基本信息

姓名

殷飞

性别

男

联系方式

fyin@nlpr.ia.ac.cn

专业技术职务

正高级

部门/实验室

模式识别国家重点实验室

通信地址

北京市海淀区中关村东路95号

邮编

100190

研究领域

模式识别、文档分析、计算机视觉、深度学习

教育背景

2006.9-2010.7

中国科学院自动化研究所

博士

1999.9-2002.7

华中科技大学

硕士

1995.9-1999.7

西安邮电大学

学士

工作经历

2022.1-今

中科院自动化所模式识别国家重点实验室

研究员

2013.11-2021.12

中科院自动化所模式识别国家重点实验室

副研究员

2010.7-2013.10

中科院自动化所模式识别国家重点实验室

助理研究员

2002.7-2006.7

深圳中兴通信股份有限公司

软件工程师

发表论文

1、Meng-Biao Zhao, Wei Feng，Fei Yin, Cheng-lin Liu. Mixed-Supervised Scene Text Detection with Expectation-Maximization Algorithm, IEEE Trans. Image Processing (TIP), Accepted.

2、Zhuo Chen, Fei Yin, Qing Yang, Cheng-lin Liu, Cross-Lingual Text Image Recognition via Multi-Hierarchy Cross-Modal Mimic, IEEE Trans. Multimedia (TMM), Accepted.

3、Hong-Ming Yang, Xu-Yao Zhang, Fei Yin, Qing Yang, Cheng-Lin Liu, Convolutional prototype network for open set recognition, IEEE Tran. Pattern Analysis and Machine Intelligence (TPAMI), 44(5): 2358-2370, 2022.

4、Xiao-Long Yun, Yan-Ming Zhang, Fei Yin, Cheng-Lin Liu, Instance GNN: A learning framework for joint symbol segmentation and recognition in online handwritten diagrams, IEEE Trans. Multimedia (TMM), 24: 2580-2594, 2022.

5、Xiu-Chuan Li, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu, Decision-based adversarial attack with frequency mixup, IEEE Trans. Information Forensics and Security , 17: 1038-1052, 2022.

6、Wei Feng, Fei Yin, Xu-Yao Zhang, Wenhao He, Cheng-Lin Liu, Residual dual scale scene text spotting by fusing bottom-up and top-down processing, Int. J. Computer Vision (IJCV), 129: 619-637, 2021。

7、Li Liu, Linlin Huang, Fei Yin, Youbin Chen, Offline signature verification using a region based deep metric learning network, Pattern Recognition (PR), 118: 108009, 2021.

8、Wen-Hao He, Xu-Yao Zhang, Fei Yin, Zhenbo Luo, Jean-Marc Ogier, Cheng-Lin Liu, Real-time multi-scale scene text detection with scale-based region proposal network, Pattern Recognition (PR), 98:107026, 2020.

9、Zhuo Chen, Fei Yin, Xu-Yao Zhang, Qing Yang, Cheng-Lin Liu, Multilingual Handwritten Text Recognition via Multi-task Learning of Recurrent Neural Networks, Pattern Recognition (PR), 108:107555, 2020.

10、Jin-Wen Wu, Fei Yin, Yan-Ming Zhang, Xu-Yao Zhang, Cheng-Lin Liu, Handwritten Mathematical Expression Recognition via Paired Adversarial Learning, Int. J. Computer Vision (IJCV), 128: 2386-2401, 2020。

11、Xu-Yao Zhang, Fei Yin, Yan-Ming Zhang, Cheng-Lin Liu, Yoshua Bengio, Drawing and Recognizing Chinese Characters with Recurrent Neural Network, IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI), 40(4): 849-862, 2018。

12、Wenhao He, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu, Multi-oriented and multi-lingual scene text detection with direct regression, IEEE Trans. Image Processing (TIP), 27(11): 5406-5419, 2018.

13、Guo-Shuai Liu, Rui-Qi Wang, Fei Yin, Jean-Marc Ogier, Cheng-Lin Liu, Fast genre classification of web images using global and local features, CAAI Trans. Intelligence Technology, 3(3): 161-168, 2018。

14、Yi-Chao Wu, Fei Yin, Cheng-Lin Liu, Improving Handwritten Chinese Text Recognition UsingNeural Network Language Models and Convolutional Neural Network Shape Models, Pattern Recognition (PR), 65: 251-264, 2017.

