{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:05:35Z","timestamp":1778079935658,"version":"3.51.4"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031705458","type":"print"},{"value":"9783031705465","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70546-5_25","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:02:47Z","timestamp":1725944567000},"page":"425-440","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Enhancing CRNN HTR Architectures with\u00a0Transformer Blocks"],"prefix":"10.1007","author":[{"given":"George","family":"Retsinas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstantina","family":"Nikolaidou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giorgos","family":"Sfikas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"25_CR1","unstructured":"Barrere, K., Soullard, Y., Lemaitre, A., Co\u00fcasnon, B.: Transformers for historical handwritten text recognition. In: Doctoral Consortium-ICDAR 2021 (2021)"},{"key":"25_CR2","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/978-3-031-06555-2_19","volume-title":"Document Analysis Systems: 15th IAPR International Workshop, DAS 2022, La Rochelle, France, May 22\u201325, 2022, Proceedings","author":"K Barrere","year":"2022","unstructured":"Barrere, K., Soullard, Y., Lemaitre, A., Co\u00fcasnon, B.: A light transformer-based architecture for\u00a0handwritten text recognition. In: Uchida, S., Barney, E., Eglin, V. (eds.) Document Analysis Systems: 15th IAPR International Workshop, DAS 2022, La Rochelle, France, May 22\u201325, 2022, Proceedings, pp. 275\u2013290. Springer International Publishing, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-06555-2_19"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Bhunia, A.K., Khan, S., Cholakkal, H., Anwer, R.M., Khan, F.S., Shah, M.: Handwriting transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1086\u20131094 (2021)","DOI":"10.1109\/ICCV48922.2021.00112"},{"issue":"10","key":"25_CR4","doi-asserted-by":"publisher","first-page":"2066","DOI":"10.1109\/TPAMI.2011.22","volume":"33","author":"AL Bianne-Bernard","year":"2011","unstructured":"Bianne-Bernard, A.L., Menasri, F., Mohamad, R.A.H., Mokbel, C., Kermorvant, C., Likforman-Sulem, L.: Dynamic and contextual information in hmm modeling for handwritten word recognition. IEEE Trans. Pattern Anal. Mach. Intell. 33(10), 2066\u20132080 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"25_CR5","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1109\/TPAMI.2022.3144899","volume":"45","author":"D Coquenet","year":"2022","unstructured":"Coquenet, D., Chatelain, C., Paquet, T.: End-to-end handwritten paragraph text recognition using a vertical attention network. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 508\u2013524 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR6","unstructured":"Diaz, D.H., Qin, S., Ingle, R.R., Fujii, Y., Bissacco, A.: Rethinking Text Line Recognition Models. ArXiv:abs\/2104.07787 (2021)"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Dutta, K., et al.: Improving CNN-RNN Hybrid Networks for Handwriting Recognition. 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 80\u201385 (2018)","DOI":"10.1109\/ICFHR-2018.2018.00023"},{"key":"25_CR8","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1007\/978-3-031-21648-0_27","volume-title":"Frontiers in Handwriting Recognition: 18th International Conference, ICFHR 2022, Hyderabad, India, December 4\u20137, 2022, Proceedings","author":"R d\u2019Arce","year":"2022","unstructured":"d\u2019Arce, R., Norton, T., Hannuna, S., Cristianini, N.: Self-attention networks for\u00a0non-recurrent handwritten text recognition. In: Porwal, U., Forn\u00e9s, A., Shafait, F. (eds.) Frontiers in Handwriting Recognition: 18th International Conference, ICFHR 2022, Hyderabad, India, December 4\u20137, 2022, Proceedings, pp. 389\u2013403. Springer International Publishing, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-21648-0_27"},{"issue":"4","key":"25_CR9","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1109\/TPAMI.2010.141","volume":"33","author":"S Espana-Boquera","year":"2010","unstructured":"Espana-Boquera, S., Castro-Bleda, M.J., Gorbe-Moya, J., Zamora-Martinez, F.: Improving offline handwritten text recognition with Hybrid HMM\/ANN models. IEEE Trans. Pattern Anal. Mach. Intell. 33(4), 767\u2013779 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR10","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":"25_CR11","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1016\/j.patrec.2012.09.002","volume":"35","author":"A Gim\u00e9nez","year":"2014","unstructured":"Gim\u00e9nez, A., Khoury, I., Andr\u00e9s-Ferrer, J., Juan, A.: Handwriting word recognition using windowed Bernoulli HMMs. Pattern Recogn. Lett. 35, 149\u2013156 (2014)","journal-title":"Pattern Recogn. Lett."},{"key":"25_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"},{"issue":"10","key":"25_CR13","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.1109\/TNNLS.2016.2582924","volume":"28","author":"K Greff","year":"2016","unstructured":"Greff, K., Srivastava, R.K., Koutn\u00edk, J., Steunebrink, B.R., Schmidhuber, J.: LSTM: a search space odyssey. IEEE Trans. Neural Netw. Learn. Syst. 28(10), 2222\u20132232 (2016)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Grosicki, E., Carr\u00e9, M., Brodin, J.M., Geoffrois, E.: Results of the RIMES evaluation campaign for handwritten mail processing. In: 2009 10th International Conference on Document Analysis and Recognition, pp. 941\u2013945. IEEE (2009)","DOI":"10.1109\/ICDAR.2009.224"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"25_CR16","doi-asserted-by":"publisher","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":"25_CR17","unstructured":"Keskar, N.S., Mudigere, D., Nocedal, J., Smelyanskiy, M., Tang, P.T.P.: On large-batch training for deep learning: Generalization gap and sharp minima (2017)"},{"key":"25_CR18","unstructured":"Li, M., et al.: TrOCR: transformer-based optical character recognition with pre-trained models. In: AAAI Conference on Artificial Intelligence (2021)"},{"key":"25_CR19","unstructured":"Loshchilov, I., Hutter, F.: Decoupled Weight Decay Regularization. In: International Conference on Learning Representations (2017)"},{"key":"25_CR20","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/978-3-030-68787-8_18","volume-title":"Pattern