中科院计算所视觉信息处理与学习组
中科院计算所视觉信息处理与学习组
山世光 (Shiguang Shan)

职 称:研究员 (Professor)

研究方向:计算机视觉(CV), 模式识别(PR), 机器学习(ML), 人脸识别(FR)

山世光,中科院计算所研究员、博导,现任中科院智能信息处理重点实验室常务副主任。他是基金委优青,第三批国家万人计划入选者,科技部创新人才推进计划中青年科技创新领军人才,人社部国家百千万人才工程有突出贡献中青年专家,CCF青年科学家奖获得者。他的研究领域为计算机视觉和机器学习。已在国内外刊物和学术会议上发表论文300余篇,其中CCF A类论文70余篇,论文被谷歌学术引用13000余次。曾应邀担任过ICCV11,ACCV12/16/18,ICPR12/14,FG13/18,ICASSP14,BTAS18等十余次领域主流国际会议的领域主席,现/曾任IEEE TIP, CVIU, PRL, Neurocomputing, FCS等国际学术刊物的编委(AE)。研究成果获2005年度国家科技进步二等奖,2015年度国家自然科学二等奖,CVPR2008 Best Student Poster Award Runner-up奖。他带领团队研发的人脸识别技术已应用于公安部门、华为等众多产品或系统中,取得了良好的经济和社会效益。


他的研究兴趣集中于以人脸识别为典型案例的计算机视觉和机器学习理论、方法和关键技术上,特别是在人脸识别领域有超过20年的研究经验。近年来也特别关注基于面像的情感计算,面向智能监控的视频结构化,面向无人机的视觉计算等应用。在理论和算法层面,他和团队有非常丰富的机器学习特别是深度学习研究经验,尤其关注X数据驱动的机器学习理论和方法,这里所谓的X数据包括小数据、无监督数据、半监督数据、弱监督数据、脏数据、增广数据等等。


作为个人兴趣,他深切关注认知神经科学和脑科学的进展,并乐于思考和讨论生物视觉的本质问题,以及脑神经科学给视觉计算带来的启示。


My ORCID: https://orcid.org/0000-0002-8348-392X 

My Google scholarhttps://scholar.google.com/citations?user=Vkzd7MIAAAAJ


Shiguang Shan received M.S. degree in computer science from the Harbin Institute of Technology, Harbin, China, in 1999, and Ph.D. degree in computer science from the Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China, in 2004. After graduate, he joined ICT, CAS in 2002 and became a full Professor in 2010. He is now the deputy director of the Key Lab of Intelligent Information Processing of CAS. 

His research interests cover computer vision, pattern recognition, and machine learning (deep learning). He especially focuses on face recognition related research topics, and machine learning with little data or weakly-supervised data. He has published more than 200 papers in refereed journals and proceedings in the areas of computer vision and pattern recognition. He has served as Area Chair for many international conferences including ICCV11, ICPR12, ACCV12, FG13, ICPR14, ICASSP14, ACCV16, ACCV18, FG18, and BTAS18. He is(/was) Associate Editors of several international journals including IEEE Trans. on Image Processing, Computer Vision and Image Understanding, Neurocomputing, and Pattern Recognition Letters. He is a recipient of the China’s State Natural Science Award in 2015, and the China’s State S&T Progress Award in 2005 for his research work.

He is also personally interested in brain science, cognitive neuroscience, as well as their interdisciplinary researche topics with AI. 


