{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T00:45:17Z","timestamp":1777077917459,"version":"3.51.4"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031048807","type":"print"},{"value":"9783031048814","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-04881-4_37","type":"book-chapter","created":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T15:02:54Z","timestamp":1650898974000},"page":"470-481","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["On the\u00a0Use of\u00a0Transformers for\u00a0End-to-End Optical Music Recognition"],"prefix":"10.1007","author":[{"given":"Antonio","family":"R\u00edos-Vila","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jos\u00e9 M.","family":"I\u00f1esta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jorge","family":"Calvo-Zaragoza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,4,26]]},"reference":[{"key":"37_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"37_CR2","doi-asserted-by":"crossref","unstructured":"Bar\u00f3, A., Badal, C., Forn\u00e9s, A.: Handwritten historical music recognition by sequence-to-sequence with attention mechanism. In: 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 205\u2013210 (2020)","DOI":"10.1109\/ICFHR2020.2020.00046"},{"key":"37_CR3","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1080\/09298215.2015.1045424","volume":"44","author":"D Byrd","year":"2015","unstructured":"Byrd, D., Simonsen, J.: Towards a standard testbed for optical music recognition: definitions, metrics, and page images. J. New Music Res. 44, 169\u2013195 (2015)","journal-title":"J. New Music Res."},{"issue":"4","key":"37_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3397499","volume":"53","author":"J Calvo-Zaragoza","year":"2020","unstructured":"Calvo-Zaragoza, J., Haji\u010d, J., Jr., Pacha, A.: Understanding optical music recognition. ACM Comput. Surv. 53(4), 1\u201335 (2020)","journal-title":"ACM Comput. Surv."},{"key":"37_CR5","unstructured":"Calvo-Zaragoza, J., Rizo, D.: Camera-PrIMuS: neural end-to-end optical music recognition on realistic monophonic scores. In: Proceedings of the 19th International Society for Music Information Retrieval Conference, ISMIR 2018, Paris, France, September 23\u201327, 2018, pp. 248\u2013255 (2018)"},{"key":"37_CR6","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.patrec.2019.08.021","volume":"128","author":"J Calvo-Zaragoza","year":"2019","unstructured":"Calvo-Zaragoza, J., Toselli, A.H., Vidal, E.: Handwritten music recognition for mensural notation with convolutional recurrent neural networks. Pattern Recogn. Lett. 128, 115\u2013121 (2019)","journal-title":"Pattern Recogn. Lett."},{"key":"37_CR7","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. CoRR abs\/1810.04805 (2018)"},{"key":"37_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. CoRR abs\/2010.11929 (2020)"},{"issue":"4","key":"37_CR9","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/s11023-020-09548-1","volume":"30","author":"L Floridi","year":"2020","unstructured":"Floridi, L., Chiriatti, M.: Gpt-3: Its nature, scope, limits, and consequences. Mind. Mach. 30(4), 681\u2013694 (2020)","journal-title":"Mind. Mach."},{"key":"37_CR10","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F.J., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the Twenty-Third International Conference on Machine Learning, (ICML 2006), Pittsburgh, Pennsylvania, USA, June 25\u201329, 2006, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"37_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. CoRR abs\/2005.13044 (2020)"},{"key":"37_CR12","unstructured":"Khan, S.H., Naseer, M., Hayat, M., Zamir, S.W., Khan, F.S., Shah, M.: Transformers in vision: A survey. CoRR abs\/2101.01169 (2021)"},{"issue":"9","key":"37_CR13","doi-asserted-by":"publisher","first-page":"1488","DOI":"10.3390\/app8091488","volume":"8","author":"A Pacha","year":"2018","unstructured":"Pacha, A., Haji\u010d, J., Jr., Calvo-Zaragoza, J.: A baseline for general music object detection with deep learning. Appl. Sci. 8(9), 1488 (2018)","journal-title":"Appl. Sci."},{"key":"37_CR14","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language Models are Unsupervised Multitask Learners (2019)"},{"issue":"3","key":"37_CR15","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/s13735-012-0004-6","volume":"1","author":"A Rebelo","year":"2012","unstructured":"Rebelo, A., Fujinaga, I., Paszkiewicz, F., Mar\u00e7al, A.R.S., Guedes, C., Cardoso, J.S.: Optical music recognition: state-of-the-art and open issues. Int. J. Multim. Inf. Retr. 1(3), 173\u2013190 (2012)","journal-title":"Int. J. Multim. Inf. Retr."},{"key":"37_CR16","doi-asserted-by":"crossref","unstructured":"R\u00edos-Vila, A., Calvo-Zaragoza, J., I\u00f1esta, J.M.: Exploring the two-dimensional nature of music notation for score recognition with end-to-end approaches. In: 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 193\u2013198 (2020)","DOI":"10.1109\/ICFHR2020.2020.00044"},{"key":"37_CR17","doi-asserted-by":"crossref","unstructured":"Singh, S.S., Karayev, S.: Full page handwriting recognition via image to sequence extraction. arXiv preprint arXiv:2103.06450 (2021)","DOI":"10.1007\/978-3-030-86334-0_4"},{"key":"37_CR18","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104\u20133112 (2014)"},{"key":"37_CR19","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jegou, H.: Training data-efficient image transformers & distillation through attention. In: Proceedings of the 38th International Conference on Machine Learning, vol. 139, pp. 10347\u201310357 (2021)"},{"key":"37_CR20","unstructured":"Vaswani, A., et al.: Attention is all you need. CoRR abs\/1706.03762 (2017)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-04881-4_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T00:01:31Z","timestamp":1777075291000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-04881-4_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031048807","9783031048814"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-04881-4_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"26 April 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IbPRIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Iberian Conference on Pattern Recognition and Image Analysis","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Aveiro","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 May 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 May 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ibpria2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ibpria.org\/2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"72","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":"54","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":"75% - 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":"3","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":"3","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}