Recognition. ICPR International Workshops and Challenges: Virtual Event, January 10-15, 2021, Proceedings, Part VII","author":"K Markou","year":"2021","unstructured":"Markou, K., et al.: A convolutional recurrent neural network for the handwritten text recognition of historical greek manuscripts. In: Del Bimbo, A., et al. (eds.) Pattern Recognition. ICPR International Workshops and Challenges: Virtual Event, January 10-15, 2021, Proceedings, Part VII, pp. 249\u2013262. Springer International Publishing, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-68787-8_18"},{"key":"25_CR21","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":"25_CR22","unstructured":"Mehta, S., Rastegari, M.: MobileViT: light-weight, general-purpose, and mobile-friendly vision transformer. In: International Conference on Learning Representations (2021)"},{"key":"25_CR23","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":"25_CR24","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":"25_CR25","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/978-3-031-06555-2_17","volume-title":"Document Analysis Systems: 15th IAPR International Workshop, DAS 2022, La Rochelle, France, May 22\u201325, 2022, Proceedings","author":"G Retsinas","year":"2022","unstructured":"Retsinas, G., Sfikas, G., Gatos, B., Nikou, C.: Best practices for a handwritten text recognition system. In: Uchida, S., Barney, E., Eglin, V. (eds.) Document Analysis Systems: 15th IAPR International Workshop, DAS 2022, La Rochelle, France, May 22\u201325, 2022, Proceedings, pp. 247\u2013259. Springer International Publishing, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-06555-2_17"},{"key":"25_CR26","doi-asserted-by":"publisher","unstructured":"Retsinas, G., Sfikas, G., Nikou, C., Maragos, P.: Deformation-Invariant networks for handwritten text recognition. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 949\u2013953 (2021). https:\/\/doi.org\/10.1109\/ICIP42928.2021.9506414","DOI":"10.1109\/ICIP42928.2021.9506414"},{"key":"25_CR27","unstructured":"Retsinas, G., Sfikas, G., Nikou, C., Maragos, P.: From Seq2Seq recognition to handwritten word embeddings. In: Proceedings of the British Machine Vision Conference (BMVC) (2021)"},{"key":"25_CR28","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1007\/978-3-031-41685-9_13","volume-title":"Document Analysis and Recognition - ICDAR 2023: 17th International Conference, San Jos\u00e9, CA, USA, August 21\u201326, 2023, Proceedings, Part IV","author":"G Sfikas","year":"2023","unstructured":"Sfikas, G., Retsinas, G., Dimitrakopoulos, P., Gatos, B., Nikou, C.: Shared-operation hypercomplex networks for\u00a0handwritten text recognition. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) Document Analysis and Recognition - ICDAR 2023: 17th International Conference, San Jos\u00e9, CA, USA, August 21\u201326, 2023, Proceedings, Part IV, pp. 200\u2013216. Springer Nature Switzerland, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41685-9_13"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Tassopoulou, V., Retsinas, G., Maragos, P.: Enhancing handwritten text recognition with n-gram sequence decomposition and multitask learning. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 10555\u201310560. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412351"},{"key":"25_CR30","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Neural Information Processing Systems (2017)"},{"key":"25_CR31","unstructured":"Wang, T., et al.: Decoupled attention network for text recognition. In: AAAI Conference on Artificial Intelligence (2019)"},{"key":"25_CR32","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1007\/978-3-030-86334-0_8","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021: 16th International Conference, Lausanne, Switzerland, September 5\u201310, 2021, Proceedings, Part III","author":"C Wick","year":"2021","unstructured":"Wick, C., Z\u00f6llner, J., Gr\u00fcning, T.: Transformer for handwritten text recognition using bidirectional post-decoding. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) Document Analysis and Recognition \u2013 ICDAR 2021: 16th International Conference, Lausanne, Switzerland, September 5\u201310, 2021, Proceedings, Part III, pp. 112\u2013126. Springer International Publishing, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86334-0_8"},{"key":"25_CR33","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1007\/978-3-031-06555-2_18","volume-title":"Document Analysis Systems: 15th IAPR International Workshop, DAS 2022, La Rochelle, France, May 22\u201325, 2022, Proceedings","author":"C Wick","year":"2022","unstructured":"Wick, C., Z\u00f6llner, J., Gr\u00fcning, T.: Rescoring sequence-to-sequence models for text line recognition with CTC-prefixes. In: Uchida, S., Barney, E., Eglin, V. (eds.) Document Analysis Systems: 15th IAPR International Workshop, DAS 2022, La Rochelle, France, May 22\u201325, 2022, Proceedings, pp. 260\u2013274. Springer International Publishing, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-06555-2_18"},{"key":"25_CR34","first-page":"30392","volume":"34","author":"T Xiao","year":"2021","unstructured":"Xiao, T., Singh, M., Mintun, E., Darrell, T., Doll\u00e1r, P., Girshick, R.: Early convolutions help transformer see better. Adv. Neural. Inf. Process. Syst. 34, 30392\u201330400 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR35","doi-asserted-by":"publisher","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 Recogn. 108, 107482 (2020)","journal-title":"Pattern Recogn."},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, X., Su, Y., Tripathi, S., Tu, Z.: Text spotting transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9519\u20139528 (2022)","DOI":"10.1109\/CVPR52688.2022.00930"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70546-5_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:08:24Z","timestamp":1725944904000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70546-5_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705458","9783031705465"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70546-5_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"11 September 2024","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":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2024.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}