计算机辅助设计与图形学学报

基于对比学习和田字格变换数据增强的小样本汉字字体生成方法

PDF下载

曾锦山 , 汪叶飞 , 熊康悦 , 袁艺扬

计算机辅助设计与图形学学报 | 图像视频处理 2025,37(12): 2191-2201

收起

计算机辅助设计与图形学学报 |图像视频处理 2025 , 37 (12) : 2191 -2201

基于对比学习和田字格变换数据增强的小样本汉字字体生成方法

全屏

[Author(id=1317501475333456833, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=jinshanzeng@jxnu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1317501475400565699, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, authorId=1317501475333456833, language=EN, stringName=Jinshan Zeng, firstName=Jinshan, middleName=null, lastName=Zeng, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Computer and Information Engineering, Jiangxi Normal University, Nanchang　330022, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1317501475484451780, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, authorId=1317501475333456833, language=CN, stringName=曾锦山, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=江西师范大学计算机信息工程学院　南昌　330022, bio={"content":"

曾锦山（1987—），男，博士，教授，博士生导师，CCF会员，主要研究方向为人工智能算法理论、计算机视觉、自然语言处理等

"}, bioImg=null, bioContent=

曾锦山（1987—），男，博士，教授，博士生导师，CCF会员，主要研究方向为人工智能算法理论、计算机视觉、自然语言处理等

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1317501475224404925, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, xref=null, ext=[AuthorCompanyExt(id=1317501475232793534, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, companyId=1317501475224404925, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Computer and Information Engineering, Jiangxi Normal University, Nanchang　330022), AuthorCompanyExt(id=1317501475241182143, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, companyId=1317501475224404925, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=江西师范大学计算机信息工程学院　南昌　330022)])]), Author(id=1317501475564143558, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1317501475652223944, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, authorId=1317501475564143558, language=EN, stringName=Yefei Wang, firstName=Yefei, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Computer and Information Engineering, Jiangxi Normal University, Nanchang　330022, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1317501475727721417, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, authorId=1317501475564143558, language=CN, stringName=汪叶飞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=江西师范大学计算机信息工程学院　南昌　330022, bio={"content":"

汪叶飞（1997—），男，硕士研究生，主要研究方向为计算机视觉、小样本学习等

"}, bioImg=null, bioContent=

汪叶飞（1997—），男，硕士研究生，主要研究方向为计算机视觉、小样本学习等

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1317501475224404925, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, xref=null, ext=[AuthorCompanyExt(id=1317501475232793534, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, companyId=1317501475224404925, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Computer and Information Engineering, Jiangxi Normal University, Nanchang　330022), AuthorCompanyExt(id=1317501475241182143, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, companyId=1317501475224404925, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=江西师范大学计算机信息工程学院　南昌　330022)])]), Author(id=1317501475799024587, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1317501475878716365, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, authorId=1317501475799024587, language=EN, stringName=Kangyue Xiong, firstName=Kangyue, middleName=null, lastName=Xiong, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Computer and Information Engineering, Jiangxi Normal University, Nanchang　330022, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1317501475975185358, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, authorId=1317501475799024587, language=CN, stringName=熊康悦, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=江西师范大学计算机信息工程学院　南昌　330022, bio={"content":"

熊康悦（2003—），男，在校学生，主要研究方向为计算机视觉、字体生成等

"}, bioImg=null, bioContent=

熊康悦（2003—），男，在校学生，主要研究方向为计算机视觉、字体生成等

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1317501475224404925, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, xref=null, ext=[AuthorCompanyExt(id=1317501475232793534, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, companyId=1317501475224404925, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Computer and Information Engineering, Jiangxi Normal University, Nanchang　330022), AuthorCompanyExt(id=1317501475241182143, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, companyId=1317501475224404925, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=江西师范大学计算机信息工程学院　南昌　330022)])]), Author(id=1317501476050682832, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1317501476138763218, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, authorId=1317501476050682832, language=EN, stringName=Yiyang Yuan, firstName=Yiyang, middleName=null, lastName=Yuan, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Computer and Information Engineering, Jiangxi Normal University, Nanchang　330022, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1317501476214260691, tenantId=1146029695717560320, journalId=1315121996591366276, articleId=1315694017774469713, authorId=1317501476050682832, language=CN, stringName=袁艺扬, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=江西师范大学计算机信息工程学院　南昌　330022, bio={"content":"

袁艺扬（2003—），女，硕士研究生，主要研究方向为计算机视觉、图像生成.

