Xu-Yao Zhang

PhD, Professor

State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS)

Institute of Automation, Chinese Academy of Sciences (CASIA)

95 Zhongguancun East Road, Beijing 100190, P.R. China

Email: xyz@nlpr.ia.ac.cn

Xu-Yao Zhang is a Professor at the State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation of Chinese Academy of Sciences, Beijing, China. He received the B.S. degree in computational mathematics from Wuhan University, Wuhan, China, in 2008 and the Ph.D. degree in pattern recognition and intelligent systems from the Institute of Automation, Chinese Academy of Sciences, Beijing, China, in 2013. He was a visiting researcher at CENPARMI of Concordia University in 2012. From March 2015 to March 2016, he was a visiting scholar at the Montreal Institute for Learning Algorithms (MILA), University of Montreal, Canada. His research interests include pattern recognition, machine learning, deep learning, AI4Science, and OCR.

Excellent Course for Graduate Students, University of Chinese Academy of Sciences (2019)

First Prize of Technology Transfer, Chinese Academy of Sciences (2019)

Youth Innovation Promotion Association, Chinese Academy of Sciences (2019)

Young Elite Scientists Sponsorship, China Association for Science and Technology (2018)

Outstanding Staff, National Laboratory of Pattern Recognition (2016)

Chinese Government Scholarship for Studying Abroad (2015)

China Computer Federation Outstanding Doctoral Dissertation Award (2014)

Spotlight Paper of IEEE Trans. Pattern Analysis and Machine Intelligence (2013)

Pattern Recognition and Machine Learning, CASIA, Fall 2019

Pattern Recognition, UCAS, Fall 2019

Deep Learning in CV and NLP, UCAS, Summer 2018

Pattern Recognition and Machine Learning, CASIA, Fall 2018

Pattern Recognition, UCAS, Fall 2018

Deep Learning in CV and NLP, UCAS, Summer 2017

Pattern Recognition and Machine Learning, CASIA, Fall 2017

Pattern Recognition, UCAS, Fall 2017

Deep Learning, UCAS, Summer 2016

• Xu-Yao Zhang, Cheng-Lin Liu, Ching Y. Suen. Towards robust pattern recognition: A review. Proceedings of the IEEE, vol. 108, no. 6, pp. 894-922, June 2020.

• Xu-Yao Zhang, Guo-Sen Xie, Xiuli Li, Tao Mei, Cheng-Lin Liu. A survey on learning to reject. Proceedings of the IEEE, vol. 111, no. 2, pp. 185-215, February 2023.

• Fei Zhu, Xu-Yao Zhang*, Rui-Qi Wang, Cheng-Lin Liu. Learning by seeing more classes. IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI). vol. 45, no. 6, pp. 7477-7493, June 2023.

• Hong-Ming Yang, Xu-Yao Zhang*, Fei Yin, Qing Yang, Cheng-Lin Liu. Convolutional prototype network for open set recognition. IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), vol. 44, no. 5, pp. 2358-2370, May 2022.

• 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 (PAMI), vol. 40, no. 4, pp. 849-862, April 2018.

• Xu-Yao Zhang, Cheng-Lin Liu. Writer adaptation with style transfer mapping. IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), vol. 35, no. 7, pp. 1773-1787, July 2013. 

• Jiao Zhang, Xu-Yao Zhang, Chuang Wang, Cheng-Lin Liu. Deep representation learning for domain generalization with information bottleneck principle, Pattern Recognition, vol. 143, article number 109737, pp. 1-12, November 2023.

• Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu. Imitating the oracle: Towards calibrated model for class incremental learning. Neural Networks, vol. 164, pp. 38-48, July 2023.

• Zhen Cheng, Fei Zhu, Xu-Yao Zhang*, Cheng-Lin Liu. Adversarial training with distribution normalization and margin balance, Pattern Recognition, vol. 136, article number 109182, pp. 1-11, April 2023.

