{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T09:07:29Z","timestamp":1784279249700,"version":"3.55.0"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFE0105400"],"award-info":[{"award-number":["2024YFE0105400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024A1515011437"],"award-info":[{"award-number":["2024A1515011437"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012245","name":"Science and Technology Planning Project of Guangdong Province","doi-asserted-by":"publisher","award":["2025A050508003"],"award-info":[{"award-number":["2025A050508003"]}],"id":[{"id":"10.13039\/501100012245","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113776","type":"journal-article","created":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T06:30:17Z","timestamp":1776493817000},"page":"113776","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["Collaborative character-component style integration transformer for few-shot font generation"],"prefix":"10.1016","volume":"179","author":[{"given":"Jiaxin","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Si","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113776_b1","doi-asserted-by":"crossref","unstructured":"J. Long, E. Shelhamer, T. Darrell, Fully convolutional networks for semantic segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"10.1016\/j.patcog.2026.113776_b2","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113776_b3","doi-asserted-by":"crossref","unstructured":"L. Yuan, Y. Chen, T. Wang, W. Yu, Y. Shi, Z.-H. Jiang, F.E. Tay, J. Feng, S. Yan, Tokens-to-token vit: Training vision transformers from scratch on imagenet, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 558\u2013567.","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"10.1016\/j.patcog.2026.113776_b4","series-title":"International Conference on Machine Learning","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015"},{"key":"10.1016\/j.patcog.2026.113776_b5","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XIX 16","first-page":"735","article-title":"Few-shot compositional font generation with dual memory","author":"Cha","year":"2020"},{"key":"10.1016\/j.patcog.2026.113776_b6","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2393","article-title":"Few-shot font generation with localized style representations and factorization","author":"Park","year":"2021"},{"key":"10.1016\/j.patcog.2026.113776_b7","doi-asserted-by":"crossref","unstructured":"S. Park, S. Chun, J. Cha, B. Lee, H. Shim, Multiple heads are better than one: Few-shot font generation with multiple localized experts, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 13900\u201313909.","DOI":"10.1109\/ICCV48922.2021.01364"},{"key":"10.1016\/j.patcog.2026.113776_b8","doi-asserted-by":"crossref","unstructured":"W. Liu, F. Liu, F. Ding, Q. He, Z. Yi, Xmp-font: Self-supervised cross-modality pre-training for few-shot font generation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 7905\u20137914.","DOI":"10.1109\/CVPR52688.2022.00775"},{"key":"10.1016\/j.patcog.2026.113776_b9","doi-asserted-by":"crossref","unstructured":"Y. Xie, X. Chen, L. Sun, Y. Lu, Dg-font: Deformable generative networks for unsupervised font generation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 5130\u20135140.","DOI":"10.1109\/CVPR46437.2021.00509"},{"key":"10.1016\/j.patcog.2026.113776_b10","doi-asserted-by":"crossref","unstructured":"C. Wang, M. Zhou, T. Ge, Y. Jiang, H. Bao, W. Xu, Cf-font: Content fusion for few-shot font generation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 1858\u20131867.","DOI":"10.1109\/CVPR52729.2023.00185"},{"key":"10.1016\/j.patcog.2026.113776_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109593","article-title":"FontTransformer: Few-shot high-resolution Chinese glyph image synthesis via stacked transformers","volume":"141","author":"Liu","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113776_b12","doi-asserted-by":"crossref","unstructured":"W. Pan, A. Zhu, X. Zhou, B.K. Iwana, S. Li, Few shot font generation via transferring similarity guided global style and quantization local style, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 19506\u201319516.","DOI":"10.1109\/ICCV51070.2023.01787"},{"key":"10.1016\/j.patcog.2026.113776_b13","doi-asserted-by":"crossref","unstructured":"Z. Yang, D. Peng, Y. Kong, Y. Zhang, C. Yao, L. Jin, 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, (7) 2024, pp. 6603\u20136611.","DOI":"10.1609\/aaai.v38i7.28482"},{"key":"10.1016\/j.patcog.2026.113776_b14","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et al., An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, in: International Conference on Learning Representations, ICLR, 2021."