{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T04:38:14Z","timestamp":1758083894232,"version":"3.44.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032046260"},{"type":"electronic","value":"9783032046277"}],"license":[{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"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\/978-3-032-04627-7_24","type":"book-chapter","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T02:09:00Z","timestamp":1757988540000},"page":"414-428","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SFRD: Handwritten Mathematical Expressions Generation by\u00a0Spatial-Aware Feature Refinement Diffusion"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9994-3691","authenticated-orcid":false,"given":"Yiming","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2570-4544","authenticated-orcid":false,"given":"Hongxi","family":"Wei","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0007-3483","authenticated-orcid":false,"given":"Heng","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8416-4406","authenticated-orcid":false,"given":"Shiwen","family":"Sun","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Bhunia, A.K., Khan, S., Cholakkal, H., Anwer, R.M., Khan, F.S., Shah, M.: Handwriting transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1086\u20131094 (2021)","DOI":"10.1109\/ICCV48922.2021.00112"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Y., Gao, F., Zhang, Y., Qiao, M., Wang, N.: Generating handwritten mathematical expressions from symbol graphs: an end-to-end pipeline. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15675\u201315685 (2024)","DOI":"10.1109\/CVPR52733.2024.01484"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Dai, G., Zhang, Y., Ke, Q., Guo, Q., Huang, S.: One-DM: one-shot diffusion mimicker for handwritten text generation. In: European Conference on Computer Vision, pp. 410\u2013427. Springer, Cham (2025)","DOI":"10.1007\/978-3-031-73636-0_24"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Gan, J., Wang, W.: HiGAN: handwriting imitation conditioned on arbitrary-length texts and disentangled styles. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 7484\u20137492 (2021)","DOI":"10.1609\/aaai.v35i9.16917"},{"key":"24_CR6","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Guan, T., Lin, C., Shen, W., Yang, X.: Posformer: recognizing complex handwritten mathematical expression with position forest transformer. In: European Conference on Computer Vision, pp. 130\u2013147. Springer, Cham (2025)","DOI":"10.1007\/978-3-031-72670-5_8"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"He, H., et al.: Diff-font: diffusion model for robust one-shot font generation. Int. J. Comput. Vis. 1\u201315 (2024)","DOI":"10.1007\/s11263-024-02137-0"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"24_CR10","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, vol. 30 (2017)"},{"key":"24_CR11","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Johnson, J., Gupta, A., Fei-Fei, L.: Image generation from scene graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1219\u20131228 (2018)","DOI":"10.1109\/CVPR.2018.00133"},{"key":"24_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/978-3-030-58592-1_17","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Kang","year":"2020","unstructured":"Kang, L., Riba, P., Wang, Y., Rusi\u00f1ol, M., Forn\u00e9s, A., Villegas, M.: GANwriting: content-conditioned generation of styled handwritten word images. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 273\u2013289. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_17"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Kang, L., et al.: Grif-DM: generation of rich impression fonts using diffusion models. In: ECAI 2024, pp. 226\u2013233. IOS Press (2024)","DOI":"10.3233\/FAIA240492"},{"key":"24_CR15","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Mahdavi, M., Zanibbi, R., Mouchere, H., Viard-Gaudin, C., Garain, U.: ICDAR 2019 CROHME+ TFD: competition on recognition of handwritten mathematical expressions and typeset formula detection. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1533\u20131538. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00247"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Nikolaidou, K., et al.: Wordstylist: styled verbatim handwritten text generation with latent diffusion models. In: International Conference on Document Analysis and Recognition, pp. 384\u2013401. Springer, Cham (2023)","DOI":"10.1007\/978-3-031-41679-8_22"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Nikolaidou, K., Retsinas, G., Sfikas, G., Liwicki, M.: Diffusionpen: towards controlling the style of handwritten text generation. arXiv preprint arXiv:2409.06065 (2024)","DOI":"10.1007\/978-3-031-73013-9_24"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Pippi, V., Cascianelli, S., Cucchiara, R.: Handwritten text generation from visual archetypes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22458\u201322467 (2023)","DOI":"10.1109\/CVPR52729.2023.02151"},{"key":"24_CR20","unstructured":"Pippi, V., Quattrini, F., Cascianelli, S., Cucchiara, R.: HWD: a novel evaluation score for styled handwritten text generation. arXiv preprint arXiv:2310.20316 (2023)"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Springstein, M., M\u00fcller-Budack, E., Ewerth, R.: Unsupervised training data generation of handwritten formulas using generative adversarial networks with self-attention. In: Proceedings of the 2021 Workshop on Multi-Modal Pre-Training for Multimedia Understanding, pp. 46\u201354 (2021)","DOI":"10.1145\/3463945.3469059"},{"key":"24_CR22","unstructured":"Vaswani, A.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Y., Gao, Y., Lian, Z.: Attribute2font: creating fonts you want from attributes. ACM Trans. Graph. (TOG) 39(4), 69\u20131 (2020)","DOI":"10.1145\/3386569.3392456"},{"issue":"6","key":"24_CR24","first-page":"1","volume":"40","author":"Y Wang","year":"2021","unstructured":"Wang, Y., Lian, Z.: Deepvecfont: synthesizing high-quality vector fonts via dual-modality learning. ACM Trans. Graph. (TOG) 40(6), 1\u201315 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"4","key":"24_CR25","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Wu, P., Zhai, W., Cao, Y., Luo, J., Zha, Z.J.: Spatial-aware token for weakly supervised object localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1844\u20131854 (2023)","DOI":"10.1109\/ICCV51070.2023.00177"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Xie, Y., Chen, X., Sun, L., Lu, Y.: DG-font: deformable generative networks for unsupervised font generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5130\u20135140 (2021)","DOI":"10.1109\/CVPR46437.2021.00509"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Yang, Z., Peng, D., Kong, Y., Zhang, Y., Yao, C., Jin, L.: Fontdiffuser: one-shot font generation via denoising diffusion with multi-scale content aggregation and style contrastive learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 6603\u20136611 (2024)","DOI":"10.1609\/aaai.v38i7.28482"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Zhou, S., Chen, D., Pan, J., Shi, J., Yang, J.: Adapt or perish: adaptive sparse transformer with attentive feature refinement for image restoration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2952\u20132963 (2024)","DOI":"10.1109\/CVPR52733.2024.00285"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04627-7_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T02:09:15Z","timestamp":1757988555000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04627-7_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"ISBN":["9783032046260","9783032046277"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04627-7_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,16]]},"assertion":[{"value":"16 September 2025","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":"Wuhan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"16 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2025","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":"icdar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iapr.org\/icdar2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}