学术服务
刊物服务
  • Associate Editor of IEEE Trans. on Image Processing (CCF A期刊)
  • Associate Editor of Journal of Computer Vision and Image Understanding
  • Associate Editor of Pattern Recognition Letters
  • Associate Editor of Neurocomputing
  • Editor Board member of EURASIP Journal of Image and Video Processing
  • Associate Editor of IPSJ Transactions on Computer Vision and Applications (CVA)
  • 《计算机研究与发展》编委
会议服务
  • Area Chair of IEEE International Conference on Biometrics: Theory, Application AND Systems (BTAS 2018)
  • Area Chair of IEEE International Conference on Automatic Face and Gesture Recognition (FG 2018)
  • Area Chair of Asian Conference on Computer Vision (ACCV) 2018
  • Area Chair of International Conference on Computer Vision (ICCV) 2011
  • Program Chair of Chinese Conference on Biometric Recognition 2014, 2015, 2016
  • Area Chair of International Conference on Pattern Recognition (ICPR) 2012
  • Area Chair of Asian Conference on Computer Vision (ACCV) 2012
  • Area Chair of International Conference on Face and Gesture Recognition (FG2013)
  • Workshop Chair of Asian Conference on Computer Vision (ACCV) 2014
  • Area Chair of Asian Conference on Computer Vision (ACCV) 2016
  • Area Chair of International Conference on Pattern Recognition (ICPR) 2014
研究内容

1.   Machine learning: deep learning and beyond

重点关注复杂数据条件下的机器学习方法和技术,特别是面向小数据、弱标注数据、半监督数据、非完备数据等数据条件下的深度学习模型设计及优化方法。从方法层面,重点关注迁移学习、元学习、知识引导的学习算法等。

My team focuses on new machine learning methods for scenarios with complex data conditions, especially little data, wealy-labeled data, semi-supervised data, incomplete data, where new models and new optimizing methodsareneeded to design. In terms of methodology, we are interested in transfer learning, meta-learning, and knowledge-guided learning. 

2.   Face recognition: methods, technologies, and applications

从事人脸检测与跟踪、面部关键特征点定位、人脸识别与验证、表情分析与识别、人脸属性估计、3D人脸重建等一切与人脸感知计算相关的研究课题。应用合作单位包括:华为、平安、百度、银晨科技、三星、欧姆龙、松下、高通、中移动等,2016年和2017年两次获华为优秀合作成果奖。相关成果还曾获2015年度国家自然科学二等奖等,2005年度国家科技进步二等奖。

My team is interested in everything on face perception, including (but not limited to) face detection and tracking, facial landmark locating, face alignment, face identification, face verification, face retrieval, expression recognition, facial attribute estimation, 3D face reconstruction, face parsing, etc. We have broad cooperation with industrial parters, including Huawei, Ping'an, Qualcomm, China Mobile, Baidu, Isvision, Samsung, Omron, Panasonic, etc. Especially, our face recognition technology has been used on Huawei smart phone and Huawei Cloud album. 

3.   Generic object detection, segmentation, and recognition

关注通用目标检测、分割和识别等计算机视觉任务,重点关注面向视频监控场景的行人检测与跟踪、人体姿态估计与分割、车辆检测与跟踪、行人再识别和车辆再识别等研究课题。

My team is also interested in generic object detection, segmentation, and recognition, especially pedestrian detection and tracking, human pose estimation and body segmentation, vehicle detection and tracking, human and vehicle re-identification etc. These technologies are applied to video surveillance. 

科研项目

1.   复杂样本条件下的深度学习方法与技术

项目类型:科技部重点研发计划项目(课题)
项目时间:2018-2022
项目负责人:山世光(课题负责人)

2.   视频大数据多种类对象检测技术合作项目

项目类型:企业合作项目
项目时间:2016-2017
项目负责人:山世光

3.   人脸识别技术合作项目

项目类型:企业合作(华为)
项目时间:2016-2019
项目负责人:山世光

4.   视觉模式分析与识别

项目类型:基金委优青项目
项目时间:2013-2015
项目负责人:山世光
著论

著作

1.   Please kindly refer to my Google scholar homepage: https://scholar.google.com/citations?user=Vkzd7MIAAAAJ&hl=zh-CN 【pdf】


视觉信息处理和学习组
  • 单位地址:北京海淀区中关村科学院南路6号
  • 邮编:100190
  • 联系电话:010-62600514
  • Email:yi.cheng@vipl.ict.ac.cn
  • Valse

  • 深度学习大讲堂

版权所有 @ 中科院计算所视觉信息处理与学习组 京ICP备05002829号 京公网安备1101080060