},{"key":"10.1016\/j.patcog.2026.113776_b15","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2021","journal-title":"Int. Conf. Learn. Represent. (ICLR)"},{"key":"10.1016\/j.patcog.2026.113776_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110190","article-title":"TSVT: Token sparsification vision transformer for robust RGB-d salient object detection","volume":"148","author":"Gao","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113776_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.109958","article-title":"TSEV-GAN: Generative adversarial networks with target-aware style encoding and verification for facial makeup transfer","volume":"257","author":"Xu","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.patcog.2026.113776_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111861","article-title":"Learning region-aware style-content feature transformations for face image beautification","volume":"170","author":"Xu","year":"2026","journal-title":"Pattern Recognit."},{"issue":"3","key":"10.1016\/j.patcog.2026.113776_b19","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/MMUL.2023.3285550","article-title":"Content-aware latent semantic direction fusion for multi-attribute editing","volume":"30","author":"Wei","year":"2023","journal-title":"IEEE MultiMedia"},{"key":"10.1016\/j.patcog.2026.113776_b20","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1109\/TMM.2023.3266611","article-title":"A graph-based discriminator architecture for multi-attribute facial image editing","volume":"26","author":"Song","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113776_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110022","article-title":"Semi-supervised class-conditional image synthesis with semantics-guided adaptive feature transforms","volume":"146","author":"Huo","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113776_b22","article-title":"Class-conditional image synthesis with intra-class relation preservation","author":"Zhang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.patcog.2026.113776_b23","article-title":"ClassBooth: Boost class semantics with bidirectional feature fusion in text-to-image diffusion models","author":"Zhang","year":"2026","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113776_b24","series-title":"International Conference on Machine Learning","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021"},{"key":"10.1016\/j.patcog.2026.113776_b25","doi-asserted-by":"crossref","unstructured":"Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, B. Guo, Swin transformer: Hierarchical vision transformer using shifted windows, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.patcog.2026.113776_b26","doi-asserted-by":"crossref","unstructured":"P. Esser, R. Rombach, B. Ommer, Taming transformers for high-resolution image synthesis, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 12873\u201312883.","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"10.1016\/j.patcog.2026.113776_b27","doi-asserted-by":"crossref","unstructured":"S.W. Zamir, A. Arora, S. Khan, M. Hayat, F.S. Khan, M.-H. Yang, Restormer: Efficient transformer for high-resolution image restoration, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5728\u20135739.","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"10.1016\/j.patcog.2026.113776_b28","series-title":"BMVC","first-page":"290","article-title":"Chinese handwriting imitation with hierarchical generative adversarial network.","author":"Chang","year":"2018"},{"key":"10.1016\/j.patcog.2026.113776_b29","unstructured":"S. Wu, C. Yang, J. Hsu, Calligan: Style and structure-aware chinese calligraphy character generator., in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops), 2020."},{"key":"10.1016\/j.patcog.2026.113776_b30","doi-asserted-by":"crossref","unstructured":"Y. Gao, J. Wu, Gan-based unpaired chinese character image translation via skeleton transformation and stroke rendering, in: Proceedings of the AAAI Conference on Artificial Intelligence, (01) 2020, pp. 646\u2013653.","DOI":"10.1609\/aaai.v34i01.5405"},{"key":"10.1016\/j.patcog.2026.113776_b31","first-page":"1","article-title":"Pix2pix gan for image-to-image translation","author":"Henry","year":"2021","journal-title":"Res. Gate Publ."