{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T17:52:53Z","timestamp":1758477173400,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":81,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,12,18]],"date-time":"2018-12-18T00:00:00Z","timestamp":1545091200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,12,18]]},"DOI":"10.1145\/3293353.3293386","type":"proceedings-article","created":{"date-parts":[[2020,5,4]],"date-time":"2020-05-04T22:07:32Z","timestamp":1588630052000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Learning to Read by Spelling"],"prefix":"10.1145","author":[{"given":"Ankush","family":"Gupta","sequence":"first","affiliation":[{"name":"Visual Geometry Group, University of Oxford"}]},{"given":"Andrea","family":"Vedaldi","sequence":"additional","affiliation":[{"name":"Visual Geometry Group, University of Oxford"}]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[{"name":"Visual Geometry Group, University of Oxford"}]}],"member":"320","published-online":{"date-parts":[[2020,5,3]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"EMNLP conference on machine translation 2018.  EMNLP conference on machine translation 2018."},{"key":"e_1_3_2_1_2_1","first-page":"265","volume-title":"OSDI","volume":"16","author":"Abadi M.","year":"2016","unstructured":"M. Abadi , P. Barham , J. Chen , Z. Chen , A. Davis , J. Dean , M. Devin , S. Ghemawat , G. Irving , M. Isard , : a system for large-scale machine learning . In OSDI , volume 16 , pages 265 -- 283 , 2016 . M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, et al. Tensorflow: a system for large-scale machine learning. In OSDI, volume 16, pages 265--283, 2016."},{"key":"e_1_3_2_1_3_1","volume-title":"Decipherment of historical manuscripts. Master's thesis","author":"Aldarrab N.","year":"2017","unstructured":"N. Aldarrab . Decipherment of historical manuscripts. Master's thesis , University of Southern California , 2017 . N. Aldarrab. Decipherment of historical manuscripts. Master's thesis, University of Southern California, 2017."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2339814"},{"key":"e_1_3_2_1_5_1","volume-title":"Proc. ICLR","author":"Alsharif O.","year":"2014","unstructured":"O. Alsharif and J. Pineau . End-to-end text recognition with hybrid HMM maxout models . In Proc. ICLR , 2014 . O. Alsharif and J. Pineau. End-to-end text recognition with hybrid HMM maxout models. In Proc. ICLR, 2014."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.294"},{"key":"e_1_3_2_1_7_1","volume-title":"Proc. ICLR","author":"Artetxe M.","year":"2017","unstructured":"M. Artetxe , G. Labaka , E. Agirre , and K. Cho . Unsupervised neural machine translation . In Proc. ICLR , 2017 . M. Artetxe, G. Labaka, E. Agirre, and K. Cho. Unsupervised neural machine translation. In Proc. ICLR, 2017."},{"key":"e_1_3_2_1_8_1","volume-title":"Layer normalization. arXiv preprint arXiv:1607.06450","author":"Ba J. L.","year":"2016","unstructured":"J. L. Ba , J. R. Kiros , and G. E. Hinton . Layer normalization. arXiv preprint arXiv:1607.06450 , 2016 . J. L. Ba, J. R. Kiros, and G. E. Hinton. Layer normalization. arXiv preprint arXiv:1607.06450, 2016."},{"key":"e_1_3_2_1_9_1","volume-title":"Proc. ICLR","author":"Bahdanau D.","year":"2015","unstructured":"D. Bahdanau , K. Cho , and Y. Bengio . Neural machine translation by jointly learning to align and translate . In Proc. ICLR , 2015 . D. Bahdanau, K. Cho, and Y. Bengio. Neural machine translation by jointly learning to align and translate. In Proc. ICLR, 2015."},{"key":"e_1_3_2_1_10_1","first-page":"207","volume-title":"Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","volume":"1","author":"Berg-Kirkpatrick T.","year":"2013","unstructured":"T. Berg-Kirkpatrick , G. Durrett , and D. Klein . Unsupervised transcription of historical documents . In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , volume 1 , pages 207 -- 217 , 2013 . T. Berg-Kirkpatrick, G. Durrett, and D. Klein. Unsupervised transcription of historical documents. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), volume 1, pages 207--217, 2013."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.102"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.14"},{"key":"e_1_3_2_1_13_1","volume-title":"Text OCR by solving a cryptogram","author":"Casey R. G.","year":"1986","unstructured":"R. G. Casey . Text OCR by solving a cryptogram . 