"}, bioImg=null, bioContent=

袁艺扬（2003—），女，硕士研究生，主要研究方向为计算机视觉、图像生成.

曾锦山, 汪叶飞, 熊康悦, 袁艺扬

作者信息

江西师范大学计算机信息工程学院　南昌　330022

通讯作者:

（jinshanzeng@jxnu.edu.cn）

作者简介:

曾锦山（1987—），男，博士，教授，博士生导师，CCF会员，主要研究方向为人工智能算法理论、计算机视觉、自然语言处理等

汪叶飞（1997—），男，硕士研究生，主要研究方向为计算机视觉、小样本学习等

熊康悦（2003—），男，在校学生，主要研究方向为计算机视觉、字体生成等

袁艺扬（2003—），女，硕士研究生，主要研究方向为计算机视觉、图像生成.

Few-Shot Chinese Font Generation Based on Contrastive Learning and Square-Block Transformation Data Augmentation

Jinshan Zeng, Yefei Wang, Kangyue Xiong, Yiyang Yuan

Affiliations

School of Computer and Information Engineering, Jiangxi Normal University, Nanchang　330022

出版时间: 2025-12-20 doi: 10.3724/SP.J.1089.2023-00733

文章导航

摘要

收起

现有小样本汉字字体生成模型难以通过少量参考汉字有效实现字体风格与内容解耦，导致字体生成效果欠佳. 为解决该问题，提出一种基于对比学习和田字格变换数据增强的小样本汉字字体生成方法. 利用对比学习思想，对输出图像分别进行风格对比和内容对比，更好地实现字体风格和内容的自适应解耦；为了进一步提高小样本字体生成性能，提出一种基于田字格变化的数据增强方式，通过对田字格区域的几何变换，嵌入字体的全局结构信息，提高字体的风格和内容解耦能力. 所提方法的有效性在公开的汉字字体数据集进行多次实验得到验证. 实验结果表明，与当前先进的小样本字体生成模型相比，所提方法在生成字体质量上有显著优势，并且FID，SSIM，PSNR，LPIPS等性能指标也均优于对比方法模型. 特别地，所提方法嵌入现有小样本字体生成模型，仅使用较少训练数据集训练后，便可显著地提升现有小样本汉字字体生成模型性能.

关键词

小样本字体生成 / 汉字字体生成 / 生成对抗网络 / 深度学习

Abstract

收起

Existing few-shot Chinese font generation models struggle to effectively decouple font style and content using a limited number of reference characters, leading to suboptimal font generation results. To address this issue, a novel few-shot Chinese font generation method based on contrastive learning and square-block transformation data augmentation is proposed. Utilizing the concept of contrastive learning, the output images undergo separat e style and content comparisons, achieving better adaptive decoupling of font style and content. To further improve the performance of few-shot font generation, a data augmentation method based on square-block transformations is introduced, embedding the global structural information of the fonts through geometric transformations of the square-block areas, thereby enhancing the ability to decouple font style and content. The effectiveness of the proposed method is validated through extensive experiments on public Chinese font datasets. Experimental results demonstrate that, compared to current state-of-the-art few-shot font generation models, the proposed method significantly improves the quality of generated fonts and outperforms comparative models in performance metrics such as FID, SSIM, PSNR, and LPIPS. Notably, the proposed method can be integrated into existing few-shot font generation models and, with only a small training dataset, can significantly enhance the performance of these models.

