李卫军
时间:2019-10-20李卫军,博士,研究员,博士生导师。IEEE、中国人工智能学会等高级会员,中国集成电路知识产权联盟专家委员。国际高性能大数据及智能系统会议(International Conference on High Performance Big Data and Intelligent Systems, HPBD&IS)指导委员会委员,HPBD&IS2019、2020会议组委会共同主席,IEEE TNNLS、IEEE TIP、IEEE Access、IEEE SPL、Neurocomputing、Information Science、中国科学、电子学报/CJE、智能系统学报等国内外重要学术期刊审稿人。
长期从事人工智能领域的学术研究与成果产业化工作,带领研究组取得了以下代表性成果:(1)系统研究图像处理与理解技术,研究出多种仿生视觉计算模型与算法,应用于安防、智慧城市等行业产品,多次获得行业“优秀AI应用奖”、“创新产品奖”等奖项;(2)系统研究智能存储管理与控制技术,研究出数据存储处理器(Data-storage Processing Unit, DPU)架构与多项核心技术,联合创办一家国家高新技术企业,完成DPU芯片设计与开发并成功量产;(3)系统研究人工神经网络模型、算法与实现技术,提出一种逻辑思维与形象思维融合的类脑计算系统结构,研究出模式识别专用神经网络计算机系统,并实现技术转化。发表学术论文100余篇,出版学术著作1部,授权发明专利20余项,完成科研成果转化10余项。
近年来主要研究方向:
(1)神经网络与深度学习;
(2)符号回归与深度建模;
(3)视觉计算模型与算法;
(4)3D主动视觉芯片与系统。
联系方式:
E-mail: wjli@semi.ac.cn;电话:010-82304336
近年来主要科研项目:
1. 广东省重点领域研发计划“新一代人工智能”专项项目:智能数据存储处理芯片关键技术及应用研究,项目负责人。
2. 国家自然科学基金:“基于同源连续性原理的人脸老化建模与识别方法研究”,项目负责人。
3. 企业联合实验室项目:“认知计算技术”,项目负责人。
4. 国家重大科学仪器设备开发专项项目:“基于高维形象几何分析的NIR分析技术研究与软件开发”,任务负责人。
5. 国家自然科学基金重大研究计划项目:“基于高维形象几何分析方法的仿生人脸图像处理与识别方法研究”,课题负责人。
6. 国家高新技术研究发展计划(863计划):“基于高维仿生信息学的低数据量面像识别技术”,课题负责人 。
近三年代表性论文(*为通讯作者):
1. Xin Ning, Pengfei Duan, Weijun Li*, Shaolin Zhang. Real-time 3D Face Alignment Using an Encoder-Decoder Network with an Efficient Deconvolution Layer. IEEE SIGNAL PROCESSING LETTERS, 2020.
2. Xin Ning, Ke Gong*, Weijun Li*, LipingZhang. JWSAA: Joint weak saliency and attention aware for person re-identification. Neurocomputing, 2020.
3. Linjun Sun, Weijun Li, Xin Ning, Liping Zhang, Xiaoli Dong, Wei He. Gradient-Enhanced Softmax for Face Recognition. IEICE TRANSACTIONS on Information and Systems. vol. E103, no. 05 2020, pp1185-1189.
4. Xin Ning, Shaohui Xu, Weijun Li*, Shuai Nie. FEGAN: Flexible and efficient face editing with pre-trained generator, IEEE ACCESS, vol. 8, 2020, pp65340-65350.
5. Xin Ning, Weijuan Tian, Weijun Li*, Yueyue Lu, Shuai Nie, Linjun Sun, Ziheng Chen. BDARS_CapsNet: Bi-directional attention routing sausage capsule network, IEEE Access, vol. 8, 2020, pp59059-59068.
6. Xin Ning, Pengfei Duan, Weijun Li*, Yuan Shi, Shuang Li. A CPU Real-time Face Alignment for Mobile Platform, IEEE ACCESS, vol. 8, 2020, pp8834-8843.
7. Yakun Zhang, Weijun Li*, Liping Zhang, Xin Ning, Linjun Sun, Yaxuan Lu. Adaptive Learning Gabor Filter for Finger-Vein Recognition, IEEE Access, 2019, 7:159821-159830.
8. Peng Chen, Weijun Li*, Linjun Sun, Xin Ning, Lina Yu, Liping Zhang. LGCN: Learnable Gabor Convolution Network for Human Gender Recognition in the Wild, IEICE Transactions on Information and Systems, 2019, E102D(10): 2067-2071.
9. Jianchu Lin, Jinlong Li, Weijun Li*, Hong Qin, Shaojiang Chen, A data transfer method for improving seed identification of maize (Zea mays) haploid breeding based on genetic similarity, Plant Breeding, 2019
10. Dongyang Li, Yan Wang, Bin Xu, Wenjiang Li, Weijun Li*, Lina Yu, Qing Yang. PIPULS: Predicting I/O Patterns Using LSTM in Storage Systems, in Proceedings of 2019 International Conference on High Performance Big Data and Intelligent Systems (HPBD&IS’19), Shenzhen, China, 9-11 May 2019: 14-21.
11. Xin Ning, Weijun Li*, Jian Xu. The Principle of Homology Continuity and Geometrical Covering Learning for Pattern Recognition, International Journal of Pattern Recognition and Artificial Intelligence, 2018, 32(12): 1850042(1-11).
12. Lina Yu, Wenjie Liu, Weijun Li*, Hong Qin, Jian Xu, Min Zuo, Non-destruction identification of maize haploid seeds using nonlinear analysis method based on their near-infrared spectra, Biosystems Engineering, 172(2018),144-153
13. Xin Ning, Weijun Li*, Bo Tang, Haibo He. BULDP: Biomimetic Uncorrelated Locality Discriminant Projection for Feature Extraction in Face Recognition, IEEE Transactions on Image Processing, 2018, 27(5): 2575-2586.
14. Lin Jianchu, Yu Lina, Li Weijun*, et al. Method for Identifying Maize Haploid Seeds by Applying Diffuse Transmission Near-Infrared Spectroscopy. Applied Spectroscopy, 2017(1):3702817742790.
15. Xin Ning, Weijun Li*, Wenjie Liu. A Fast Single Image Haze Removal Method Based on Human Retina Property, IEICE Transactions on information and system,2017, E100.D(1):211-214.