1986 . R. G. Casey. Text OCR by solving a cryptogram. 1986."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_1_15_1","volume-title":"Maximum likelihood from incomplete data via the EM algorithm. 39 B:1--38","author":"Dempster A. P.","year":"1977","unstructured":"A. P. Dempster , N. M. Laird , and D. B. Rubin . Maximum likelihood from incomplete data via the EM algorithm. 39 B:1--38 , 1977 . A. P. Dempster, N. M. Laird, and D. B. Rubin. Maximum likelihood from incomplete data via the EM algorithm. 39 B:1--38, 1977."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-01628-3","volume-title":"A brief history of cryptology and cryptographic algorithms","author":"Dooley J. F.","year":"2013","unstructured":"J. F. Dooley . A brief history of cryptology and cryptographic algorithms . Springer , 2013 . J. F. Dooley. A brief history of cryptology and cryptographic algorithms. Springer, 2013."},{"key":"e_1_3_2_1_17_1","first-page":"249","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics","author":"Glorot X.","year":"2010","unstructured":"X. Glorot and Y. Bengio . Understanding the difficulty of training deep feedforward neural networks . In Proceedings of the thirteenth international conference on artificial intelligence and statistics , pages 249 -- 256 , 2010 . X. Glorot and Y. Bengio. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics, pages 249--256, 2010."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.87"},{"key":"e_1_3_2_1_19_1","volume-title":"Proc. ICLR","author":"Gomez A. N.","year":"2018","unstructured":"A. N. Gomez , S. Huang , I. Zhang , B. M. Li , M. Osama , and L. Kaiser . Unsupervised cipher cracking using discrete GANs . In Proc. ICLR , 2018 . A. N. Gomez, S. Huang, I. Zhang, B. M. Li, M. Osama, and L. Kaiser. Unsupervised cipher cracking using discrete GANs. In Proc. ICLR, 2018."},{"key":"e_1_3_2_1_20_1","volume-title":"Proc. NIPS","author":"Goodfellow I.","year":"2014","unstructured":"I. Goodfellow , J. Pouget-Abadie , M. Mirza , B. Xu , D. Warde-Farley , S. Ozair , A. Courville , and Y. Bengio . Generative adversarial nets . In Proc. NIPS , 2014 . I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. Generative adversarial nets. In Proc. NIPS, 2014."},{"key":"e_1_3_2_1_21_1","volume-title":"Aug","author":"Google Inc.","year":"2018","unstructured":"Google Inc. Book search dataset , Aug 2018 . Version V. Google Inc. Book search dataset, Aug 2018. Version V."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298914"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"e_1_3_2_1_25_1","volume-title":"Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385","author":"He K.","year":"2015","unstructured":"K. He , X. Zhang , S. Ren , and J. Sun . Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385 , 2015 . K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385, 2015."},{"key":"e_1_3_2_1_26_1","volume-title":"The 30th AAAI Conference on Artificial Intelligence (AAAI-16)","volume":"1","author":"He P.","year":"2016","unstructured":"P. He , W. Huang , Y. Qiao , C. Loy , and X. Tang . Reading scene text in deep convolutional sequences, 2016 . In The 30th AAAI Conference on Artificial Intelligence (AAAI-16) , volume 1 , 2016 . P. He, W. Huang, Y. Qiao, C. Loy, and X. Tang. Reading scene text in deep convolutional sequences, 2016. In The 30th AAAI Conference on Artificial Intelligence (AAAI-16), volume 1, 2016."},{"key":"e_1_3_2_1_27_1","volume-title":"Proc. ICPR","author":"Ho T. K.","year":"2000","unstructured":"T. K. Ho and G. Nagy . OCR with no shape training . In Proc. ICPR , 2000 . T. K. Ho and G. Nagy. OCR with no shape training. In Proc. ICPR, 2000."},{"key":"e_1_3_2_1_28_1","volume-title":"Cryptogram decoding for optical character recognition","author":"Huang G.","year":"2007","unstructured":"G. Huang , E. Learned-Miller , and A. McCallum . Cryptogram decoding for optical character recognition . 2007 . G. Huang, E. Learned-Miller, and A. McCallum. Cryptogram decoding for optical character recognition. 2007."},{"key":"e_1_3_2_1_29_1","unstructured":"Hunspell. https:\/\/hunspell.github.io.  Hunspell. https:\/\/hunspell.github.io."},{"key":"e_1_3_2_1_30_1","volume-title":"Proc. ICML","author":"Ioffe S.","year":"2015","unstructured":"S. Ioffe and C. Szegedy . Batch normalization: Accelerating deep network training by reducing internal covariate shift . In Proc. ICML , 2015 . S. Ioffe and C. Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proc. ICML, 2015."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_2_1_32_1","volume-title":"Workshop on Deep Learning, NIPS","author":"Jaderberg M.","year":"2014","unstructured":"M. Jaderberg , K. Simonyan , A. Vedaldi , and A. Zisserman . Synthetic data and artificial neural networks for natural scene text recognition . In Workshop on Deep Learning, NIPS , 2014 . M. Jaderberg, K. Simonyan, A. Vedaldi, and A. Zisserman. Synthetic data and artificial neural networks for natural scene text recognition. In Workshop on Deep Learning, NIPS, 2014."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_34"},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Learning Representations","author":"Jaderberg M.","year":"2015","unstructured":"M. Jaderberg , K. Simonyan , A. Vedaldi , and A. Zisserman . Deep structured output learning for unconstrained text recognition . In International Conference on Learning Representations , 2015 . M. Jaderberg, K. Simonyan, A. Vedaldi, and A. Zisserman. Deep structured output learning for unconstrained text recognition. In International Conference on Learning Representations, 2015."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"e_1_3_2_1_36_1","volume-title":"Learning on the fly: font-free approaches to difficult OCR problems","author":"Kae A.","year":"2009","unstructured":"A. Kae and E. Learned-Miller . Learning on the fly: font-free approaches to difficult OCR problems . 2009 . A. Kae and E. Learned-Miller. Learning on the fly: font-free approaches to difficult OCR problems. 2009."},{"key":"e_1_3_2_1_37_1","first-page":"1484","volume-title":"ICDAR 2013 robust reading competition. In Proc. ICDAR","author":"Karatzas D.","year":"2013","unstructured":"D. Karatzas , F. Shafait , S. Uchida , M. Iwamura , S. R. Mestre , J. Mas , D. F. Mota , J. A. Almazan , L. P. de las Heras, et al . ICDAR 2013 robust reading competition. In Proc. ICDAR , pages 1484 -- 1493 , 2013 . D. Karatzas, F. Shafait, S. Uchida, M. Iwamura, S. R. Mestre, J. Mas, D. F. Mota, J. A. Almazan, L. P. de las Heras, et al. ICDAR 2013 robust reading competition. In Proc. ICDAR, pages 1484--1493, 2013."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/1273073.1273138"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/2024236.2024239"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR.2014.98"},{"key":"e_1_3_2_1_41_1","first-page":"1106","volume-title":"Proc. NIPS","author":"Krizhevsky A.","year":"2012","unstructured":"A. Krizhevsky , I. Sutskever , and G. E. Hinton . ImageNet classification with deep convolutional neural networks . In Proc. NIPS , pages 1106 -- 1114 , 2012 . A. Krizhevsky, I. Sutskever, and G. E. Hinton. ImageNet classification with deep convolutional neural networks. In Proc. NIPS, pages 1106--1114, 2012."},{"key":"e_1_3_2_1_42_1","volume-title":"Proc. ICLR","author":"Lample G.","year":"2017","unstructured":"G. Lample , L. Denoyer , and M. Ranzato . Unsupervised machine translation using monolingual corpora only . In Proc. ICLR , 2017 . G. Lample, L. Denoyer, and M. Ranzato. Unsupervised machine translation using monolingual corpora only. In Proc. ICLR, 2017."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.245"},{"key":"e_1_3_2_1_45_1","volume-title":"Proc. CVPR","author":"Lee C.","year":"2014","unstructured":"C. Lee , A. Bhardwaj , W. Di , V. Jagadeesh , and R. Piramuthu . Regionbased discriminative feature pooling for scene text recognition . In Proc. CVPR , 2014 . C. Lee, A. Bhardwaj, W. Di, V. Jagadeesh, and R. Piramuthu. Regionbased discriminative feature pooling for scene text recognition. In Proc. CVPR, 2014."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"D.-S. Lee. Substitution deciphering based on HMMs with applications to compressed document processing. PAMI (12):1661--1666 2002.  D.-S. Lee. Substitution deciphering based on HMMs with applications to compressed document processing. PAMI (12):1661--1666 2002.","DOI":"10.1109\/TPAMI.2002.1114860"},{"key":"e_1_3_2_1_47_1","first-page":"707","volume-title":"Soviet Physics Doklady","volume":"10","author":"Levenshtein V.","year":"1966","unstructured":"V. Levenshtein . Binary codes capable of correcting deletions, insertions and reversals . In Soviet Physics Doklady , volume 10 , page 707 , 1966 . V. Levenshtein. Binary codes capable of correcting deletions, insertions and reversals. In Soviet Physics Doklady, volume 10, page 707, 1966."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_43"},{"key":"e_1_3_2_1_49_1","first-page":"700","volume-title":"Proc. NIPS","author":"Liu M.-Y.","year":"2017","unstructured":"M.-Y. Liu , T. Breuel , and J. Kautz . Unsupervised image-to-image translation networks . In Proc. NIPS , pages 700 -- 708 , 2017 . M.-Y. Liu, T. Breuel, and J. Kautz. Unsupervised image-to-image translation networks. In Proc. NIPS, pages 700--708, 2017."},{"key":"e_1_3_2_1_50_1","first-page":"3550","volume-title":"Proc. NIPS","author":"Liu Y.","year":"2017","unstructured":"Y. Liu , J. Chen , and L. Deng . Unsupervised sequence classification using sequential output statistics . In Proc. NIPS , pages 3550 -- 3559 , 2017 . Y. Liu, J. Chen, and L. Deng. Unsupervised sequence classification using sequential output statistics. In Proc. NIPS, pages 3550--3559, 2017."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_1_52_1","first-page":"3","volume-title":"Proc. ICML","volume":"30","author":"Maas A. L.","year":"2013","unstructured":"A. L. Maas , A. Y. Hannun , and A. Y. Ng . Rectifier nonlinearities improve neural network acoustic models . In Proc. ICML , volume 30 , page 3 , 2013 . A. L. Maas, A. Y. Hannun, and A. Y. Ng. Rectifier nonlinearities improve neural network acoustic models. In Proc. ICML, volume 30, page 3, 2013."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247990"},{"key":"e_1_3_2_1_56_1","first-page":"352","volume-title":"Proc. ICPR","author":"Nagy G.","year":"1986","unstructured":"G. Nagy . Efficient algorithms to decode substitution ciphers with applications to OCR . In Proc. ICPR , pages 352 -- 355 , 1986 . G. Nagy. Efficient algorithms to decode substitution ciphers with applications to OCR. In Proc. ICPR, pages 352--355, 1986."},{"key":"e_1_3_2_1_57_1","volume-title":"NIPS DLW","volume":"2011","author":"Netzer Y.","year":"2011","unstructured":"Y. Netzer , T. Wang , A. Coates , A. Bissacco , B. Wu , and A. Y. Ng . Reading digits in natural images with unsupervised feature learning . In NIPS DLW , volume 2011 , 2011 . Y. Netzer, T. Wang, A. Coates, A. Bissacco, B. Wu, and A. Y. Ng. Reading digits in natural images with unsupervised feature learning. In NIPS DLW, volume 2011, 2011."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_54"},{"key":"e_1_3_2_1_60_1","first-page":"615","volume-title":"Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics","volume":"1","author":"Nuhn M.","year":"2013","unstructured":"M. Nuhn and H. Ney . Decipherment complexity in 1: 1 substitution ciphers . In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics , volume 1 , pages 615 -- 621 , 2013 . M. Nuhn and H. Ney. Decipherment complexity in 1: 1 substitution ciphers. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, volume 1, pages 615--621, 2013."},{"key":"e_1_3_2_1_61_1","volume-title":"Observations on the Nature and Cure of Gout: On Nodes of the Joints","author":"Parkinson J.","year":"1805","unstructured":"J. Parkinson . Observations on the Nature and Cure of Gout: On Nodes of the Joints ; and on the Influence of Certain Articles of Diet, in Gout, Rheumatism, and Gravel. Symonds , 1805 . J. Parkinson. Observations on the Nature and Cure of Gout: On Nodes of the Joints; and on the Influence of Certain Articles of Diet, in Gout, Rheumatism, and Gravel. Symonds, 1805."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/359168.359174"},{"key":"e_1_3_2_1_63_1","volume-title":"Proc. CVPR","author":"Poznanski A.","year":"2016","unstructured":"A. Poznanski and L. Wolf . CNN-N-Gram for handwriting word recognition . In Proc. CVPR , 2016 . A. Poznanski and L. Wolf. CNN-N-Gram for handwriting word recognition. In Proc. CVPR, 2016."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.5555\/1613715.1613819"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0793-6"},{"key":"e_1_3_2_1_66_1","volume-title":"An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. ArXiv e-prints","author":"Shi B.","year":"2015","unstructured":"B. Shi , X. Bai , and C. Yao . An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. ArXiv e-prints , 2015 . B. Shi, X. Bai, and C. Yao. An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. ArXiv e-prints, 2015."