{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T16:59:06Z","timestamp":1778345946872,"version":"3.51.4"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031736353","type":"print"},{"value":"9783031736360","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T00:00:00Z","timestamp":1730764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T00:00:00Z","timestamp":1730764800000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73636-0_24","type":"book-chapter","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T15:03:58Z","timestamp":1730732638000},"page":"410-427","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["One-DM: One-Shot Diffusion Mimicker for\u00a0Handwritten Text Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8864-908X","authenticated-orcid":false,"given":"Gang","family":"Dai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2125-1074","authenticated-orcid":false,"given":"Yifan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1393-3059","authenticated-orcid":false,"given":"Quhui","family":"Ke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5347-6198","authenticated-orcid":false,"given":"Qiangya","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5544-4544","authenticated-orcid":false,"given":"Shuangping","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,5]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Aksan, E., Pece, F., Hilliges, O.: DeepWriting: making digital ink editable via deep generative modeling. In: ACM Conference on Human Factors in Computing Systems, pp. 1\u201314 (2018)","DOI":"10.1145\/3173574.3173779"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Alonso, E., Moysset, B., Messina, R.: Adversarial generation of handwritten text images conditioned on sequences, In: ICDAR, pp. 481\u2013486 (2019)","DOI":"10.1109\/ICDAR.2019.00083"},{"key":"24_CR3","unstructured":"Betker, J., et al.: Improving image generation with better captions. Comput. Sci. 2(3), 8 (2023)"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Bhunia, A.K., Khan, S., Cholakkal, H., Anwer, R.M., Khan, F.S., Shah, M.: Handwriting transformers. In: ICCV, pp. 1086\u20131094 (2021)","DOI":"10.1109\/ICCV48922.2021.00112"},{"key":"24_CR5","unstructured":"Cao, J., Mo, L., Zhang, Y., Jia, K., Shen, C., Tan, M.: Multi-marginal wasserstein GAN. In: NeurIPS, vol.\u00a032 (2019)"},{"key":"24_CR6","unstructured":"Chen, Z., etal.: Complex handwriting trajectory recovery: evaluation metrics and algorithm. In: ACCV, pp. 1060\u20131076 (2022)"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Dai, G., Zhang, Y., Wang, Q., Du, Q., Yu, Z., Liu, Z., Huang, S.: Disentangling writer and character styles for handwriting generation. In: CVPR, pp. 5977\u20135986 (2023)","DOI":"10.1109\/CVPR52729.2023.00579"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Davis, B.L., Morse, B.S., Price, B.L., Tensmeyer, C., Wigington, C., Jain, R.: Text and style conditioned GAN for the generation of offline-handwriting lines. In: BMVC (2020)","DOI":"10.5244\/C.34.174"},{"key":"24_CR9","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS, pp. 8780\u20138794 (2021)"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Ding, H., Luan, B., Gui, D., Chen, K., Huo, Q.: Improving handwritten OCR with training samples generated by glyph conditional denoising diffusion probabilistic model. In: ICDAR, pp. 20\u201337 (2023)","DOI":"10.1007\/978-3-031-41685-9_2"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Fogel, S., Averbuch-Elor, H., Cohen, S., Mazor, S., Litman, R.: ScrabbleGAN: semi-supervised varying length handwritten text generation. In: CVPR, pp. 4324\u20134333 (2020)","DOI":"10.1109\/CVPR42600.2020.00438"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Gan, J., Wang, W.: HiGAN: handwriting imitation conditioned on arbitrary-length texts and disentangled styles. In: AAAI, pp. 7484\u20137492 (2021)","DOI":"10.1609\/aaai.v35i9.16917"},{"issue":"1","key":"24_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3550070","volume":"42","author":"J Gan","year":"2022","unstructured":"Gan, J., Wang, W., Leng, J., Gao, X.: HiGAN+: handwriting imitation GAN with disentangled representations. ACM TOG 42(1), 1\u201317 (2022)","journal-title":"ACM TOG"},{"key":"24_CR14","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS, pp. 2672\u20132680 (2014)"},{"key":"24_CR15","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: ICML, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"24_CR17","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems (2017)"},{"key":"24_CR18","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"24_CR19","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: arXiv (2022)"},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"Huang, H., et al.: AGTGAN: unpaired image translation for photographic