{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T20:53:47Z","timestamp":1758056027195,"version":"3.44.0"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032046161","type":"print"},{"value":"9783032046178","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"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\/978-3-032-04617-8_11","type":"book-chapter","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T11:46:57Z","timestamp":1757936817000},"page":"184-200","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Unified Model for\u00a0Paragraph and\u00a0Line-Level Handwritten Text Recognition"],"prefix":"10.1007","author":[{"given":"Ernest Yu-Kai","family":"Chew","sequence":"first","affiliation":[]},{"given":"Adams Wai-Kin","family":"Kong","sequence":"additional","affiliation":[]},{"given":"Joo-Hwee","family":"Lim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,15]]},"reference":[{"key":"11_CR1","unstructured":"Bluche, T.: Joint line segmentation and transcription for end-to-end handwritten paragraph recognition. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Chew, E.Y.K., Kong, A.W.K., Joo-Hwee, L.: Decreasing word error rates in paragraph handwritten text recognition with synthetic data. In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2025)","DOI":"10.1109\/ICASSP49660.2025.10890316"},{"issue":"1","key":"11_CR3","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":"11_CR4","doi-asserted-by":"crossref","unstructured":"Davis, B., Morse, B., Price, B., Tensmeyer, C., Wigington, C., Morariu, V.: End-to-end document recognition and understanding with dessurt. In: European Conference on Computer Vision, pp. 280\u2013296. Springer (2022)","DOI":"10.1007\/978-3-031-25069-9_19"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Doetsch, P., Kozielski, M., Ney, H.: Fast and robust training of recurrent neural networks for offline handwriting recognition. In: 2014 14th International Conference on Frontiers in Handwriting Recognition, pp. 279\u2013284. IEEE (2014)","DOI":"10.1109\/ICFHR.2014.54"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Dreuw, P., Doetsch, P., Plahl, C., Ney, H.: Hierarchical hybrid mlp\/hmm or rather mlp features for a discriminatively trained gaussian hmm: a comparison for offline handwriting recognition. In: 2011 18th IEEE International Conference on Image Processing, pp. 3541\u20133544. IEEE (2011)","DOI":"10.1109\/ICIP.2011.6116480"},{"issue":"4","key":"11_CR7","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":"11_CR8","unstructured":"Fan, A., Grave, E., Joulin, A.: Reducing transformer depth on demand with structured dropout. In: International Conference on Learning Representations (2019)"},{"key":"11_CR9","unstructured":"Farajtabar, M., Azizan, N., Mott, A., Li, A.: Orthogonal gradient descent for continual learning. In: Chiappa, S., Calandra, R. (eds.) Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics. Proceedings of Machine Learning Research, vol.\u00a0108, pp. 3762\u20133773. PMLR, 26\u201328 August 2020, https:\/\/proceedings.mlr.press\/v108\/farajtabar20a.html"},{"key":"11_CR10","unstructured":"Garipov, T., Izmailov, P., Podoprikhin, D., Vetrov, D.P., Wilson, A.G.: Loss surfaces, mode connectivity, and fast ensembling of dnns. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Graves, A., Graves, A.: Connectionist temporal classification. In: Supervised Sequence Labelling with Recurrent Neural Networks, pp. 61\u201393 (2012)","DOI":"10.1007\/978-3-642-24797-2_7"},{"issue":"5","key":"11_CR12","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1109\/TPAMI.2008.137","volume":"31","author":"A Graves","year":"2008","unstructured":"Graves, A., Liwicki, M., Fern\u00e1ndez, S., Bertolami, R., Bunke, H., Schmidhuber, J.: A novel connectionist system for unconstrained handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31(5), 855\u2013868 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"11_CR13","unstructured":"Ilharco, G., Ribeiro, M.T., Wortsman, M., Schmidt, L., Hajishirzi, H., Farhadi, A.: Editing models with task arithmetic. In: The Eleventh International Conference on Learning Representations"},{"key":"11_CR14","unstructured":"Jin, X., Ren, X., Preotiuc-Pietro, D., Cheng, P.: Dataless knowledge fusion by merging weights of language models. arXiv preprint arXiv:2212.09849 (2022)"},{"key":"11_CR15","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Kozielski, M., Doetsch, P., Ney, H., et\u00a0al.: Improvements in rwth\u2019s system for off-line handwriting recognition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 935\u2013939. