{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T11:19:38Z","timestamp":1788520778767,"version":"build-2803163510"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819543946","type":"print"},{"value":"9789819543953","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"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\/978-981-95-4395-3_29","type":"book-chapter","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T10:29:27Z","timestamp":1762770567000},"page":"418-432","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Handwritten-Text-Image Editing with\u00a0Diffusion Models and\u00a0Attention-Based Matching"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4150-0446","authenticated-orcid":false,"given":"Yuteng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6743-2972","authenticated-orcid":false,"given":"Koji","family":"Eguchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"key":"29_CR1","unstructured":"Agrawal, A., et al.: VQA: Visual question answering (2016). https:\/\/arxiv.org\/abs\/1505.00468"},{"key":"29_CR2","unstructured":"Anonymous: WD14 tagger (2023). https:\/\/github.com\/toriato\/stable-diffusion-webui-wd14-tagger"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Generic attention-model explainability for interpreting bi-modal and encoder-decoder transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 397\u2013406, October 2021","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Chen, J., Huang, Y., Lv, T., Cui, L., Chen, Q., Wei, F.: TextDiffuser: diffusion models as text painters (2023). https:\/\/arxiv.org\/abs\/2305.10855","DOI":"10.52202\/075280-0410"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Dai, G., Zhang, Y., Ke, Q., Guo, Q., Huang, S.: One-shot diffusion mimicker for handwritten text generation (2024). https:\/\/arxiv.org\/abs\/2409.04004","DOI":"10.1007\/978-3-031-73636-0_24"},{"key":"29_CR6","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models (2020). https:\/\/arxiv.org\/abs\/2006.11239"},{"key":"29_CR7","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models (2021). https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"29_CR8","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2017). https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"29_CR9","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes (2022). https:\/\/arxiv.org\/abs\/1312.6114"},{"key":"29_CR10","doi-asserted-by":"publisher","unstructured":"Kleber, F., Fiel, S., Diem, M., Sablatnig, R.: CVL database - an off-line database for writer retrieval, writer identification and word spotting, November 2018. https:\/\/doi.org\/10.5281\/zenodo.1492267","DOI":"10.5281\/zenodo.1492267"},{"key":"29_CR11","unstructured":"Liao, M., Wan, Z., Yao, C., Chen, K., Bai, X.: Real-time scene text detection with differentiable binarization (2019). https:\/\/arxiv.org\/abs\/1911.08947"},{"key":"29_CR12","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization (2019). https:\/\/arxiv.org\/abs\/1711.05101"},{"key":"29_CR13","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60, 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vision"},{"key":"29_CR14","doi-asserted-by":"publisher","unstructured":"Marti, U.V., Bunke, H.: The IAM-database: an English sentence database for offline handwriting recognition (2024). https:\/\/doi.org\/10.57702\/lyl7nrys","DOI":"10.57702\/lyl7nrys"},{"key":"29_CR15","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021). https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"29_CR16","unstructured":"Tuo, Y., Xiang, W., He, J.Y., Geng, Y., Xie, X.: AnyText: Multilingual visual text generation and editing (2024). https:\/\/arxiv.org\/abs\/2311.03054"},{"key":"29_CR17","unstructured":"Wang, P., et al.: PGNet: real-time arbitrarily-shaped text spotting with point gathering network (2021), https:\/\/arxiv.org\/abs\/2104.05458"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric (2018). https:\/\/arxiv.org\/abs\/1801.03924","DOI":"10.1109\/CVPR.2018.00068"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Zhu, S., Fang, P., Zhu, C., Zhao, Z., Xu, Q., Xue, H.: Text image inpainting via global structure-guided diffusion models (2024). https:\/\/arxiv.org\/abs\/2401.14832","DOI":"10.1609\/aaai.v38i7.28612"},{"issue":"1","key":"29_CR20","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1016\/B978-0-12-336156-1.50061-6","volume":"4","author":"KJ Zuiderveld","year":"1994","unstructured":"Zuiderveld, K.J., et al.: Contrast limited adaptive histogram equalization. Graphics Gems 4(1), 474\u2013485 (1994)","journal-title":"Graphics Gems"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4395-3_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T11:03:36Z","timestamp":1788519816000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4395-3_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,11]]},"ISBN":["9789819543946","9789819543953"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4395-3_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,11]]},"assertion":[{"value":"11 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Gold Coast, QLD","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"10 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acpr2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.acpr2025.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}