更新时间:2022-11-25 13:33
李卫军,博士,研究员,博士生导师。2004年毕业于中国科学院半导体研究所,获工学博士学位。
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 andIntelligent Systems, HPBD&IS)指导委员会委员,HPBD&IS2019、2020会议组委会共同主席,IEEE TNNLS、IEEETIP、IEEE Access、IEEESPL、Neurocomputing、InformationScience、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,带领研究团队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-storageProcessing 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。
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
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。
1.XinNing, Pengfei Duan, Weijun Li*, Shaolin Zhang. Real-time 3D Face AlignmentUsing an Encoder-Decoder Network with an Efficient Deconvolution Layer. IEEESIGNAL PROCESSING LETTERS, 2020.
2.XinNing, Ke Gong*, Weijun Li*, LipingZhang. JWSAA: Joint weak saliency andattention aware for person re-identification. Neurocomputing, 2020.
3.LinjunSun, Weijun Li, Xin Ning, Liping Zhang, Xiaoli Dong, Wei He. Gradient-Enhanced Softmaxfor Face Recognition. IEICE TRANSACTIONS on Information and Systems.vol. E103, no. 05 2020, pp1185-1189.
4.XinNing, Shaohui Xu, Weijun Li*, Shuai Nie. FEGAN: Flexible and efficient faceediting with pre-trained generator, IEEE ACCESS, vol. 8, 2020, pp65340-65350.
5.XinNing, Weijuan Tian, Weijun Li*, Yueyue Lu, Shuai Nie, Linjun Sun, Ziheng Chen.BDARS_CapsNet: Bi-directional attention routing sausage capsule network, IEEEAccess, vol. 8, 2020, pp59059-59068.
6.XinNing, Pengfei Duan, Weijun Li*, Yuan Shi, Shuang Li. A CPU Real-time FaceAlignment for Mobile Platform, IEEE ACCESS, vol. 8, 2020, pp8834-8843.
7.YakunZhang, Weijun Li*, Liping Zhang, Xin Ning, Linjun Sun, Yaxuan Lu. AdaptiveLearning Gabor Filter for Finger-Vein Recognition, IEEE Access, 2019,7:159821-159830.
8.PengChen, Weijun Li*, Linjun Sun, Xin Ning, Lina Yu, Liping Zhang. LGCN: LearnableGabor Convolution Network for Human Gender Recognition in the Wild, IEICETransactions on Information and Systems, 2019, E102D(10): 2067-2071.
9.JianchuLin, Jinlong Li, Weijun Li*, Hong Qin, Shaojiang Chen, A data transfer methodfor improving seed identification of maize (Zea mays) haploid breeding based ongenetic similarity, Plant Breeding, 2019
10.DongyangLi, 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 2019International Conference on High Performance Big Data and Intelligent Systems(HPBD&IS’19), Shenzhen, China, 9-11 May 2019: 14-21.
11.XinNing, Weijun Li*, Jian Xu. The Principle of Homology Continuity and GeometricalCovering Learning for Pattern Recognition, International Journal of PatternRecognition and Artificial Intelligence, 2018, 32(12): 1850042(1-11).
12.LinaYu, Wenjie Liu, Weijun Li*, Hong Qin, Jian Xu, Min Zuo, Non-destructionidentification of maize haploid seeds using nonlinear analysis method based ontheir near-infrared spectra, Biosystems Engineering, 172(2018),144-153
13.XinNing, Weijun Li*, Bo Tang, Haibo He. BULDP: Biomimetic Uncorrelated LocalityDiscriminant Projection for Feature Extraction in Face Recognition, IEEETransactions on Image Processing, 2018, 27(5): 2575-2586.
14.LinJianchu, Yu Lina, Li Weijun*, et al. Method for Identifying Maize Haploid Seedsby Applying Diffuse Transmission Near-Infrared Spectroscopy. AppliedSpectroscopy, 2017(1):3702817742790.
15.XinNing, Weijun Li*, Wenjie Liu. A Fast Single Image Haze Removal Method Based onHuman Retina Property, IEICE Transactions on information and system,2017, E100.D(1):211-214.