Ad- vances in Neural Information Processing Systems"},{"key":"ref5","first-page":"4168","article-title":"Robust scene text recognition with automatic recti cation","author":"shi","year":"2016","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition(CVPR)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.543"},{"key":"ref7","first-page":"2231","article-title":"Recursive recurrent nets with attention mod-eling for ocr in the wild","author":"chen-yu","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"},{"journal-title":"Stn-ocr A single neural network for text detection and text recognition","year":"0","author":"bartz","key":"ref9"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240571"},{"journal-title":"Deep structured output learning for unconstrained text recognition","year":"0","author":"jaderberg","key":"ref45"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.76"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref42","first-page":"1457","article-title":"End-to-end scene text recognition, Computer Vision (ICCV)","volume":"1707","author":"kai","year":"2011","journal-title":"2011 IEEE International Conference on"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref44","first-page":"1156","article-title":"Icdar 2015 competition on robust reading, Document Analysis and Recognition (ICDAR)","author":"karatzas","year":"2015","journal-title":"2015 13th International Conference on"},{"journal-title":"A method for stochastic optimization","year":"0","author":"kingma","key":"ref43"}],"event":{"name":"2019 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2019,7,14]]},"location":"Budapest, Hungary","end":{"date-parts":[[2019,7,19]]}},"container-title":["2019 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8840768\/8851681\/08852010.pdf?arnumber=8852010","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:55:41Z","timestamp":1658094941000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8852010\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2019.8852010","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}