{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T02:38:49Z","timestamp":1777430329695,"version":"3.51.4"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031416781","type":"print"},{"value":"9783031416798","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-41679-8_20","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"348-365","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Zero-shot Generation of\u00a0Training Data with\u00a0Denoising Diffusion Probabilistic Model for\u00a0Handwritten Chinese Character Recognition"],"prefix":"10.1007","author":[{"given":"Dongnan","family":"Gui","sequence":"first","affiliation":[]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Haisong","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Qiang","family":"Huo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Ao, X., Zhang, X.Y., Yang, H.M., Yin, F., Liu, C.L.: Cross-modal prototype learning for zero-shot handwriting recognition. In: ICDAR, pp. 589\u2013594 (2019)","DOI":"10.1109\/ICDAR.2019.00100"},{"key":"20_CR2","unstructured":"Austin, J., Johnson, D.D., Ho, J., Tarlow, D., van den Berg, R.: Structured denoising diffusion models in discrete state-spaces. In: NeurIPS, vol. 34, pp. 17981\u201317993 (2021)"},{"key":"20_CR3","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: ICLR (2019)"},{"key":"20_CR4","doi-asserted-by":"publisher","first-page":"107488","DOI":"10.1016\/j.patcog.2020.107488","volume":"107","author":"Z Cao","year":"2020","unstructured":"Cao, Z., Lu, J., Cui, S., Zhang, C.: Zero-shot handwritten Chinese character recognition with hierarchical decomposition embedding. Pattern Recogn. 107, 107488 (2020)","journal-title":"Pattern Recogn."},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Chen, J., Li, B., Xue, X.: Zero-shot Chinese character recognition with stroke-level decomposition. In: IJCAI, pp. 615\u2013621 (2021)","DOI":"10.24963\/ijcai.2021\/85"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L., Wang, S., Fan, W., Sun, J., Naoi, S.: Beyond human recognition: a CNN-based framework for handwritten character recognition. In: ACPR, pp. 695\u2013699 (2015)","DOI":"10.1109\/ACPR.2015.7486592"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Cire\u015fan, D., Meier, U.: Multi-column deep neural networks for offline handwritten Chinese character classification. In: IJCNN, pp. 1\u20136 (2015)","DOI":"10.1109\/IJCNN.2015.7280516"},{"key":"20_CR8","unstructured":"Croitoru, F.A., Hondru, V., Ionescu, R.T., Shah, M.: Diffusion models in vision: a survey. CoRR abs\/2209.04747 (2022)"},{"key":"20_CR9","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS, vol. 34, pp. 8780\u20138794 (2021)"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Diao, X., Shi, D., Tang, H., Wu, L., Li, Y., Xu, H.: REZCR: a zero-shot character recognition method via radical extraction. CoRR abs\/2207.05842 (2022)","DOI":"10.24963\/ijcai.2023\/73"},{"issue":"6","key":"20_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3355089.3356488","volume":"38","author":"Y Gao","year":"2019","unstructured":"Gao, Y., Guo, Y., Lian, Z., Tang, Y., Xiao, J.: Artistic glyph image synthesis via one-stage few-shot learning. ACM TOG 38(6), 1\u201312 (2019)","journal-title":"ACM TOG"},{"key":"20_CR12","unstructured":"Graves, A.: Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850 (2013)"},{"key":"20_CR13","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":"20_CR14","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: NeurIPS, vol. 30, pp. 6626\u20136637 (2017)"},{"key":"20_CR15","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS. vol. 33, pp. 6840\u20136851 (2020)"},{"key":"20_CR16","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPS 2021 Workshop DGMs Applications (2021)"},{"key":"20_CR17","doi-asserted-by":"publisher","first-page":"108818","DOI":"10.1016\/j.patcog.2022.108818","volume":"130","author":"G Huang","year":"2022","unstructured":"Huang, G., Luo, X., Wang, S., Gu, T., Su, K.: Hippocampus-heuristic character recognition network for zero-shot learning in Chinese character recognition. Pattern Recogn. 130, 108818 (2022)","journal-title":"Pattern Recogn."