宁欣,男,博士,副研究员,硕士生导师。
IEEE、中国人工智能学会、中国计算机学会高级会员。在IEEE TIP、IEEE TNNLS、IEEE TMM、IEEE TITS、IEEE TGRS、IEEE TCSVT、Pattern Recognition、Neurocomputing、计算机学报等国内外知名期刊或会议发表论文70余篇,其中第1或通信作者发表论文50余篇,ESI热点论文4篇,ESI高被引论文8篇。授权发明专利16项,撰写中英文专著各1部。担任CSIG视觉大数据专委会委员,CSIG多媒体专委会委员,CAAI青工委委员;担任IEEE HPBD&IS 2021、IEEE HDIS 2022、Edutainment & Metaverse 2022国际会议的Publication Chair。担任SCI期刊Displays, IET Image Processing, IET Computer Vision, Comput Intel Neurosc等期刊的编委或客座编辑。获2020半导体所首届“青年创芯奖”一等奖,本人或指导学生获国内外算法竞赛冠军10余项。
招生要求:需要有扎实的数理基础、较好的编程能力和英语读写能力,具备科研的浓厚兴趣,较强的自主学习能力,并有追求高水平学术与实用性科研的理想。导师和课题组会对因材施教,全力培养优秀的研究生。近年来,研究组毕业学生就职于华为、联想、谷歌、百度、腾讯、阿里巴巴、美团等知名企业及高校科研院所。本研究组有完善的科研设备和充足的实验数据库,长期招收研究生和联合培养学生,欢迎报考!
取得的主要成果及获奖情况:
在基于脑启发的形象认知计算理论方面取得了一系列成果:提出了一种基于同源连续性的不相关局部保持鉴别分析方法,形成了一种特征提取新思路,一作发表于图像处理顶刊IEEE TIP(中科院一区);基于同源连续性规律构建了一种新型高阶神经元模型,并以此模型为基础构建了一种新型拓扑积覆盖式神经网络,一作发表于模式识别顶刊Pattern Recognition(中科院一区);进一步地,提出了一种用于模式分类的覆盖式超香肠神经元模型, 一作发表于模式识别顶刊Pattern Recognition(中科院一区)。
主要研究领域或方向:
(1)类脑形象认知计算理论与方法
(2)面向人体的3D视觉技术
1)技术开发项目:“生物特征识别技术”, 2018.5-2023.5,主持
2)国家自然科学基金青年基金项目:“基于同源连续性原理的小样本多视角表示学习方法研究”,2020.01-2022.12,No. 61901436,主持
3)企业联合实验室项目:“认知计算技术”,2018.5-2023.5,1500万,骨干(执行主任)
4)企业联合实验室项目:“中医AI视觉技术”,2021.8-2026.8,1000万,骨干(执行主任)
联系方式:
E-mail:ningxin@semi.ac.cn;
1)Xin Ning, W. Tian, Z. Yu, et al. HCFNN: High-order Coverage Function Neural Network for Image Classification, Pattern Recognition, 2022.
2)Xin Ning, Weijun Li, Bo Tang and Haibo He,BULDP: Biomimetic Uncorrelated Locality Discriminant Projection for Feature Extraction in Face Recognition, IEEE Transactions on Image Processing, 2018, 27(5), 2575-2586.
3)Xin Ning, Ke Gong, et al. Feature Refinement and Filter Network for Person Re-identification. IEEE Transactions on Circuits and Systems for Video Technology, 2020.
4)Xin Ning, Pengfei Duan, et al. Real-time 3D Face Alignment Using an Encoder-Decoder Network with an Efficient Deconvolution Layer, IEEE Signal Processing Letters,2020, 27, 1944-1948.
5)Xin Ning, Ke Gong, Weijun Li, Liping Zhang. JWSAA: Joint Weak Saliency and Attention Aware for person re-identification, Neurocomputing, 2021, volume 453, pp. 801-811.
6)Xin Ning, Weijun Li, Jian Xu. The Principle of Homology Continuity and Geometrical Covering Learning for Pattern Recognition. Int J Pattern Recogn, 2018,32(12).
7)Xin Ning, S. Xu, et al. Face editing with based on human cognitive characteristics, IEEE Transactions on Cognitive and Developmental Systems, 2022.
8)C. Wang, X. Wang, J. Zhang, et al. Uncertainty Estimation for Stereo Matching Based on Evidential Deep Learning. Pattern Recognition, 2022. (通讯)
9)C. Wang, X. Ning*, L. Sun, et al. Learning Discriminative Features by Covering Local Geometric Space for Point Cloud Analysis, IEEE Transactions on Geoscience and Remote Sensing, 2022. (通讯)
10)W. Cai, X. Ning*, et al. A Novel Hyperspectral Image Classification Model Using Bole Convolution with Three-Directions Attention Mechanism: Small sample and Unbalanced Learning, IEEE Transactions on Geoscience and Remote Sensing, 2022. (通讯)
11)S. Qi, X. Ning*, G.Yang, et al. “Review of Multi-view 3D Object Recognition Methods Based on Deep Learning,” Displays, vol. 69, no. 1, 2021. (通讯)
12)L. Zhang, L. Sun, L.Yu, et al. “ARFace: Attention-aware and regularization for Face Recognition with Reinforcement Learning,” IEEE Transactions on Biometrics, Behavior, and Identity Science, 2021. (通讯)
13)王昌硕,宁欣*,等. 基于局部区域动态覆盖的3D点云分类方法, 软件学报,2022.(通讯、CCF A类中文期刊)
14)宁欣,李卫军,等. 基于仿生学的不相关局部保持鉴别分析.计算机研究与发展.2016.53(11). (CCF A类中文期刊)
15)宁欣,田伟娟,等. 面向小目标和遮挡目标检测的脑启发CIRA-DETR全推理方法, 计算机学报,2022. 45(10) .(CCF A类中文期刊)