15、刘国帅、仲伟峰、殷飞、刘成林，自然场景图像与合成图像的快速分类，中国图象图形学报，2017. G. Liu, W. Zhong, F. Yin, C. Liu, Fast classification of natural scene and born-digital images, Chinese Journal of Image and Graphics, 2017.

16、Ming-Ke Zhou, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu, Discriminative quadratic feature learning for handwritten Chinese character recognition, Pattern Recognition (PR), 49(1): 7-18, 2016.

17、 Liang Xu, Fei Yin, Qiu-Feng Wang, Cheng-Lin Liu, An over-segmentation method for single-touching Chinese handwriting with learning based filtering, J. Document Analysis and Recognition (IJDAR), 17(1): 91-104, 2014.

18、 Qiu-Feng Wang, Fei Yin, Cheng-Lin Liu, Unsupervised language model adaptation for handwritten Chinese text recognition, Pattern Recognition (PR), 47(3): 1202-1216, 2014.

19、Hiang Huang, Fei Yin, Qing-Hu Chen, Cheng-Lin Liu, Keyword spotting in unconstrained handwritten Chinese documents using contextual word model, Image and Vision Computing (IVC), 31(12): 958-968, 2013.

20、Cheng-Lin Liu, Fei Yin, Da-Han Wang, Qiu-Feng Wang, Online and offline handwritten Chinese character recognition: Benchmarking on new databases, Pattern Recognition (PR), 46(1): 155-162, 2013.

21、Fei Yin, Qiu-Feng Wang, Cheng-Lin Liu, Transcript mapping for handwritten Chinese documents by integrating character recognition model and geometric context, Pattern Recognition (PR), 46(10): 2807-2818, 2013.

22、Qiu-Feng Wang, Fei Yin, Cheng-Lin Liu, Handwritten Chinese text recognition by integrating multiple contexts, IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI), 34(8): 1469-1481, 2012.

23、Fei Yin, Cheng-Lin Liu, Handwritten Chinese text line segmentation by clustering with distance metric learning, Pattern Recognition (PR), 42(12): 3146-3157, 2009.

专利与奖励

学术竞赛奖励：

1、ICDAR2019 Commpetition on Historical Book Analysis-HBA2019， Challenge 1：Text/Graphic seperation, First Place.

2、ICDAR2019 Commpetition on Historical Book Analysis-HBA2019，Challenge 2：Font discrimination, First Place.

3、ICDAR2017  Commpetition on Reading Chinese Text in the Wild (RCTW-17) Task: End-to-End Recognition, First Place.

4、ICDAR2017  Commpetition on Reading Chinese Text in the Wild (RCTW-17) Task: Text Location, Second Place.

5、ICDAR2017 Competition on Page Object Detection in Document Images, Task A: Formula Detection, Task B: Table Detection, Task C: Figure Detection, Task D: Page Object Detection, First Place.

6、ICFHR 2014 Competition on Handwritten Digit String Recognition in Challenging Datasets (HDSRC14), First Place.

7、ICDAR2013 Competition on Historical Book Recognition (HCR2013) Task: Layout Analysis, First Place.

8、ICDAR2013 Competition on Historical Newspaper Layout Analysis (HNLA2013), First Place.

学术论文奖励：

1、ICFHR2014 Best Poster Paper Award.

2、DAS2020 Best Student Paper Award.

3、ICPR 2020 Best Scientific Paper Award.

4、ACPR 2021 Best Student Paper Award.

科研项目

1、复杂版面手写图文识别及理解关键技术研究，科技部“创新2030”新一代人工智能重大项目，2021-2024。

2、面向移动终端的高效率多通道信息输入和内容编辑，科技部国家重点研发计划项目，2019-2021。

3、面向网络信息安全的图像视频中的文字语义理解理论与方法，自然科学基金重点项目，2018-2022。

4、基于弱监督学习的中文古籍识别方法研究，自然科学基金面上项目，2016-2019。

5、基于扰动的文字识别理论与关键技术研究，自然科学基金面上项目，2012-2015。

6、混合在线手写识别技术合作项目，企业合作，2021-2022。

7、道路图像数据的多目标关系解析，企业合作，2021-2023。