Key words

few-shot font generation / Chinese font generation / generative adversarial networks / deep learning

引用本文

曾锦山, 汪叶飞, 熊康悦, 袁艺扬. 基于对比学习和田字格变换数据增强的小样本汉字字体生成方法. 计算机辅助设计与图形学学报, 2025 , 37 (12) : 2191 -2201 . DOI: 10.3724/SP.J.1089.2023-00733

Jinshan Zeng, Yefei Wang, Kangyue Xiong, Yiyang Yuan. Few-Shot Chinese Font Generation Based on Contrastive Learning and Square-Block Transformation Data Augmentation[J]. Journal of Computer-Aided Design & Computer Graphics, 2025 , 37 (12) : 2191 -2201 . DOI: 10.3724/SP.J.1089.2023-00733

基金

收起

国家自然科学基金(62376110; 61977038)
江西省“双千计划”(jxsq2019201124)
江西省自然科学杰出青年基金(20224ACB212004)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

Zhang Y X, Zhang Y, Cai W B. Separating style and content for generalized style transfer[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society Press, 2018: 8447-8455

[2]

Gao Y, Guo Y, Lian Z H, et al. Artistic glyph image synthesis via one-stage few-shot learning[J]. ACM Transactions on Graphics, 2019, 38(6): Article No.185

[3]

Xie Y C, Chen X Y, Sun L, et al. DG-font: deformable generative networks for unsupervised font generation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society Press, 2021: 5126-5136

[4]

Azadi S, Fisher M, Kim V, et al. Multi-content GAN for few-shot font style transfer[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society Press, 2018: 7564-7573

[5]

Sun D Y, Ren T Z, Li C X, et al. Learning to write stylized Chinese characters by reading a handful of examples[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence. San Fransisco: Morgan Kaufmann, 2018: 920-927

[6]

Park S, Chun S, Cha J, et al. Few-shot font generation with localized style representations and factorization[C]//Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2021: 2393-2402

[7]

Park S, Chun S, Cha J, et al. Multiple heads are better than one: few-shot font generation with multiple localized experts[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Los Alamitos: IEEE Computer Society Press, 2021: 13880-13889

[8]

Kong Y X, Luo C J, Ma W H, et al. Look closer to supervise better: one-shot font generation via component-based discriminator[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society Press, 2022: 13472-13481

[9]

Tang L C, Cai Y Y, Liu J M, et al. Few-shot font generation by learning fine-grained local styles[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society Press, 2022: 7885-7894

[10]

Liu W, Liu F Y, Ding F, et al. XMP-font: self-supervised cross-modality pre-training for few-shot font generation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society Press, 2022: 7895-7904

[11]

Chen T, Kornblith S, Norouzi M, et al. A simple framework for contrastive learning of visual representations[C]//Proceedings of the 37th International Conference on Machine Learning. New York: PMLR, 2020: 1597-1607

[12]

Ye M, Zhang X, Yuen P C, et al. Unsupervised embedding learning via invariant and spreading instance feature[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society Press, 2019: 6203-6212

[13]

Tian Y L, Krishnan D, Isola P. Contrastive multiview coding[C]//Proceedings of the 16th European Conference on Computer Vision. Heidelberg: Springer, 2020: 776-794

[14]

He K M, Fan H Q, Wu Y X, et al. Momentum contrast for unsupervised visual representation learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society Press, 2020: 9726-9735

[15]

Zeng Jinshan, Chen Qi, Wang Mingwen. Self-supervised Chinese font generation based on square-block transformation[J]. Scientia Sinica Informationis, 2022, 52(1): 145-159 (in Chinese) (曾锦山, 陈琪, 王明文. 基于田字格变换的自监督汉字字体生成[J]. 中国科学: 信息科学, 2022, 52(1): 145-159)

[16]

Li B H, Hou Y T, Che W X. Data augmentation approaches in natural language processing: a survey[J]. AI Open, 2022, 3: 71-90

[17]

Bartoli A. Groupwise geometric and photometric direct image registration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(12): 2098-2108

[18]

Tian Y. Master Chinese calligraphy with conditional adversarial networks[OL]. [2023-11-13]. https://github.com/kaonashi-tyc/zi2zi

[19]

Chang B, Zhang Q, Pan S Y, et al. Generating handwritten Chinese characters using CycleGAN[C]//Proceedings of the IEEE Winter Conference on Applications of Computer Vision. Los Alamitos: IEEE Computer Society Press, 2018: 199-207

[20]

Zhu J Y, Park T, Isola P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]//Proceedings of the IEEE International Conference on Computer Vision. Los Alamitos: IEEE Computer Society Press, 2017: 2242-2251

[21]

Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2014: 2672-2680

[22]