ancient character generation. In: ACM MM, pp. 5456\u20135467 (2022)","DOI":"10.1145\/3503161.3548338"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Huang, S., Luo, Y., Zhuang, Z., Yu, J.G., He, M., Wang, Y.: Context-aware selective label smoothing for calibrating sequence recognition model. In: ACM MM (2021)","DOI":"10.1145\/3474085.3475618"},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"Jaeger, S., Nakagawa, M.: Two on-line Japanese character databases in unipen format. In: ICDAR, pp. 566\u2013570 (2001)","DOI":"10.1109\/ICDAR.2001.953853"},{"issue":"12","key":"24_CR23","doi-asserted-by":"publisher","first-page":"8846","DOI":"10.1109\/TPAMI.2021.3122572","volume":"44","author":"L Kang","year":"2021","unstructured":"Kang, L., Riba, P., Rusinol, M., Fornes, A., Villegas, M.: Content and style aware generation of text-line images for handwriting recognition. IEEE TPAMI 44(12), 8846\u20138860 (2021)","journal-title":"IEEE TPAMI"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Kang, L., Riba, P., Wang, Y., Rusinol, M., Forn\u00e9s, A., Villegas, M.: Ganwriting: content-conditioned generation of styled handwritten word images. In: ECCV, pp. 273\u2013289 (2020)","DOI":"10.1007\/978-3-030-58592-1_17"},{"key":"24_CR25","unstructured":"Khosla, P., et al.: Supervised contrastive learning. In: NeurIPS, pp. 18661\u201318673 (2020)"},{"key":"24_CR26","unstructured":"Khrulkov, V., Oseledets, I.: Geometry score: a method for comparing generative adversarial networks. In: International Conference on Machine Learning, pp. 2621\u20132629. PMLR (2018)"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Kleber, F., Fiel, S., Diem, M., Sablatnig, R.: CVL-database: an off-line database for writer retrieval, writer identification and word spotting. In: ICDAR, pp. 560\u2013564 (2013)","DOI":"10.1109\/ICDAR.2013.117"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Kotani, A., Tellex, S., Tompkin, J.: Generating handwriting via decoupled style descriptors. In: ECCV, pp. 764\u2013780 (2020)","DOI":"10.1007\/978-3-030-58610-2_45"},{"key":"24_CR29","doi-asserted-by":"publisher","first-page":"106275","DOI":"10.1016\/j.neunet.2024.106275","volume":"175","author":"D Li","year":"2024","unstructured":"Li, D., Chen, G., Wu, X., Yu, Z., Tan, M.: Face anti-spoofing with cross-stage relation enhancement and spoof material perception. Neural Netw. 175, 106275 (2024)","journal-title":"Neural Netw."},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Lin, T., et al.: Drafting and revision: Laplacian pyramid network for fast high-quality artistic style transfer. In: CVPR, pp. 5141\u20135150 (2021)","DOI":"10.1109\/CVPR46437.2021.00510"},{"key":"24_CR31","unstructured":"Liu, Z., et al.: Geom-erasing: geometry-driven removal of implicit concept in diffusion models. arXiv (2023)"},{"key":"24_CR32","first-page":"451","volume":"24","author":"Z Liu","year":"2021","unstructured":"Liu, Z., Jia, W., Yang, M., Luo, P., Guo, Y., Tan, M.: Deep view synthesis via self-consistent generative network. IEEE TMM 24, 451\u2013465 (2021)","journal-title":"IEEE TMM"},{"key":"24_CR33","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: arXiv (2017)"},{"key":"24_CR34","unstructured":"Luhman, T., Luhman, E.: Diffusion models for handwriting generation. arXiv (2020)"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Luo, C., Zhu, Y., Jin, L., Li, Z., Peng, D.: SLOGAN: handwriting style synthesis for arbitrary-length and out-of-vocabulary text. IEEE Trans. Neural Netw. Learn. Syst. 34(11), 8503\u20138515 (2022)","DOI":"10.1109\/TNNLS.2022.3151477"},{"key":"24_CR36","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":"24_CR37","doi-asserted-by":"crossref","unstructured":"Nikolaidou, K., et al.: Wordstylist: styled verbatim handwritten text generation with latent diffusion models. In: ICDAR, pp. 384\u2013401 (2023)","DOI":"10.1007\/978-3-031-41679-8_22"},{"key":"24_CR38","doi-asserted-by":"crossref","unstructured":"Pan, Z., Ji, Z., Liu, X., Bai, J., Liu, C.L.: Visa: visual and semantic alignment for robust scene text recognition. In: ICDAR, pp. 223\u2013242 (2023)","DOI":"10.1007\/978-3-031-41679-8_13"},{"key":"24_CR39","doi-asserted-by":"crossref","unstructured":"Pippi, V., Cascianelli, S., Cucchiara, R.: Handwritten text generation from visual archetypes. In: CVPR, pp. 22458\u201322467 (2023)","DOI":"10.1109\/CVPR52729.2023.02151"},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Ren, M.S., Zhang, Y.M., Wang, Q.F., Yin, F., Liu, C.L.: Diff-writer: a diffusion model-based stylized online handwritten Chinese character generator. In: International Conference on Neural Information Processing, pp. 86\u2013100 (2023)","DOI":"10.1007\/978-981-99-8141-0_7"},{"key":"24_CR41","doi-asserted-by":"crossref","unstructured":"Retsinas, G., Sfikas, G., Gatos, B., Nikou, C.: Best practices for a handwritten text recognition system. In: International Workshop on Document Analysis Systems, pp. 247\u2013259 (2022)","DOI":"10.1007\/978-3-031-06555-2_17"},{"key":"24_CR42","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"24_CR43","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"24_CR44","doi-asserted-by":"crossref","unstructured":"Tang, S., Lian, Z.: Write like you: synthesizing your cursive online chinese handwriting via metric-based meta learning. In: Computer Graphics Forum, pp. 141\u2013151 (2021)","DOI":"10.1111\/cgf.142621"},{"key":"24_CR45","doi-asserted-by":"crossref","unstructured":"Tang, S., Xia, Z., Lian, Z., Tang, Y., Xiao, J.: FontRNN: generating large-scale chinese fonts via recurrent neural network. In: Computer Graphics Forum, pp. 567\u2013577 (2019)","DOI":"10.1111\/cgf.13861"},{"key":"24_CR46","doi-asserted-by":"crossref","unstructured":"Tolosana, R., Delgado-Santos, P., Perez-Uribe, A., Vera-Rodriguez, R., Fierrez, J., Morales, A.: DeepWriteSYN: on-line handwriting synthesis via deep short-term representations. In: AAAI, pp. 600\u2013608 (2021)","DOI":"10.1609\/aaai.v35i1.16139"},{"key":"24_CR47","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"24_CR48","doi-asserted-by":"crossref","unstructured":"Xie, X., Fu, L., Zhang, Z., Wang, Z., Bai, X.: Toward understanding wordart: corner-guided transformer for scene text recognition. In: ECCV, pp. 5456\u20135467 (2022)","DOI":"10.1007\/978-3-031-19815-1_18"},{"key":"24_CR49","doi-asserted-by":"crossref","unstructured":"Xie, Y., Chen, X., Sun, L., Lu, Y.: Dg-font: deformable generative networks for unsupervised font generation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00509"},{"key":"24_CR50","doi-asserted-by":"crossref","unstructured":"Yang, Y., Liu, D., Zhang, S., Deng, Z., Huang, Z., Tan, M.: Hilo: detailed and robust 3d clothed human reconstruction with high-and low-frequency information of parametric models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10671\u201310681 (2024)","DOI":"10.1109\/CVPR52733.2024.01015"},{"key":"24_CR51","doi-asserted-by":"crossref","unstructured":"Yang, Y., Zhang, S., Huang, Z., Zhang, Y., Tan, M.: Cross-ray neural radiance fields for novel-view synthesis from unconstrained image collections. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15901\u201315911 (2023)","DOI":"10.1109\/ICCV51070.2023.01457"},{"key":"24_CR52","doi-asserted-by":"crossref","unstructured":"Yin, F., Wang, Q.F., Zhang, X.Y., Liu, C.L.: ICDAR 2013 chinese handwriting recognition competition. In: International Conference on Document Analysis and Recognition, pp. 1464\u20131470 (2013)","DOI":"10.1109\/ICDAR.2013.218"},{"key":"24_CR53","unstructured":"Zhang, Y., Hooi, B.: HIPA: enabling one-step text-to-image diffusion models via high-frequency-promoting adaptation. arXiv (2023)"},{"key":"24_CR54","unstructured":"Zhang, Y., Hooi, B., Hong, L., Feng, J.: Self-supervised aggregation of diverse experts for test-agnostic long-tailed recognition. In: NeurIPS, pp. 34077\u201334090 (2022)"},{"key":"24_CR55","unstructured":"Zhang, Y., Hooi, B., Hu, D., Liang, J., Feng, J.: Unleashing the power of contrastive self-supervised visual models via contrast-regularized fine-tuning. In: NeurIPS, pp. 29848\u201329860 (2021)"},{"key":"24_CR56","doi-asserted-by":"publisher","first-page":"107080","DOI":"10.1016\/j.patcog.2019.107080","volume":"104","author":"B Zhao","year":"2020","unstructured":"Zhao, B., Tao, J., Yang, M., Tian, Z., Fan, C., Bai, Y.: Deep imitator: handwriting calligraphy imitation via deep attention networks. Pattern Recogn. 104, 107080 (2020)","journal-title":"Pattern Recogn."},{"key":"24_CR57","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Li, Z., Wang, T., He, M., Yao, C.: Conditional text image generation with diffusion models. In: CVPR, pp. 14235\u201314245 (2023)","DOI":"10.1109\/CVPR52729.2023.01368"},{"key":"24_CR58","doi-asserted-by":"crossref","unstructured":"Zhuang, Z., Liu, Z., Lam, K.M., Huang, S., Dai, G.: A new semi-automatic annotation model via semantic boundary estimation for scene text detection. In: ICDAR, pp. 257\u2013273 (2021)","DOI":"10.1007\/978-3-030-86334-0_17"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73636-0_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T10:53:20Z","timestamp":1765018400000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73636-0_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,5]]},"ISBN":["9783031736353","9783031736360"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73636-0_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,5]]},"assertion":[{"value":"5 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","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":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}