{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:51:46Z","timestamp":1757620306946,"version":"3.44.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031995644"},{"type":"electronic","value":"9783031995651"}],"license":[{"start":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T00:00:00Z","timestamp":1753833600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T00:00:00Z","timestamp":1753833600000},"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":[[2026]]},"DOI":"10.1007\/978-3-031-99565-1_29","type":"book-chapter","created":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T06:42:40Z","timestamp":1753771360000},"page":"379-390","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Mitigating Overfitting in\u00a0Fully Transformer Architectures for\u00a0Handwritten Text Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6460-1831","authenticated-orcid":false,"given":"Carlos","family":"Penarrubia","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8667-4070","authenticated-orcid":false,"given":"Jose J.","family":"Valero-Mas","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3183-2232","authenticated-orcid":false,"given":"Jorge","family":"Calvo-Zaragoza","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,30]]},"reference":[{"issue":"1","key":"29_CR1","doi-asserted-by":"publisher","first-page":"18","DOI":"10.3390\/jimaging10010018","volume":"10","author":"W AlKendi","year":"2024","unstructured":"AlKendi, W., Gechter, F., Heyberger, L., Guyeux, C.: Advancements and challenges in handwritten text recognition: a comprehensive survey. J. Imag. 10(1), 18 (2024)","journal-title":"J. Imag."},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Ansari, A., Kaur, B., Rakhra, M., Singh, A., Singh, D.: Handwritten text recognition using deep learning algorithms. In: 2022 4th International Conference on Artificial Intelligence and Speech Technology (AIST), pp.\u00a01\u20136. IEEE (2022)","DOI":"10.1109\/AIST55798.2022.10065348"},{"key":"29_CR3","unstructured":"Ba, J.L.: Layer normalization. arXiv preprint: arXiv:1607.06450 (2016)"},{"key":"29_CR4","unstructured":"Bahdanau, D.: Neural machine translation by jointly learning to align and translate. arXiv preprint: arXiv:1409.0473 (2014)"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Calvo-Zaragoza, J., Martinez-Sevilla, J.C., Penarrubia, C., Rios-Vila, A.: Optical music recognition: Recent advances, current challenges, and future directions. In: International Conference on Document Analysis and Recognition, pp. 94\u2013104. Springer (2023)","DOI":"10.1007\/978-3-031-41498-5_7"},{"key":"29_CR6","unstructured":"Chowdhury, A., Vig, L.: An efficient end-to-end neural model for handwritten text recognition. arXiv preprint: arXiv:1807.07965 (2018)"},{"issue":"7","key":"29_CR7","doi-asserted-by":"publisher","first-page":"8227","DOI":"10.1109\/TPAMI.2023.3235826","volume":"45","author":"D Coquenet","year":"2023","unstructured":"Coquenet, D., Chatelain, C., Paquet, T.: DAN: a segmentation-free document attention network for handwritten document recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(7), 8227\u20138243 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR8","unstructured":"Dosovitskiy, A.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint: arXiv:2010.11929 (2020)"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Fujitake, M.: DTrOCR: decoder-only transformer for optical character recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 8025\u20138035 (2024)","DOI":"10.1109\/WACV57701.2024.00784"},{"key":"29_CR10","unstructured":"Garrido-Munoz, C., Rios-Vila, A., Calvo-Zaragoza, J.: Handwritten text recognition: a survey. arXiv preprint: arXiv:2502.08417 (2025)"},{"key":"29_CR11","doi-asserted-by":"publisher","first-page":"100515","DOI":"10.1016\/j.cosrev.2022.100515","volume":"46","author":"T Ghosh","year":"2022","unstructured":"Ghosh, T., Sen, S., Obaidullah, S.M., Santosh, K., Roy, K., Pal, U.: Advances in online handwritten recognition in the last decades. Comput. Sci. Rev. 46, 100515 (2022)","journal-title":"Comput. Sci. Rev."},{"key":"29_CR12","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: Proceedings of the 23rd International Conference on Machine Learning, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"29_CR14","doi-asserted-by":"publisher","first-page":"108766","DOI":"10.1016\/j.patcog.2022.108766","volume":"129","author":"L Kang","year":"2022","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. Pattern Recogn. 129, 108766 (2022)","journal-title":"Pattern Recogn."},{"key":"29_CR15","unstructured":"Kingma, D.P.: Adam: a method for stochastic optimization. arXiv preprint: arXiv:1412.6980 (2014)"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Knerr, S., Augustin, E.: A neural network-hidden Markov model hybrid for cursive word recognition. In: Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No. 98EX170), vol.