Liu Yu, Ding Yang, Khalid F B, et al. Unsupervised font generation network integrating content and style representation[J]. Journal of Computer-Aided Design & Computer Graphics, 2025, 37(5): 865-876 (in Chinese) (刘宇, 丁阳, Khalid F B, 等. 联合内容和风格表示的无监督字体生成网络[J]. 计算机辅助设计与图形学学报, 2025, 37(5): 865-876)

[23]

Zeng J S, Chen Q, Liu Y X, et al. StrokeGAN: reducing mode collapse in Chinese font generation via stroke encoding[C]//Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2021: 3270-3277

[24]

Wang Cunrui, Ding Yang, Liu Yu, et al. Chinese font generation from stroke semantic and attention mechanism[J]. Journal of Computer-Aided Design & Computer Graphics, 2022, 34(8): 1229-1237 (in Chinese) (王存睿, 丁阳, 刘宇, 等. 融合笔画语义和注意力机制的汉字字体生成算法[J]. 计算机辅助设计与图形学学报, 2022, 34(8): 1229-1237)

[25]

Zeng J S, Wang Y F, Chen Q, et al. StrokeGAN+: few-shot semi-supervised Chinese font generation with stroke encoding[OL]. [2023-11-13]. https://arxiv.org/abs/2211.06198

[26]

Zhou J, Wang Y F, Yuan Y Y, et al. SGCE-font: skeleton guided channel expansion for Chinese font generation[OL]. [2023-11-13]. https://arxiv.org/abs/2211.14475

[27]

Zeng J S, Tu L, Zhou J, et al. Enhancing Chinese calligraphy generation with contour and region-aware attention[C]//Proceedings of the International Joint Conference on Neural Networks. Los Alamitos: IEEE Computer Society Press, 2023: 1-9

[28]

Jiang Y, Lian Z H, Tang Y M, et al. DCFont: an end-to-end deep Chinese font generation system[C]//Proceedings of SIGGR-APH Asia 2017 Technical Briefs. New York: ACM Press, 2017: 1-4

[29]

Park S, Chun S, Cha J, et al. Few-shot font generation with weakly supervised localized representations[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(3): 1479-1495

[30]

Kuhn H W. The Hungarian method for the assignment problem[J]. Naval Research Logistics Quarterly, 1955, 2(1-2): 83-97

[31]

Gretton A, Bousquet O, Smola A, et al. Measuring statistical dependence with Hilbert-Schmidt norms[C]//Proceedings of the 16th International Conference on Algorithmic Learning Theory. Heidelberg: Springer, 2005: 63-77

[32]

Liu M Y, Huang X, Mallya A, et al. Few-shot unsupervised image-to-image translation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Los Alamitos: IEEE Computer Society Press, 2019: 10550-10559

[33]

Wang C, Zhou M, Ge T Z, et al. CF-font: content fusion for few-shot font generation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society Press, 2023: 1858-1867

[34]

Li Y M, Lin G F, He M L, et al. Layer similarity guiding few-shot Chinese style transfer[J]. The Visual Computer, 2024, 40(4): 2265-2278

[35]

Wang Z, Bovik A C, Sheikh H R, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612

[36]

Zhang R, Isola P, Efros A A, et al. The unreasonable effectiveness of deep features as a perceptual metric[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society Press, 2018: 586-595

[37]

Heusel M, Ramsauer H, Unterthiner T, et al. GANs trained by a two time-scale update rule converge to a local nash equilibrium[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc, 2017: 6629-6640

[38]

Kingma D P, Ba J. Adam: a method for stochastic optimization[OL]. [2023-11-13]. https://arxiv.org/pdf/1412.6980

2025年第37卷第12期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.3724/SP.J.1089.2023-00733

接收时间：2023-11-13
首发时间：2026-10-10
出版时间：2025-12-20

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2023-11-13
修回日期：2024-07-10

基金

国家自然科学基金(62376110; 61977038)

江西省“双千计划”(jxsq2019201124)

江西省自然科学杰出青年基金(20224ACB212004)

作者信息

江西师范大学计算机信息工程学院　南昌　330022

通讯作者:

（jinshanzeng@jxnu.edu.cn）

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/jsjfzsj/CN/10.3724/SP.J.1089.2023-00733

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT