{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:52:24Z","timestamp":1773154344997,"version":"3.50.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030863333","type":"print"},{"value":"9783030863340","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86334-0_8","type":"book-chapter","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T20:16:02Z","timestamp":1630700162000},"page":"112-126","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":47,"title":["Transformer for Handwritten Text Recognition Using Bidirectional Post-decoding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3958-6240","authenticated-orcid":false,"given":"Christoph","family":"Wick","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3889-6629","authenticated-orcid":false,"given":"Jochen","family":"Z\u00f6llner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0031-4942","authenticated-orcid":false,"given":"Tobias","family":"Gr\u00fcning","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Al Azawi, M., Liwicki, M., Breuel, T.M.: Combination of multiple aligned recognition outputs using WFST and LSTM. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 31\u201335. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333720"},{"key":"8_CR2","unstructured":"Al-Sabahi, K., Zuping, Z., Kang, Y.: Bidirectional attentional encoder-decoder model and bidirectional beam search for abstractive summarization. arXiv preprint arXiv:1809.06662 (2018)"},{"key":"8_CR3","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. CoRR abs\/1409.0473 (2014)"},{"key":"8_CR4","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer. arXiv preprint arXiv:2004.05150 (2020)"},{"key":"8_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1007\/978-3-642-04346-8_17","volume-title":"Research and Advanced Technology for Digital Libraries","author":"F Boschetti","year":"2009","unstructured":"Boschetti, F., Romanello, M., Babeu, A., Bamman, D., Crane, G.: Improving OCR accuracy for classical critical editions. In: Agosti, M., Borbinha, J., Kapidakis, S., Papatheodorou, C., Tsakonas, G. (eds.) ECDL 2009. LNCS, vol. 5714, pp. 156\u2013167. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-04346-8_17"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Breuel, T.: High performance text recognition using a hybrid convolutional-LSTM implementation. In: 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), pp. 11\u201316. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.12"},{"key":"8_CR7","doi-asserted-by":"publisher","first-page":"1875","DOI":"10.1109\/TMM.2015.2477044","volume":"17","author":"K Cho","year":"2015","unstructured":"Cho, K., Courville, A., Bengio, Y.: Describing multimedia content using attention-based encoder-decoder networks. IEEE Trans. Multimed. 17, 1875\u20131886 (2015). https:\/\/doi.org\/10.1109\/TMM.2015.2477044","journal-title":"IEEE Trans. Multimed."},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Doetsch, P., Zeyer, A., Ney, H.: Bidirectional decoder networks for attention-based end-to-end offline handwriting recognition. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 361\u2013366. IEEE (2016)","DOI":"10.1109\/ICFHR.2016.0074"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Dutta, K., Krishnan, P., Mathew, M., Jawahar, C.: Improving CNN-RNN hybrid networks for handwriting recognition. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 80\u201385. IEEE (2018)","DOI":"10.1109\/ICFHR-2018.2018.00023"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Schmidhuber, J.: Multi-dimensional recurrent neural networks. CoRR abs\/0705.2011 (2007)","DOI":"10.1007\/978-3-540-74690-4_56"},{"key":"8_CR11","unstructured":"Kang, L., Riba, P., Rusi\u00f1ol, M., Forn\u00e9s, A., Villegas, M.: Pay attention to what you read: non-recurrent handwritten text-line recognition. arXiv preprint arXiv:2005.13044 (2020)"},{"issue":"1","key":"8_CR12","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1006\/cviu.1996.0502","volume":"67","author":"D Lopresti","year":"1997","unstructured":"Lopresti, D., Zhou, J.: Using consensus sequence voting to correct OCR errors. Comput. Vis. Image Underst. 67(1), 39\u201347 (1997)","journal-title":"Comput. Vis. Image Underst."},{"key":"8_CR13","unstructured":"Maas, A.L., Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models. In: ICML (2013)"},{"issue":"1","key":"8_CR14","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/s100320200071","volume":"5","author":"UV Marti","year":"2002","unstructured":"Marti, U.V., Bunke, H.: The IAM-database: an English sentence database for offline handwriting recognition. Int. J. Doc. Anal. Recognit. 