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.190"},{"key":"11_CR17","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":"11_CR18","first-page":"17703","volume":"35","author":"MS Matena","year":"2022","unstructured":"Matena, M.S., Raffel, C.A.: Merging models with fisher-weighted averaging. Adv. Neural. Inf. Process. Syst. 35, 17703\u201317716 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR19","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, pp. 1286\u20131293. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00208"},{"key":"11_CR20","first-page":"512","volume":"33","author":"B Neyshabur","year":"2020","unstructured":"Neyshabur, B., Sedghi, H., Zhang, C.: What is being transferred in transfer learning? Adv. Neural. Inf. Process. Syst. 33, 512\u2013523 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Pfitzmann, B., Auer, C., Dolfi, M., Nassar, A.S., Staar, P.: Doclaynet: a large human-annotated dataset for document-layout segmentation. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 3743\u20133751 (2022)","DOI":"10.1145\/3534678.3539043"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Pham, V., Bluche, T., Kermorvant, C., Louradour, J.: Dropout improves recurrent neural networks for handwriting recognition. In: 2014 14th International Conference on Frontiers in Handwriting Recognition, pp. 285\u2013290. IEEE (2014)","DOI":"10.1109\/ICFHR.2014.55"},{"key":"11_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.\u00a01, pp. 67\u201372. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.20"},{"key":"11_CR24","first-page":"23359","volume":"34","author":"S Santurkar","year":"2021","unstructured":"Santurkar, S., Tsipras, D., Elango, M., Bau, D., Torralba, A., Madry, A.: Editing a classifier by rewriting its prediction rules. Adv. Neural. Inf. Process. Syst. 34, 23359\u201323373 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR25","unstructured":"Shi, G., Li, Q., Zhang, W., Chen, J., Wu, X.M.: Recon: reducing conflicting gradients from the root for multi-task learning. arXiv preprint arXiv:2302.11289 (2023)"},{"issue":"1","key":"11_CR26","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":"11_CR27","unstructured":"Suteu, M., Guo, Y.: Regularizing deep multi-task networks using orthogonal gradients. arXiv preprint arXiv:1912.06844 (2019)"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Weliwitage, C., Harvey, A., Jennings, A.B.: Handwritten document offline text line segmentation. In: Digital Image Computing: Techniques and Applications, pp. 27\u201327. IEEE (2005)","DOI":"10.1109\/DICTA.2005.42"},{"key":"11_CR29","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, pp. 367\u2013383 (2018)","DOI":"10.1007\/978-3-030-01231-1_23"},{"key":"11_CR30","unstructured":"Wortsman, M., et\u00a0al.: Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. In: International Conference on Machine Learning, pp. 23965\u201323998. PMLR (2022)"},{"key":"11_CR31","unstructured":"Yadav, P., Tam, D., Choshen, L., Raffel, C.A., Bansal, M.: Ties-merging: resolving interference when merging models. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"11_CR32","unstructured":"Yu, L., Yu, B., Yu, H., Huang, F., Li, Y.: Language models are super mario: absorbing abilities from homologous models as a free lunch. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: Vsr: a unified framework for document layout analysis combining vision, semantics and relations. In: Document Analysis and Recognition\u2013ICDAR 2021: 16th International Conference, Lausanne, Switzerland, 5\u201310 September 2021, Proceedings, Part I 16, pp. 115\u2013130. Springer (2021)","DOI":"10.1007\/978-3-030-86549-8_8"},{"key":"11_CR34","doi-asserted-by":"crossref","unstructured":"Zhou, W., Ge, T., Xu, K., Wei, F., Zhou, M.: Scheduled drophead: a regularization method for transformer models. arXiv preprint arXiv:2004.13342 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.178"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04617-8_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T11:47:06Z","timestamp":1757936826000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04617-8_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,15]]},"ISBN":["9783032046161","9783032046178"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04617-8_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,15]]},"assertion":[{"value":"15 September 2025","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":"Wuhan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"16 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iapr.org\/icdar2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}