{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T18:22:07Z","timestamp":1787509327632,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032360380","type":"print"},{"value":"9783032360397","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-36039-7_24","type":"book-chapter","created":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T18:07:21Z","timestamp":1787508441000},"page":"405-417","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Vision-Language Model Based Transfer Learning for\u00a0Historical Document Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4587-1655","authenticated-orcid":false,"given":"Yifan","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7793-1039","authenticated-orcid":false,"given":"Liangrui","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0433-1662","authenticated-orcid":false,"given":"Tianqi","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1422-5189","authenticated-orcid":false,"given":"Di","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3539-5163","authenticated-orcid":false,"given":"Kemeng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0846-6516","authenticated-orcid":false,"given":"Shuo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3726-6096","authenticated-orcid":false,"given":"Zhiyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6569-3457","authenticated-orcid":false,"given":"Yuyang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Hajebrahimi, A., Santoso, M.E., Kov\u00e1cs, M., Kryssanov, V.V.: Few-shot learning for character recognition in Persian historical documents. In: Machine Learning, Optimization, and Data Science (LOD 2023), pp. 259\u2013273. Springer (2024)","DOI":"10.1007\/978-3-031-53969-5_20"},{"key":"24_CR2","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: International Conference on Machine Learning, pp. 2790\u20132799. PMLR (2019)"},{"key":"24_CR3","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2022)"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Kim, G., et al.: OCR-free document understanding transformer. In: European Conference on Computer Vision, pp. 498\u2013517. Springer (2022)","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"24_CR5","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":"24_CR6","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Reul, C., Tomasek, S., Langhanki, F., Springmann, U.: Open source handwritten text recognition on medieval manuscripts using mixed models and document-specific finetuning. In: Document Analysis Systems \u2013 15th IAPR International Workshop, DAS 2022. LNCS, vol. 13237, pp. 414\u2013428. Springer (2022)","DOI":"10.1007\/978-3-031-06555-2_28"},{"key":"24_CR8","doi-asserted-by":"publisher","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015. Lecture Notes in Computer Science, vol.\u00a09351, pp. 234\u2013241. Springer (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"24_CR9","doi-asserted-by":"publisher","unstructured":"Sharma, S., Simonetta, F.: Understanding transformer-based OCR for medieval manuscripts: a systematic ablation study and inspection analysis. Research Square preprint (2025). https:\/\/doi.org\/10.21203\/rs.3.rs-8109357\/v1","DOI":"10.21203\/rs.3.rs-8109357\/v1"},{"issue":"1","key":"24_CR10","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1038\/s41597-025-04495-x","volume":"12","author":"Y Shi","year":"2025","unstructured":"Shi, Y., Peng, D., Zhang, Y., Cao, J., Jin, L.: A large-scale dataset for Chinese historical document recognition and analysis. Sci. Data 12(1), 169 (2025)","journal-title":"Sci. Data"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Wang, K., Wu, T., Shi, Y., Chen, C.: AttGraph disentangling confusable ancient Chinese characters via component-correlation synergy. NPJ Heritage Sci. 14(1), 7 (2026)","DOI":"10.1038\/s40494-025-02278-6"},{"key":"24_CR12","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1007\/s44443-025-00386-8","volume":"37","author":"Y Wang","year":"2025","unstructured":"Wang, Y., et al.: FFSSC: a framework for discovering new classes of ancient texts based on feature fusion and semi-supervised clustering. J. King Saud Univ. Comput. Info. Sci. 37, 359 (2025)","journal-title":"J. King Saud Univ. Comput. Info. Sci."},{"key":"24_CR13","unstructured":"Wei, H., et al.: General OCR theory: towards OCR-2.0 via a unified end-to-end model (2024). arXiv:2409.01704 arXiv preprint"},{"key":"24_CR14","unstructured":"Yu, H., et al.: Benchmarking vision-language models on Chinese ancient documents: from OCR to knowledge reasoning. CoRR abs\/2509.09731 (2025). https:\/\/doi.org\/10.48550\/arXiv.2509.09731"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, J.O., Sax, A., Zamir, A., Guibas, L., Malik, J.: Side-tuning: a baseline for network adaptation via additive side networks. In: European Conference on Computer Vision, pp. 698\u2013714. Springer (2020)","DOI":"10.1007\/978-3-030-58580-8_41"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Zhao, M., Jin, X., Wang, G., Zhao, Y.: Zero-shot character recognition method of Korean ancient documents based on the Chinese and Korean characters unified IDS encoding. In: International Conference on Advanced Data Mining and Applications, pp. 267\u2013280. Springer (2025)","DOI":"10.1007\/978-981-95-3453-1_18"},{"key":"24_CR17","unstructured":"Zhao, T., et al.: Dream: document recognition with explicit adaptive memory. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2715\u20132724 (2026)"},{"issue":"7","key":"24_CR18","doi-asserted-by":"publisher","first-page":"2182","DOI":"10.3390\/s24072182","volume":"24","author":"Y Zheng","year":"2024","unstructured":"Zheng, Y., Chen, Y., Wang, X., Qi, D., Yan, Y.: Ancient Chinese character recognition with improved swin-Transformer and flexible data enhancement strategies. Sensors 24(7), 2182 (2024)","journal-title":"Sensors"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-36039-7_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T18:07:22Z","timestamp":1787508442000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36039-7_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"ISBN":["9783032360380","9783032360397"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36039-7_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,24]]},"assertion":[{"value":"24 August 2026","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":"Vienna","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Austria","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}