{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T10:11:27Z","timestamp":1772532687547,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":16,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,9,20]],"date-time":"2022-09-20T00:00:00Z","timestamp":1663632000000},"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":[[2022,9,20]]},"DOI":"10.1145\/3558100.3563845","type":"proceedings-article","created":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T18:03:30Z","timestamp":1668794610000},"page":"1-4","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Optical character recognition with transformers and CTC"],"prefix":"10.1145","author":[{"given":"Israel","family":"Campiotti","sequence":"first","affiliation":[{"name":"University of Campinas"}]},{"given":"Roberto","family":"Lotufo","sequence":"additional","affiliation":[{"name":"University of Campinas"}]}],"member":"320","published-online":{"date-parts":[[2022,11,18]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"05717","article-title":"An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition","volume":"1507","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 ,\" CoRR , vol. abs\/ 1507 . 05717 , 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,\" CoRR, vol. abs\/1507.05717, 2015.","journal-title":"CoRR"},{"key":"e_1_3_2_1_2_1","first-page":"369","volume-title":"Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks,\" in Proceedings of the 23rd international conference on Machine learning","author":"Graves A.","year":"2006","unstructured":"A. Graves , S. Fern\u00e1ndez , F. Gomez , and J. Schmidhuber , \" Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks,\" in Proceedings of the 23rd international conference on Machine learning , pp. 369 -- 376 , 2006 . A. Graves, S. Fern\u00e1ndez, F. Gomez, and J. Schmidhuber, \"Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks,\" in Proceedings of the 23rd international conference on Machine learning, pp. 369--376, 2006."},{"key":"e_1_3_2_1_3_1","volume-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau D.","year":"2014","unstructured":"D. Bahdanau , K. Cho , and Y. Bengio , \" Neural machine translation by jointly learning to align and translate ,\" 2014 . D. Bahdanau, K. Cho, and Y. Bengio, \"Neural machine translation by jointly learning to align and translate,\" 2014."},{"key":"e_1_3_2_1_4_1","volume-title":"Stn-ocr: A single neural network for text detection and text recognition","author":"Bartz C.","year":"2017","unstructured":"C. Bartz , H. Yang , and C. Meinel , \" Stn-ocr: A single neural network for text detection and text recognition ,\" 2017 . C. Bartz, H. Yang, and C. Meinel, \"Stn-ocr: A single neural network for text detection and text recognition,\" 2017."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"D. V. Sang and L. T. B. Cuong \"Improving crnn with efficientnet-like feature extractor and multi-head attention for text recognition \" in Proceedings of the Tenth International Symposium on Information and Communication Technology SoICT 2019 (New York NY USA) p. 285--290 Association for Computing Machinery 2019.  D. V. Sang and L. T. B. Cuong \"Improving crnn with efficientnet-like feature extractor and multi-head attention for text recognition \" in Proceedings of the Tenth International Symposium on Information and Communication Technology SoICT 2019 (New York NY USA) p. 285--290 Association for Computing Machinery 2019.","DOI":"10.1145\/3368926.3369689"},{"key":"e_1_3_2_1_6_1","first-page":"10282","article-title":"Trocr: Transformer-based optical character recognition with pre-trained models","volume":"2109","author":"Li M.","year":"2021","unstructured":"M. Li , T. Lv , L. Cui , Y. Lu , D. A. F. Flor\u00eancio , C. Zhang , Z. Li , and F. Wei , \" Trocr: Transformer-based optical character recognition with pre-trained models ,\" CoRR , vol. abs\/ 2109 . 10282 , 2021 . M. Li, T. Lv, L. Cui, Y. Lu, D. A. F. Flor\u00eancio, C. Zhang, Z. Li, and F. Wei, \"Trocr: Transformer-based optical character recognition with pre-trained models,\" CoRR, vol. abs\/2109.10282, 2021.","journal-title":"CoRR"},{"key":"e_1_3_2_1_7_1","volume-title":"Offline handwriting recognition with multidimensional recurrent neural networks,\" in Advances in Neural Information Processing Systems","author":"Graves A.","year":"2008","unstructured":"A. Graves and J. Schmidhuber , \" Offline handwriting recognition with multidimensional recurrent neural networks,\" in Advances in Neural Information Processing Systems (D. Koller, D. Schuurmans, Y. Bengio, and L. Bottou, eds.), vol. 21 , Curran Associates, Inc. , 2008 . A. Graves and J. Schmidhuber, \"Offline handwriting recognition with multidimensional recurrent neural networks,\" in Advances in Neural Information Processing Systems (D. Koller, D. Schuurmans, Y. Bengio, and L. Bottou, eds.), vol. 21, Curran Associates, Inc., 2008."},{"key":"e_1_3_2_1_8_1","volume-title":"Pp-ocr: A practical ultra lightweight ocr system","author":"Du Y.","year":"2020","unstructured":"Y. Du , C. Li , R. Guo , X. Yin , W. Liu , J. Zhou , Y. Bai , Z. Yu , Y. Yang , Q. Dang , and H. Wang , \" Pp-ocr: A practical ultra lightweight ocr system ,\" 2020 . Y. Du, C. Li, R. Guo, X. Yin, W. Liu, J. Zhou, Y. Bai, Z. Yu, Y. Yang, Q. Dang, and H. Wang, \"Pp-ocr: A practical ultra lightweight ocr system,\" 2020."},{"key":"e_1_3_2_1_9_1","volume-title":"Beit: Bert pre-training of image transformers","author":"Bao H.","year":"2021","unstructured":"H. Bao , L. Dong , and F. Wei , \" Beit: Bert pre-training of image transformers ,\" 2021 . H. Bao, L. Dong, and F. Wei, \"Beit: Bert pre-training of image transformers,\" 2021."},{"key":"e_1_3_2_1_10_1","volume-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu Y.","year":"2019","unstructured":"Y. Liu , M. Ott , N. Goyal , J. Du , M. Joshi , D. Chen , O. Levy , M. Lewis , L. Zettlemoyer , and V. Stoyanov , \" Roberta: A robustly optimized bert pretraining approach ,\" 2019 . Y. Liu, M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer, and V. Stoyanov, \"Roberta: A robustly optimized bert pretraining approach,\" 2019."},{"key":"e_1_3_2_1_11_1","first-page":"260","volume-title":"Rescoring sequence-to-sequence models for text line recognition with ctc-prefixes,\" in International Workshop on Document Analysis Systems","author":"Wick C.","year":"2022","unstructured":"C. Wick , J. Z\u00f6llner , and T. Gr\u00fcning , \" Rescoring sequence-to-sequence models for text line recognition with ctc-prefixes,\" in International Workshop on Document Analysis Systems , pp. 260 -- 274 , Springer , 2022 . C. Wick, J. Z\u00f6llner, and T. Gr\u00fcning, \"Rescoring sequence-to-sequence models for text line recognition with ctc-prefixes,\" in International Workshop on Document Analysis Systems, pp. 260--274, Springer, 2022."},{"key":"e_1_3_2_1_12_1","first-page":"275","volume-title":"A light transformer-based architecture for handwritten text recognition,\" in International Workshop on Document Analysis Systems","author":"Barrere K.","year":"2022","unstructured":"K. Barrere , Y. Soullard , A. Lemaitre , and B. Co\u00fcasnon , \" A light transformer-based architecture for handwritten text recognition,\" in International Workshop on Document Analysis Systems , pp. 275 -- 290 , Springer , 2022 . K. Barrere, Y. Soullard, A. Lemaitre, and B. Co\u00fcasnon, \"A light transformer-based architecture for handwritten text recognition,\" in International Workshop on Document Analysis Systems, pp. 275--290, Springer, 2022."},{"key":"e_1_3_2_1_13_1","first-page":"03167","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"1502","author":"Ioffe S.","year":"2015","unstructured":"S. Ioffe and C. Szegedy , \" Batch normalization: Accelerating deep network training by reducing internal covariate shift ,\" CoRR , vol. abs\/ 1502 . 03167 , 2015 . S. Ioffe and C. Szegedy, \"Batch normalization: Accelerating deep network training by reducing internal covariate shift,\" CoRR, vol. abs\/1502.03167, 2015.","journal-title":"CoRR"},{"key":"e_1_3_2_1_14_1","first-page":"1","volume-title":"Batch normalization in convolutional neural networks --- a comparative study with cifar-10 data,\" in 2018 Fifth International Conference on Emerging Applications of Information Technology (EAIT)","author":"Thakkar V.","year":"2018","unstructured":"V. Thakkar , S. Tewary , and C. Chakraborty , \" Batch normalization in convolutional neural networks --- a comparative study with cifar-10 data,\" in 2018 Fifth International Conference on Emerging Applications of Information Technology (EAIT) , pp. 1 -- 5 , 2018 . V. Thakkar, S. Tewary, and C. Chakraborty, \"Batch normalization in convolutional neural networks --- a comparative study with cifar-10 data,\" in 2018 Fifth International Conference on Emerging Applications of Information Technology (EAIT), pp. 1--5, 2018."},{"key":"e_1_3_2_1_15_1","first-page":"01155","article-title":"Batch normalization tells you which filter is important","volume":"2112","author":"Oh J.","year":"2021","unstructured":"J. Oh , H. Kim , S. Baik , C. Hong , and K. M. Lee , \" Batch normalization tells you which filter is important ,\" CoRR , vol. abs\/ 2112 . 01155 , 2021 . J. Oh, H. Kim, S. Baik, C. Hong, and K. M. Lee, \"Batch normalization tells you which filter is important,\" CoRR, vol. abs\/2112.01155, 2021.","journal-title":"CoRR"},{"key":"e_1_3_2_1_16_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin J.","year":"2018","unstructured":"J. Devlin , M.-W. Chang , K. Lee , and K. Toutanova , \" Bert: Pre-training of deep bidirectional transformers for language understanding ,\" 2018 . J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, \"Bert: Pre-training of deep bidirectional transformers for language understanding,\" 2018."}],"event":{"name":"DocEng '22: ACM Symposium on Document Engineering 2022","location":"San Jose California","acronym":"DocEng '22","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGDOC ACM Special Interest Group on Systems Documentation"]},"container-title":["Proceedings of the 22nd ACM Symposium on Document Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3558100.3563845","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3558100.3563845","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:32Z","timestamp":1750182572000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3558100.3563845"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,20]]},"references-count":16,"alternative-id":["10.1145\/3558100.3563845","10.1145\/3558100"],"URL":"https:\/\/doi.org\/10.1145\/3558100.3563845","relation":{},"subject":[],"published":{"date-parts":[[2022,9,20]]},"assertion":[{"value":"2022-11-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}