• Ming-Liang Zhang, Xu-Yao Zhang, Chuang Wang, Cheng-Lin Liu. Towards prior gap and representation gap for long-tailed recognition. Pattern Recognition, vol. 133, article number 109012, pp. 1-12, January 2023.

• Rui-Qi Wang, Xu-Yao Zhang, Cheng-Lin Liu. Meta-prototypical learning for domain-agnostic few-shot recognition. IEEE Trans. Neural Networks and Learning Systems (TNNLS), vol. 33, no. 11, pp. 6990-6996, November 2022

• Xiang Ao, Xu-Yao Zhang, Cheng-Lin Liu. Cross-modal prototype learning for zero-shot handwritten character recognition. Pattern Recognition, vol. 131, article number 108859, pp. 1-13, November 2022.

• Xiu-Chuan Li, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu. Decision-based adversarial attack with frequency mixup. IEEE Trans. Information Forensics and Security (TIFS), vol. 17, pp. 1038-1052, March 2022.

• Guo-Sen Xie, Xu-Yao Zhang, Yazhou Yao, Zheng Zhang, Fang Zhao, Ling Shao. VMAN: A virtual mainstay alignment network for transductive zero-shot learning. IEEE Trans. Image Processing (TIP), vol. 30, pp. 4316-4329, April 2021.

• Wenhao He, Xu-Yao Zhang, Fei Yin, Zhenbo Luo, Jean-Marc Ogier, Cheng-Lin Liu. Realtime multi-scale scene text detection with scale-based region proposal network. Pattern Recognition, vol. 98, article number 107026, pp. 1-14, February 2020.

• Xiao-Bo Jin, Xu-Yao Zhang, Kaizhu Huang, Guang-Gang Geng. Stochastic conjugate gradient algorithm with variance reduction. IEEE Trans. Neural Networks and Learning Systems (TNNLS), vol. 30, no. 5, pp. 1360-1369, May 2019.

• 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), vol. 27, no. 11, pp. 5406-5419, November 2018.

• Guo-Sen Xie, Xu-Yao Zhang, Shuicheng Yan, Cheng-Lin Liu. SDE: A novel selective, discriminative and equalizing feature representation for visual recognition. International Journal of Computer Vision (IJCV), vol. 124, pp. 145-168, September 2017.

• Guo-Sen Xie, Xu-Yao Zhang, Shuicheng Yan, Cheng-Lin Liu. Hybrid CNN and dictionary-based models for scene recognition and domain adaptation. IEEE Trans. Circuits and Systems for Video Technology (TCSVT), vol. 27, no. 6, pp. 1263-1274, June 2017.

• Xu-Yao Zhang, Guo-Sen Xie, Cheng-Lin Liu, Yoshua Bengio. End-to-end online writer identification with recurrent neural network. IEEE Trans. Human-Machine Systems (THMS), vol. 47, no. 2, pp. 285-292, April 2017.

• Xu-Yao Zhang, Yoshua Bengio, Cheng-Lin Liu. Online and offline handwritten Chinese character recognition: A comprehensive study and new benchmark. Pattern Recognition, vol. 61, pp. 348-360, January 2017.

• Lingfeng Wang, Xu-Yao Zhang, Chunhong Pan. MSDLSR: Margin scalable discriminative least squares regression for multicategory classification. IEEE Trans. Neural Networks and Learning Systems (TNNLS), vol. 27, no. 12, pp. 2711-2717, December 2016.

• Ming-Ke Zhou, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu. Discriminative quadratic feature learning for handwritten Chinese character recognition. Pattern Recognition, vol. 49, pp. 7-18, January 2016.

• Xu-Yao Zhang, Lingfeng Wang, Shiming Xiang, Cheng-Lin Liu. Retargeted least squares regression algorithm. IEEE Trans. Neural Networks and Learning Systems (TNNLS), vol. 26, no. 9, pp. 2206-2213, September 2015.

