{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T14:40:04Z","timestamp":1749998404008,"version":"3.41.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031705519"},{"type":"electronic","value":"9783031705526"}],"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\/978-3-031-70552-6_23","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:02:14Z","timestamp":1725940934000},"page":"381-396","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ICDAR 2024 Competition on\u00a0Multi Font Group Recognition and\u00a0OCR"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7486-669X","authenticated-orcid":false,"given":"Janne","family":"van der Loop","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1240-5809","authenticated-orcid":false,"given":"Florian","family":"Kordon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3706-285X","authenticated-orcid":false,"given":"Martin","family":"Mayr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0455-3799","authenticated-orcid":false,"given":"Vincent","family":"Christlein","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4196-0289","authenticated-orcid":false,"given":"Fei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4485-0958","authenticated-orcid":false,"given":"Dalia","family":"Rodr\u00edguez-Salas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8065-0390","authenticated-orcid":false,"given":"Nikolaus","family":"Weichselbaumer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9153-1031","authenticated-orcid":false,"given":"Mathias","family":"Seuret","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"23_CR1","doi-asserted-by":"publisher","unstructured":"Baierer, K., et al.: OCR-D - Koordinierte F\u00f6rderinitiative zur Weiterentwicklung von Verfahren der Optical Character Recognition (OCR). OCR-D kompakt: Ergebnisse und Stand der Forschung in der F\u00f6rderinitiative. Bibliothek - forschung und Praxis 44(2), 218\u2013230 (2020). https:\/\/doi.org\/10.1515\/bfp-2020-0024","DOI":"10.1515\/bfp-2020-0024"},{"key":"23_CR2","doi-asserted-by":"publisher","unstructured":"Bautista, D., Atienza, R.: Scene text recognition with permuted autoregressive sequence models. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol. 13688, pp. 178\u2013196. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_11","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"23_CR3","unstructured":"Boenig, M., Federbusch, M., Neudecker, C.: Ground truth guidelines. OCR-D: DFG-funded initiative for optical character recognition development (2023). https:\/\/ocr-d.de\/en\/gt-guidelines\/trans\/level_2_2.html"},{"key":"23_CR4","doi-asserted-by":"publisher","unstructured":"Chng, C.K., et al.: ICDAR2019 robust reading challenge on arbitrary-shaped text - RRC-ArT. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 1571\u20131576 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00252","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Degtyarenko, I., et al.: SDRV: real-time on-device subtitles detection, recognition and voicing. In: International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSPW59220.2023.10192952"},{"key":"23_CR6","doi-asserted-by":"publisher","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2315\u20132324 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.254","DOI":"10.1109\/CVPR.2016.254"},{"key":"23_CR7","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227 (2014)"},{"key":"23_CR8","doi-asserted-by":"publisher","unstructured":"Kaddas, P., Gatos, B., Palaiologos, K., Christopoulou, K., Kritsis, K.: Text line detection and recognition of Greek polytonic documents. In: Coustaty, M., Forn\u00e9s, A. (eds.) Document Analysis and Recognition \u2013 ICDAR Workshops, pp. 213\u2013225. Springer Nature Switzerland, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41501-2_15","DOI":"10.1007\/978-3-031-41501-2_15"},{"key":"23_CR9","doi-asserted-by":"publisher","unstructured":"Kaddas, P., Palaiologos, K., Gatos, B., Katsouros, V., Christopoulou, K.: A system for processing and recognition of Greek Byzantine and Post-Byzantine documents. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) International Conference on Document Analysis and Recognition (ICDAR), pp. 366\u2013376. Springer Nature Switzerland, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41685-9_23","DOI":"10.1007\/978-3-031-41685-9_23"},{"key":"23_CR10","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"23_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1007\/978-3-030-86337-1_31","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"M Ki\u0161\u0161","year":"2021","unstructured":"Ki\u0161\u0161, M., Bene\u0161, K., Hradi\u0161, M.: AT-ST: self-training adaptation strategy for OCR in domains with limited transcriptions. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12824, pp. 463\u2013477. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86337-1_31"},{"key":"23_CR12","unstructured":"van\u00a0der Loop, J., Seuret, M., Weichselbaumer, N., Christlein, V.: Optical character recognition for pages from early printed books with multiple font groups. Gutenberg-Jahrbuch, pp. 53\u201363 (2024)"},{"key":"23_CR13","unstructured":"Nicolaou, A.: (F)ast (R)ectangle (A)nnotation (T)ool (2022). https:\/\/github.com\/anguelos\/frat"},{"key":"23_CR14","unstructured":"Pavao, A., et al.: CodaLab competitions: an open source platform to organize scientific challenges. Technical Report (2022). https:\/\/hal.inria.fr\/hal-03629462v1"},{"key":"23_CR15","doi-asserted-by":"publisher","unstructured":"Sarshogh, M.R., Hines, K.: A multi-task network for localization and recognition of text in images. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 494\u2013501 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00085","DOI":"10.1109\/ICDAR.2019.00085"},{"key":"23_CR16","doi-asserted-by":"publisher","unstructured":"Seuret, M., Limbach, S., Weichselbaumer, N., Maier, A., Christlein, V.: Dataset of pages from early printed books with multiple font groups. In: International Workshop on Historical Document Imaging and Processing (HIP), pp. 1\u20136 (2019). https:\/\/doi.org\/10.1145\/3352631.3352640","DOI":"10.1145\/3352631.3352640"},{"key":"23_CR17","doi-asserted-by":"publisher","unstructured":"Seuret, M., et al.: Combining OCR models for reading early modern books. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) International Conference on Document Analysis and Recognition (ICDAR), pp. 342\u2013357. Springer Nature Switzerland, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41734-4_21","DOI":"10.1007\/978-3-031-41734-4_21"},{"key":"23_CR18","doi-asserted-by":"publisher","unstructured":"Seuret, M., et al.: ICDAR 2021 Competition on historical document classification. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) Document Analysis and Recognition - ICDAR, Lecture Notes in Computer Science, pp. 618\u2013634. Springer International Publishing, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86337-1_41","DOI":"10.1007\/978-3-030-86337-1_41"},{"key":"23_CR19","doi-asserted-by":"publisher","unstructured":"Shi, B., et al.: ICDAR2017 competition on reading Chinese text in the wild. In: International Conference on Document Analysis and Recognition (ICDAR), vol. 01, pp. 1429\u20131434 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.233","DOI":"10.1109\/ICDAR.2017.233"},{"key":"23_CR20","doi-asserted-by":"publisher","unstructured":"Singh, A., Pang, G., Toh, M., Huang, J., Galuba, W., Hassner, T.: TextOCR: towards large-scale end-to-end reasoning for arbitrary-shaped scene text. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8798\u20138808 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00869","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"23_CR21","doi-asserted-by":"publisher","unstructured":"Smith, L.N., Topin, N.: Super-convergence: very fast training of neural networks using large learning rates. In: Pham, T. (ed.) Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications, vol. 11006, p. 1100612. International Society for Optics and Photonics, SPIE (2019). https:\/\/doi.org\/10.1117\/12.2520589","DOI":"10.1117\/12.2520589"},{"key":"23_CR22","doi-asserted-by":"publisher","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: RoFormer: enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024) https:\/\/doi.org\/10.1016\/j.neucom.2023.127063, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0925231223011864","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"23_CR23","doi-asserted-by":"publisher","unstructured":"Sun, Y., et al.: ICDAR 2019 competition on large-scale street view text with partial labeling. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 1557\u20131562 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00250","DOI":"10.1109\/ICDAR.2019.00250"},{"key":"23_CR24","unstructured":"Veit, A., Matera, T., Neumann, L., Matas, J., Belongie, S.: COCO-text: dataset and benchmark for text detection and recognition in natural images. arXiv preprint arXiv:1601.07140 (2016)"},{"key":"23_CR25","doi-asserted-by":"publisher","unstructured":"Weichselbaumer, N., Seuret, M., Limbach, S., Dong, R., Burghardt, M., Christlein, V.: New approaches to OCR for early printed books. Digitalia 15(2), 74\u201387 (2020). https:\/\/doi.org\/10.36181\/digitalia-00015","DOI":"10.36181\/digitalia-00015"},{"key":"23_CR26","unstructured":"Weichselbaumer, N., Seuret, M., Limbach, S., Hinrichsen, L., Maier, A., Christlein, V.: The rapid rise of Fraktur. In: Digital Humanities im deutschsprachigen Raum, pp. 292\u2013232 (2020)"},{"key":"23_CR27","unstructured":"Wick, C., Reul, C., Puppe, F.: Calamari-a high-performance TensorFlow-based deep learning package for optical character recognition. arXiv preprint arXiv:1807.02004 (2018)"},{"key":"23_CR28","doi-asserted-by":"publisher","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.) 15th IAPR International Workshop on Document Analysis Systems (DAS), pp. 260\u2013274. Springer International Publishing, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-06555-2_18","DOI":"10.1007\/978-3-031-06555-2_18"},{"key":"23_CR29","doi-asserted-by":"publisher","unstructured":"Zhang, R., et al.: ICDAR 2019 robust reading challenge on reading Chinese text on signboard. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 1577\u20131581 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00253","DOI":"10.1109\/ICDAR.2019.00253"},{"key":"23_CR30","unstructured":"Zhang, Y., Gueguen, L., Zharkov, I., Zhang, P., Seifert, K., Kadlec, B.: Uber-text: a large-scale dataset for optical character recognition from street-level imagery. In: SUNw: Scene Understanding Workshop (CVPR), vol. 2017, p. 5 (2017)"},{"issue":"12","key":"23_CR31","doi-asserted-by":"publisher","first-page":"5586","DOI":"10.1109\/TKDE.2021.3070203","volume":"34","author":"Y Zhang","year":"2022","unstructured":"Zhang, Y., Yang, Q.: A survey on multi-task learning. Trans. Knowl. Data Eng. 34(12), 5586\u20135609 (2022). https:\/\/doi.org\/10.1109\/TKDE.2021.3070203","journal-title":"Trans. Knowl. Data Eng."}],"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\/978-3-031-70552-6_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T14:07:24Z","timestamp":1749996444000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70552-6_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705519","9783031705526"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70552-6_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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"}}]}}