{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:00:57Z","timestamp":1783530057985,"version":"3.55.0"},"publisher-location":"Cham","reference-count":33,"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_4","type":"book-chapter","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T20:16:02Z","timestamp":1630700162000},"page":"55-69","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":58,"title":["Full Page Handwriting Recognition via Image to Sequence Extraction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5323-9678","authenticated-orcid":false,"given":"Sumeet S.","family":"Singh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergey","family":"Karayev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"4_CR1","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer (2020)"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Bluche, T., Messina, R.: Gated convolutional recurrent neural networks for multilingual handwriting recognition. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 646\u2013651 (2017)","DOI":"10.1109\/ICDAR.2017.111"},{"key":"4_CR3","unstructured":"Bluche, T.: Joint line segmentation and transcription for end-to-end handwritten paragraph recognition. arXiv:1604.08352 (2016)"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Bluche, T., Louradour, J., Messina, R.O.: Scan, attend and read: end-to-end handwritten paragraph recognition with MDLSTM attention. CoRR arxiv:1604.03286 (2016)","DOI":"10.1109\/ICDAR.2017.174"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q.V., Salakhutdinov, R.: Transformer-XL: attentive language models beyond a fixed-length context (2019)","DOI":"10.18653\/v1\/P19-1285"},{"key":"4_CR6","unstructured":"Deng, Y., Kanervisto, A., Ling, J., Rush, A.M.: Image-to-markup generation with coarse-to-fine attention. In: ICML (2017)"},{"key":"4_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding (2019)"},{"key":"4_CR8","unstructured":"Graves, A.: Supervised sequence labelling with recurrent neural networks. In: Studies in Computational Intelligence (2008)"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: ICML 2006 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"4_CR10","unstructured":"Graves, A., Schmidhuber, J.: Offline handwriting recognition with multidimensional recurrent neural networks. In: NIPS (2008)"},{"key":"4_CR11","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR arxiv:1512.03385 (2015)"},{"key":"4_CR12","unstructured":"Hendrycks, D., Gimpel, K.: Bridging nonlinearities and stochastic regularizers with gaussian error linear units. CoRR arxiv:abs\/1606.08415 (2016)"},{"key":"4_CR13","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 (2020)"},{"key":"4_CR14","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2017)"},{"issue":"11","key":"4_CR15","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"4_CR16","doi-asserted-by":"publisher","unstructured":"Ly, N.T., Nguyen, C.T., Nakagawa, M.: An attention-based end-to-end model for multiple text lines recognition in japanese historical documents. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 629\u2013634 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00106","DOI":"10.1109\/ICDAR.2019.00106"},{"key":"4_CR17","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. Recogn. 5, 39\u201346 (2002). https:\/\/doi.org\/10.1007\/s100320200071","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"4_CR18","unstructured":"Merity, S., Xiong, C., Bradbury, J., Socher, R.: Pointer sentinel mixture models. CoRR arxiv:abs\/1609.07843 (2016)"},{"key":"4_CR19","unstructured":"Open SLR: Aachen data splits (train, test, val) for the IAM dataset. https:\/\/www.openslr.org\/56\/. Identifier: SLR56"},{"key":"4_CR20","unstructured":"Parmar, N., et al.: Image transformer. Shazeer (2018)"},{"key":"4_CR21","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019 Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems vol. 32, pp. 8024\u20138035. Curran Associates Inc. (2019). http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"4_CR22","unstructured":"Pham, V., Kermorvant, C., Louradour, J.: Dropout improves recurrent neural networks for handwriting recognition. CoRR arxiv:1312.4569 (2013)"},{"key":"4_CR23","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 (2017)","DOI":"10.1109\/ICDAR.2017.20"},{"key":"4_CR24","unstructured":"Radford, A.: Improving language understanding by generative pre-training (2018)"},{"key":"4_CR25","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer (2020)"},{"key":"4_CR26","unstructured":"Singh, S.S.: Teaching machines to code: neural markup generation with visual attention. CoRR arxiv:1802.05415 (2018)"},{"key":"4_CR27","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. CoRR arxiv:1409.3215 (2014)"},{"key":"4_CR28","unstructured":"Vaswani, A., et al.: Attention is all you need. CoRR arxiv:1706.03762 (2017)"},{"key":"4_CR29","unstructured":"Vaswani, A., et al.: Tensor2Tensor for neural machine translation. CoRR arxiv:1803.07416 (2018)"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Doetsch, P., Ney, H.: Handwriting recognition with large multidimensional long short-term memory recurrent neural networks. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 228\u2013233 (2016)","DOI":"10.1109\/ICFHR.2016.0052"},{"key":"4_CR31","unstructured":"Wang, T., et al.: Decoupled attention network for text recognition (2019)"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Wigington, C., Tensmeyer, C., Davis, B., Barrett, W., Price, B., Cohen, S.: Start, follow, read: end-to-end full-page handwriting recognition. In: Proceedings of the European Conference on Computer Vision (ECCV), September 2018","DOI":"10.1007\/978-3-030-01231-1_23"},{"key":"4_CR33","unstructured":"Xu, K.,et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML (2015)"}],"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_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:07:51Z","timestamp":1756850871000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86334-0_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863333","9783030863340"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86334-0_4","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)"}}]}}