\u00a02, pp. 1518\u20131520. IEEE (1998)","DOI":"10.1109\/ICPR.1998.711996"},{"key":"29_CR17","unstructured":"Krishnan, P., Jawahar, C.: Generating synthetic data for text recognition. arXiv preprint: arXiv:1608.04224 (2016)"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: TrOCR: transformer-based optical character recognition with pre-trained models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 13094\u201313102 (2023)","DOI":"10.1609\/aaai.v37i11.26538"},{"key":"29_CR19","doi-asserted-by":"publisher","first-page":"110967","DOI":"10.1016\/j.patcog.2024.110967","volume":"158","author":"Y Li","year":"2025","unstructured":"Li, Y., Chen, D., Tang, T., Shen, X.: HTR-VT: handwritten text recognition with vision transformer. Pattern Recogn. 158, 110967 (2025)","journal-title":"Pattern Recogn."},{"key":"29_CR20","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)","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"29_CR21","unstructured":"Martinez-Sevilla, J.C., Rizo, D., Calvo-Zaragoza, J.: On the performance of optical music recognition in the absence of specific training data. In: ISMIR (2024)"},{"issue":"2","key":"29_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3605943","volume":"56","author":"B Min","year":"2023","unstructured":"Min, B., et al.: Recent advances in natural language processing via large pre-trained language models: a survey. ACM Comput. Surv. 56(2), 1\u201340 (2023)","journal-title":"ACM Comput. Surv."},{"issue":"8","key":"29_CR23","doi-asserted-by":"publisher","first-page":"5517","DOI":"10.1007\/s10462-020-09827-4","volume":"53","author":"SR Narang","year":"2020","unstructured":"Narang, S.R., Jindal, M.K., Kumar, M.: Ancient text recognition: a review. Artif. Intell. Rev. 53(8), 5517\u20135558 (2020). https:\/\/doi.org\/10.1007\/s10462-020-09827-4","journal-title":"Artif. Intell. Rev."},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Neto, A.F.D.S., Bezerra, B.L.D., Toselli, A.H.: Towards the natural language processing as spelling correction for offline handwritten text recognition systems. Appl. Sci. 10(21), 7711 (2020)","DOI":"10.3390\/app10217711"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Penarrubia, C., Garrido-Munoz, C., Valero-Mas, J.J., Calvo-Zaragoza, J.: Spatial context-based self-supervised learning for handwritten text recognition. arXiv preprint: arXiv:2404.11585 (2024)","DOI":"10.1007\/s11263-025-02487-3"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Penarrubia, C., Valero-Mas, J.J., Calvo-Zaragoza, J.: Contrastive self-supervised learning for optical music recognition. In: International Workshop on Document Analysis Systems, pp. 312\u2013326. Springer (2024)","DOI":"10.1007\/978-3-031-70442-0_19"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Penarrubia, C., Valero-Mas, J.J., Calvo-Zaragoza, J.: Self-supervised learning for text recognition: a critical survey. arXiv preprint: arXiv:2407.19889 (2024)","DOI":"10.1007\/s11263-025-02487-3"},{"key":"29_CR28","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.\u00a01, pp. 67\u201372. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.20"},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"R\u00edos-Vila, A., Calvo-Zaragoza, J., Paquet, T.: Sheet music transformer: end-to-end optical music recognition beyond monophonic transcription. In: International Conference on Document Analysis and Recognition, pp. 20\u201337. Springer (2024)","DOI":"10.1007\/978-3-031-70552-6_2"},{"issue":"6","key":"29_CR30","doi-asserted-by":"publisher","first-page":"1658","DOI":"10.1016\/j.patcog.2012.11.024","volume":"46","author":"V Romero","year":"2013","unstructured":"Romero, V., et al.: The ESPOSALLES database: an ancient marriage license corpus for off-line handwriting recognition. Pattern Recogn. 46(6), 1658\u20131669 (2013)","journal-title":"Pattern Recogn."},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"de\u00a0Sousa\u00a0Neto, A.F., Bezerra, B.L.D., de\u00a0Moura, G.C.D., Toselli, A.H.: Data augmentation for offline handwritten text recognition: a systematic literature review. SN Comput. Sci. 5(2), 258 (2024)","DOI":"10.1007\/s42979-023-02583-6"},{"issue":"1","key":"29_CR32","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"29_CR33","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"29_CR34","unstructured":"Vaswani, A.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"29_CR35","unstructured":"Yang, S., Xiao, W., Zhang, M., Guo, S., Zhao, J., Shen, F.: Image data augmentation for deep learning: a survey. arXiv preprint: arXiv:2204.08610 (2022)"}],"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\/978-3-031-99565-1_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:52:09Z","timestamp":1757314329000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-99565-1_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,30]]},"ISBN":["9783031995644","9783031995651"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-99565-1_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,7,30]]},"assertion":[{"value":"30 July 2025","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":"Coimbra","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ibpria2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ibpria.org\/2025\/?page=home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}