• Xu-Yao Zhang, Peipei Yang, Yan-Ming Zhang, Kaizhu Huang, Cheng-Lin Liu. Combination of classification and clustering results with label propagation. IEEE Signal Processing Letters, vol. 21, no. 5, pp. 610-614, May 2014.

• Xu-Yao Zhang, Cheng-Lin Liu. Evaluation of weighted Fisher criteria for large category dimensionality reduction in application to Chinese handwriting recognition. Pattern Recognition, vol. 46, no. 9, pp. 2599-2611, September 2013.

• Fei Zhu, Zhen Cheng, Xu-Yao Zhang*, Cheng-Lin Liu. OpenMix: Exploring outlier samples for misclassification detection. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, June 18-22, 2023.

• Fei Zhu, Zhen Cheng, Xu-Yao Zhang*, Cheng-Lin Liu. Rethinking confidence reliability for failure prediction. European Conference on Computer Vision (ECCV), Tel Aviv, Israel, October 23–27, 2022. 

• Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu. Class-incremental learning via dual augmentation.  Thirty-Fifth Conference on Neural Information Processing Systems (NeurIPS), Virtual, December 6-14, 2021.

• Fei Zhu, Xu-Yao Zhang, Chuang Wang, Fei Yin, Cheng-Lin Liu. Prototype augmentation and self-supervision for incremental learning. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Online (Nashville, United States), June 19-25, 2021.

• Wei Feng, Fei Yin, Xu-Yao Zhang, Cheng-Lin Liu. Semantic-aware video text detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Online (Nashville, United States), June 19-25, 2021.

• Haoru Tan, Chuang Wang, Sitong Wu, Tie-Qiang Wang, Xu-Yao Zhang, Cheng-Lin Liu. Proxy graph matching with proximal matching networks. AAAI Conference on Artificial Intelligence (AAAI), Virtual Conference, February 2-9, 2021.

• Jin-Wen Wu, Fei Yin, Yan-Ming Zhang, Xu-Yao Zhang, Cheng-Lin Liu. Graph-to-graph: Towards accurate and interpretable online handwritten mathematical expression recognition. AAAI Conference on Artificial Intelligence (AAAI), Virtual Conference, February 2-9, 2021.

• Wei Feng, Wenhao He, Fei Yin, Xu-Yao Zhang, Cheng-Lin Liu. TextDragon: A end-to-end framework for arbitrary shaped text spotting. International Conference on Computer Vision (ICCV), Seoul, Korea, October 27-November 2, 2019.

• Jin-Wen Wu, Fei Yin, Yan-Ming Zhang, Xu-Yao Zhang, Cheng-Lin Liu. Image-to-markup generation via paired adversarial learning. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), Dublin, Ireland, September 10-14, 2018.

• Hong-Ming Yang, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu. Robust classification with convolutional prototype learning. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, June 18-22, 2018.

• Wenhao He, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu. Deep direct regression for multi-oriented scene text detection. IEEE International Conference on Computer Vision (ICCV), Venice, Italy, October 22-29, 2017.

• Guo-Sen Xie, Xu-Yao Zhang, Xiangbo Shu, Shuicheng Yan, Cheng-Lin Liu. Task-driven feature pooling for image classification. IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, December 13-16, 2015.

• Xu-Yao Zhang, Kaizhu Huang, Cheng-Lin Liu. Feature transformation with class conditional decorrelation. International Conference on Data Mining (ICDM), Dallas, December 7-10, 2013.

• Xu-Yao Zhang, Kaizhu Huang, Cheng-Lin Liu. Pattern field classification with style normalized transformation. International Joint Conference on Artificial Intelligence (IJCAI), Barcelona, Spain, July 16-22, 2011.

• Xu-Yao Zhang, Cheng-Lin Liu. Style transfer matrix learning for writer adaptation. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, June 21-23, 2011.