},{"key":"10.1016\/j.patcog.2026.113776_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109416","article-title":"Cycle-object consistency for image-to-image domain adaptation","volume":"138","author":"Lin","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113776_b33","series-title":"zi2zi: Master Chinese calligraphy with conditional adversarial networks","author":"Tian","year":"2017"},{"key":"10.1016\/j.patcog.2026.113776_b34","series-title":"Rewrite: Neural style transfer for chinese fonts","author":"Tian","year":"2016"},{"key":"10.1016\/j.patcog.2026.113776_b35","series-title":"SIGGRAPH Asia 2017 Technical Briefs","first-page":"1","article-title":"Dcfont: an end-to-end deep chinese font generation system","author":"Jiang","year":"2017"},{"key":"10.1016\/j.patcog.2026.113776_b36","series-title":"2017 14th IAPR International Conference on Document Analysis and Recognition","first-page":"1095","article-title":"Auto-encoder guided GAN for Chinese calligraphy synthesis","volume":"1","author":"Lyu","year":"2017"},{"key":"10.1016\/j.patcog.2026.113776_b37","doi-asserted-by":"crossref","unstructured":"Y. Zhang, Y. Zhang, W. Cai, Separating style and content for generalized style transfer, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8447\u20138455.","DOI":"10.1109\/CVPR.2018.00881"},{"issue":"6","key":"10.1016\/j.patcog.2026.113776_b38","first-page":"1","article-title":"Artistic glyph image synthesis via one-stage few-shot learning","volume":"38","author":"Gao","year":"2019","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"10.1016\/j.patcog.2026.113776_b39","doi-asserted-by":"crossref","unstructured":"Y. Kong, C. Luo, W. Ma, Q. Zhu, S. Zhu, N. Yuan, L. Jin, Look closer to supervise better: One-shot font generation via component-based discriminator, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 13482\u201313491.","DOI":"10.1109\/CVPR52688.2022.01312"},{"key":"10.1016\/j.patcog.2026.113776_b40","doi-asserted-by":"crossref","unstructured":"W. Chen, G. Zhu, Y. Li, Y. Ji, C. Liu, DA-Font: Few-Shot Font Generation via Dual-Attention Hybrid Integration, in: Proceedings of the 33rd ACM International Conference on Multimedia, 2025, pp. 6644\u20136653.","DOI":"10.1145\/3746027.3755056"},{"key":"10.1016\/j.patcog.2026.113776_b41","doi-asserted-by":"crossref","unstructured":"L. Tang, Y. Cai, J. Liu, Z. Hong, M. Gong, M. Fan, J. Han, J. Liu, E. Ding, J. Wang, Few-shot font generation by learning fine-grained local styles, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 7895\u20137904.","DOI":"10.1109\/CVPR52688.2022.00774"},{"key":"10.1016\/j.patcog.2026.113776_b42","doi-asserted-by":"crossref","unstructured":"M. Yao, Y. Zhang, X. Lin, X. Li, W. Zuo, Vq-font: Few-shot font generation with structure-aware enhancement and quantization, in: Proceedings of the AAAI Conference on Artificial Intelligence, (15) 2024, pp. 16407\u201316415.","DOI":"10.1609\/aaai.v38i15.29577"},{"key":"10.1016\/j.patcog.2026.113776_b43","doi-asserted-by":"crossref","unstructured":"B. Fu, J. He, J. Wang, Y. Qiao, Neural transformation fields for arbitrary-styled font generation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 22438\u201322447.","DOI":"10.1109\/CVPR52729.2023.02149"},{"key":"10.1016\/j.patcog.2026.113776_b44","article-title":"Fontify: One-shot font generation via in-context learning","author":"Xu","year":"2026","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.patcog.2026.113776_b45","first-page":"1","article-title":"Diff-font: Diffusion model for robust one-shot font generation","author":"He","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113776_b46","doi-asserted-by":"crossref","unstructured":"B. Fu, F. Yu, A. Liu, Z. Wang, J. Wen, J. He, Y. Qiao, Generate Like Experts: Multi-Stage Font Generation by Incorporating Font Transfer Process into Diffusion Models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 6892\u20136901.","DOI":"10.1109\/CVPR52733.2024.00658"},{"key":"10.1016\/j.patcog.2026.113776_b47","series-title":"Difffontseed: A structure-aware diffusion-based framework for few-shot Chinese font generation","author":"Lu","year":"2025"},{"key":"10.1016\/j.patcog.2026.113776_b48","doi-asserted-by":"crossref","unstructured":"R. Zhang, P. Isola, A.A. Efros, E. Shechtman, O. Wang, The unreasonable effectiveness of deep features as a perceptual metric, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 586\u2013595.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"10.1016\/j.patcog.2026.113776_b49","unstructured":"D.P. Kingma, J. Ba, Adam: A method for stochastic optimization, in: International Conference on Learning Representations, ICLR, 2015."},{"key":"10.1016\/j.patcog.2026.113776_b50","series-title":"International Conference on Machine Learning","first-page":"10524","article-title":"On layer normalization in the transformer architecture","author":"Xiong","year":"2020"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326007417?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326007417?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T08:37:29Z","timestamp":1784277449000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326007417"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":50,"alternative-id":["S0031320326007417"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113776","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Collaborative character-component style integration transformer for few-shot font generation","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113776","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113776"}}