5(1), 39\u201346 (2002)","journal-title":"Int. J. Doc. Anal. Recognit."},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Michael, J., Labahn, R., Gr\u00fcning, T., Z\u00f6llner, J.: Evaluating sequence-to-sequence models for handwritten text recognition. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1286\u20131293. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00208"},{"key":"8_CR16","unstructured":"Pham, V., Kermorvant, C., Louradour, J.: Dropout improves recurrent neural networks for handwriting recognition. CoRR abs\/1312.4569 (2013)"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Puigcerver, J.: Are multidimensional recurrent layers really necessary for handwritten text recognition?. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 67\u201372. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.20"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Reul, C., Springmann, U., Wick, C., Puppe, F.: Improving OCR accuracy on early printed books by utilizing cross fold training and voting. In: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), pp. 423\u2013428 (2018)","DOI":"10.1109\/DAS.2018.30"},{"issue":"05","key":"8_CR19","doi-asserted-by":"publisher","first-page":"1259","DOI":"10.1142\/S0218001494000632","volume":"8","author":"SV Rice","year":"1994","unstructured":"Rice, S.V., Kanai, J., Nartker, T.A.: An algorithm for matching OCR-generated text strings. Int. J. Pattern Recognit. Artif. Intell. 8(05), 1259\u20131268 (1994)","journal-title":"Int. J. Pattern Recognit. Artif. Intell."},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. arXiv preprint arXiv:1803.02155 (2018)","DOI":"10.18653\/v1\/N18-2074"},{"key":"8_CR21","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: NIPS (September 2014)"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Tensmeyer, C., Wigington, C., Davis, B., Stewart, S., Martinez, T., Barrett, W.: Language model supervision for handwriting recognition model adaptation. In: 16th International Conference on Frontiers in Handwriting Recognition, pp. 133\u2013138. IEEE (2018)","DOI":"10.1109\/ICFHR-2018.2018.00032"},{"key":"8_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Doetsch, P., Ney, H.: Handwriting recognition with large multidimensional long short-term memory recurrent neural networks. In: ICFHR, pp. 228\u2013233 (October 2016)","DOI":"10.1109\/ICFHR.2016.0052"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Wemhoener, D., Yalniz, I.Z., Manmatha, R.: Creating an improved version using noisy OCR from multiple editions. In: 2013 12th International Conference on Document Analysis and Recognition (ICDAR), pp. 160\u2013164. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.39"},{"key":"8_CR26","unstructured":"Wick, C., Reul, C., Puppe, F.: Calamari - a high-performance tensorflow-based deep learning package for optical character recognition. Digit. Humanit. Q. 14(2) (2020)"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Wigington, C., Stewart, S., Davis, B., Barrett, B., Price, B., Cohen, S.: Data augmentation for recognition of handwritten words and lines using a CNN-LSTM network. In: ICDAR, pp. 639\u2013645 (November 2017)","DOI":"10.1109\/ICDAR.2017.110"},{"key":"8_CR28","doi-asserted-by":"publisher","first-page":"107482","DOI":"10.1016\/j.patcog.2020.107482","volume":"108","author":"M Yousef","year":"2020","unstructured":"Yousef, M., Hussain, K.F., Mohammed, U.S.: Accurate, data-efficient, unconstrained text recognition with convolutional neural networks. Pattern Recognit. 108, 107482 (2020)","journal-title":"Pattern Recognit."}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86334-0_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:04:02Z","timestamp":1756850642000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86334-0_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863333","9783030863340"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86334-0_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"2 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lausanne","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iapr.org\/icdar2021","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"340","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"182","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"54% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.9","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.9","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Additionally, 13 competition reports are included.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}