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.452"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.381"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.5555\/1304596.1304846"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.5555\/1858681.1858788"},{"key":"e_1_3_2_1_71_1","volume-title":"Proc. ICML","author":"Srivastava N.","year":"2015","unstructured":"N. Srivastava , E. Mansimov , and R. Salakhudinov . Unsupervised learning of video representations using lstms . In Proc. ICML , 2015 . N. Srivastava, E. Mansimov, and R. Salakhudinov. Unsupervised learning of video representations using lstms. In Proc. ICML, 2015."},{"key":"e_1_3_2_1_72_1","volume-title":"Proc. ACCV","author":"Su B.","year":"2014","unstructured":"B. Su and S. Lu . Accurate scene text recognition based on recurrent neural network . In Proc. ACCV , 2014 . B. Su and S. Lu. Accurate scene text recognition based on recurrent neural network. In Proc. ACCV, 2014."},{"key":"e_1_3_2_1_73_1","first-page":"3104","volume-title":"Proc. NIPS","author":"Sutskever I.","year":"2014","unstructured":"I. Sutskever , O. Vinyals , and Q. V. Le . Sequence to sequence learning with neural networks . In Proc. NIPS , pages 3104 -- 3112 , 2014 . I. Sutskever, O. Vinyals, and Q. V. Le. Sequence to sequence learning with neural networks. In Proc. NIPS, pages 3104--3112, 2014."},{"key":"e_1_3_2_1_74_1","volume-title":"ICLR workshop","author":"Sutskever I.","year":"2016","unstructured":"I. Sutskever , R. Jozefowicz , K. Gregor , D. Rezende , T. Lillicrap , and O. Vinyals . Towards principled unsupervised learning . In ICLR workshop , 2016 . I. Sutskever, R. Jozefowicz, K. Gregor, D. Rezende, T. Lillicrap, and O. Vinyals. Towards principled unsupervised learning. In ICLR workshop, 2016."},{"key":"e_1_3_2_1_75_1","volume-title":"https:\/\/github.com\/tesseract-ocr\/","author":"OCR.","year":"1985","unstructured":"Tesseract OCR. https:\/\/github.com\/tesseract-ocr\/ , 1985 --2018. Tesseract OCR. https:\/\/github.com\/tesseract-ocr\/, 1985--2018."},{"key":"e_1_3_2_1_76_1","volume-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural networks for machine learning, 4(2):26--31","author":"Tieleman T.","year":"2012","unstructured":"T. Tieleman and G. Hinton . Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural networks for machine learning, 4(2):26--31 , 2012 . T. Tieleman and G. Hinton. Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural networks for machine learning, 4(2):26--31, 2012."},{"key":"e_1_3_2_1_77_1","volume-title":"Proc","author":"Wang K.","year":"2010","unstructured":"K. Wang and S. Belongie . Word spotting in the wild . In Proc . ECCV. Springer , 2010 . K. Wang and S. Belongie. Word spotting in the wild. In Proc. ECCV. Springer, 2010."},{"key":"e_1_3_2_1_78_1","first-page":"1457","volume-title":"Proc. ICCV","author":"Wang K.","year":"2011","unstructured":"K. Wang , B. Babenko , and S. Belongie . End-to-end scene text recognition . In Proc. ICCV , pages 1457 -- 1464 . IEEE, 2011 . K. Wang, B. Babenko, and S. Belongie. End-to-end scene text recognition. In Proc. ICCV, pages 1457--1464. IEEE, 2011."},{"key":"e_1_3_2_1_79_1","first-page":"3304","volume-title":"Proc. ICPR","author":"Wang T.","year":"2012","unstructured":"T. Wang , D. J. Wu , A. Coates , and A. Y. Ng . End-to-end text recognition with convolutional neural networks . In Proc. ICPR , pages 3304 -- 3308 . IEEE, 2012 . T. Wang, D. J. Wu, A. Coates, and A. Y. Ng. End-to-end text recognition with convolutional neural networks. In Proc. ICPR, pages 3304--3308. IEEE, 2012."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.515"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"event":{"name":"ICVGIP 2018: 11th Indian Conference on Computer Vision, Graphics and Image Processing","acronym":"ICVGIP 2018","location":"Hyderabad India"},"container-title":["Proceedings of the 11th Indian Conference on Computer Vision, Graphics and Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3293353.3293386","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3293353.3293386","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:58:08Z","timestamp":1750208288000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3293353.3293386"}},"subtitle":["Towards Unsupervised Text Recognition"],"short-title":[],"issued":{"date-parts":[[2018,12,18]]},"references-count":81,"alternative-id":["10.1145\/3293353.3293386","10.1145\/3293353"],"URL":"https:\/\/doi.org\/10.1145\/3293353.3293386","relation":{},"subject":[],"published":{"date-parts":[[2018,12,18]]},"assertion":[{"value":"2020-05-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}