},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Huang, Y., He, M., Jin, L., Wang, Y.: RD-GAN: few\/zero-shot Chinese character style transfer via radical decomposition and rendering. In: ECCV, pp. 156\u2013172 (2020)","DOI":"10.1007\/978-3-030-58539-6_10"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Huang, Y., Jin, L., Peng, D.: Zero-shot Chinese text recognition via matching class embedding. In: ICDAR, pp. 127\u2013141 (2021)","DOI":"10.1007\/978-3-030-86334-0_9"},{"issue":"4","key":"20_CR20","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1007\/s10032-018-0311-4","volume":"21","author":"Z Li","year":"2018","unstructured":"Li, Z., Teng, N., Jin, M., Lu, H.: Building efficient CNN architecture for offline handwritten Chinese character recognition. Int. J. Document Anal. Recog. 21(4), 233\u2013240 (2018)","journal-title":"Int. J. Document Anal. Recog."},{"key":"20_CR21","doi-asserted-by":"publisher","first-page":"109109","DOI":"10.1016\/j.patcog.2022.109109","volume":"134","author":"C Liu","year":"2022","unstructured":"Liu, C., Yang, C., Qin, H.B., Zhu, X., Liu, C.L., Yin, X.C.: Towards open-set text recognition via label-to-prototype learning. Pattern Recogn. 134, 109109 (2022)","journal-title":"Pattern Recogn."},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Liu, C., Yang, C., Yin, X.C.: Open-set text recognition via character-context decoupling. In: CVPR, pp. 4523\u20134532 (2022)","DOI":"10.1109\/CVPR52688.2022.00448"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Liu, C.L., Yin, F., Wang, D.H., Wang, Q.F.: CASIA online and offline Chinese handwriting databases. In: ICDAR, pp. 37\u201341 (2011)","DOI":"10.1109\/ICDAR.2011.17"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Liu, W., Liu, F., Ding, F., He, Q., Yi, Z.: XMP-Font: self-supervised cross-modality pre-training for few-shot font generation. In: CVPR, pp. 7905\u20137914 (2022)","DOI":"10.1109\/CVPR52688.2022.00775"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Y., Lian, Z.: FontTransformer: few-shot high-resolution Chinese glyph image synthesis via stacked Transformers. CoRR abs\/2210.06301 (2022)","DOI":"10.1016\/j.patcog.2023.109593"},{"key":"20_CR26","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"20_CR27","unstructured":"Luhman, T., Luhman, E.: Diffusion models for handwriting generation. CoRR abs\/2011.06704 (2020)"},{"key":"20_CR28","unstructured":"Nichol, A., et al.: GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models. In: ICML, vol. 162, pp. 16784\u201316804 (2022)"},{"key":"20_CR29","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: ICML, pp. 8162\u20138171 (2021)"},{"key":"20_CR30","doi-asserted-by":"publisher","first-page":"3859","DOI":"10.1109\/TMM.2021.3109419","volume":"24","author":"Y Pang","year":"2021","unstructured":"Pang, Y., Lin, J., Qin, T., Chen, Z.: Image-to-image translation: methods and applications. IEEE Trans. Multimedia 24, 3859\u20133881 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Park, S., Chun, S., Cha, J., Lee, B., Shim, H.: Few-shot font generation with localized style representations and factorization. In: AAAI, pp. 2393\u20132402 (2021)","DOI":"10.1609\/aaai.v35i3.16340"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., De Vries, H., Dumoulin, V., Courville, A.: FiLM: visual reasoning with a general conditioning layer. In: AAAI, pp. 3942\u20133951 (2018)","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"20_CR33","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. CoRR abs\/2204.06125 (2022)"},{"key":"20_CR34","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":"20_CR35","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Palette: image-to-image diffusion models. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. CoRR abs\/2205.11487 (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"20_CR37","unstructured":"Salimans, T., et al.: Improved techniques for training GANs. In: NeurIPS, vol. 29, pp. 2226\u20132234 (2016)"},{"key":"20_CR38","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML, pp. 2256\u20132265 (2015)"},{"key":"20_CR39","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"20_CR40","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. In: NeurIPS, vol. 32, pp. 11895\u201311907 (2019)"},{"key":"20_CR41","unstructured":"Song, Y., Ermon, S.: Improved techniques for training score-based generative models. In: NeurIPS, vol. 33, pp. 12438\u201312448 (2020)"},{"key":"20_CR42","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: ICLR (2021)"},{"key":"20_CR43","unstructured":"Wang, T., et al.: Pretraining is all you need for image-to-image translation. CoRR abs\/2205.12952 (2022)"},{"key":"20_CR44","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1016\/j.patrec.2019.08.005","volume":"125","author":"T Wang","year":"2019","unstructured":"Wang, T., Xie, Z., Li, Z., Jin, L., Chen, X.: Radical aggregation network for few-shot offline handwritten Chinese character recognition. Pattern Recogn. Lett. 125, 821\u2013827 (2019)","journal-title":"Pattern Recogn. Lett."},{"key":"20_CR45","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhang, J., Du, J., Wang, Z.R., Zhu, Y.: DenseRAN for offline handwritten Chinese character recognition. In: ICFHR, pp. 104\u2013109 (2018)","DOI":"10.1109\/ICFHR-2018.2018.00027"},{"key":"20_CR46","unstructured":"Weng, L.: What are diffusion models? https:\/\/lilianweng.github.io\/posts\/2021-07-11-diffusion-models\/, July 2021"},{"key":"20_CR47","doi-asserted-by":"crossref","unstructured":"Xie, Y., Chen, X., Sun, L., Lu, Y.: DG-Font: deformable generative networks for unsupervised font generation. In: CVPR, pp. 5130\u20135140 (2021)","DOI":"10.1109\/CVPR46437.2021.00509"},{"key":"20_CR48","doi-asserted-by":"crossref","unstructured":"Xue, M., Du, J., Zhang, J., Wang, Z.R., Wang, B., Ren, B.: Radical composition network for Chinese character generation. In: ICDAR, pp. 252\u2013267 (2021)","DOI":"10.1007\/978-3-030-86549-8_17"},{"key":"20_CR49","unstructured":"Yang, L., et al.: Diffusion models: a comprehensive survey of methods and applications. CoRR abs\/2209.00796 (2022)"},{"key":"20_CR50","doi-asserted-by":"crossref","unstructured":"Yin, F., Wang, Q.F., Zhang, X.Y., Liu, C.L.: ICDAR 2013 Chinese handwriting recognition competition. In: ICDAR, pp. 1464\u20131470 (2013)","DOI":"10.1109\/ICDAR.2013.218"},{"key":"20_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhang, Y., Cai, W.: Separating style and content for generalized style transfer. In: CVPR, pp. 8447\u20138455 (2018)","DOI":"10.1109\/CVPR.2018.00881"},{"key":"20_CR52","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zhang, X.Y., Yin, F., Liu, C.L.: Handwritten Chinese character recognition with spatial Transformer and deep residual networks. In: ICPR, pp. 3440\u20133445 (2016)","DOI":"10.1109\/ICPR.2016.7900166"},{"key":"20_CR53","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Jin, L., Xie, Z.: High performance offline handwritten Chinese character recognition using GoogLeNet and directional feature maps. In: ICDAR, pp. 846\u2013850 (2015)","DOI":"10.1109\/ICDAR.2015.7333881"},{"key":"20_CR54","doi-asserted-by":"publisher","first-page":"6932","DOI":"10.1109\/TIP.2020.2995062","volume":"29","author":"A Zhu","year":"2020","unstructured":"Zhu, A., Lu, X., Bai, X., Uchida, S., Iwana, B.K., Xiong, S.: Few-shot text style transfer via deep feature similarity. IEEE Trans. Image Process. 29, 6932\u20136946 (2020)","journal-title":"IEEE Trans. Image Process."}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-41679-8_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:27:05Z","timestamp":1692343625000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41679-8_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416781","9783031416798"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41679-8_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"19 August 2023","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":"San Jos\u00e9, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"316","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"154","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"49% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.89","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1.50","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Number and type of other papers accepted : IJDAR track papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}