山世光，中科院計算所研究員、博導，現任中科院智慧型信息處理重點實驗室常務副主任。他是基金委優青，第三批國家萬人計畫入選者，科技部創新人才推進計畫中青年科技創新領軍人才，人社部國家百千萬人才工程有突出貢獻中青年專家，CCF青年科學家獎獲得者。他的研究領域為計算機視覺和機器學習。已在國內外刊物和學術會議上發表論文300餘篇，其中CCF A類論文70餘篇，論文被谷歌學術引用13000余次。曾應邀擔任過ICCV11，ACCV12/16/18，ICPR12/14，FG13/18，ICASSP14，BTAS18等十餘次領域主流國際會議的領域主席，現/曾任IEEE TIP, CVIU, PRL, Neurocomputing, FCS等國際學術刊物的編委(AE)。研究成果獲2005年度國家科技進步二等獎，2015年度國家自然科學二等獎，CVPR2008 Best Student Poster Award Runner-up獎。
2019年9月，榮獲“科學探索獎”，肯定他在計算機視覺模式高階非線性建模、學習與識別領域取得的多項研究成果，支持他繼續研究深刻理解人的視覺智慧型技術，鼓勵他探索弱小數據和人類知識聯合驅動的機器學習理論與方法。
基本介紹
- 中文名：山世光
- 外文名：Shiguang Shan
- 國籍：中國
- 出生日期：1975年
- 畢業院校：卡內基梅隆大學訪問學者、中科院計算所博士
- 職務：中科院智慧型信息處理重點實驗室常務副主任
- 職稱：研究員
主要作品,研究領域,獲獎記錄,人物經歷,工作經歷,其他經歷,教育背景,科研項目,發表論文,
主要作品
已在國內外學術刊物和會議上發表論文300餘篇，其中70餘篇發表在計算機學會（CCF）認定的A類國際期刊和國際會議上，論文被谷歌學術引用13000余次。
研究領域
隸屬學科：計算機視覺，模式識別，機器學習，人機互動。在理論和算法層面，他和團隊有非常豐富的機器學習特別是深度學習研究經驗，當前尤其關注小樣本、弱監督、半監督、粗標籤等複雜數據條件下的機器學習理論和方法。在套用層面，他重點關注人臉識別相關研究，近年來也特別關注基於面部圖像或視頻的情感計算，面向智慧型監控的視頻結構化，面向智慧教育的視頻處理和分析技術等套用。作為個人興趣，他深切關注認知神經科學和腦科學的進展，並樂于思考和討論生物視覺的本質問題，以及腦神經科學給視覺計算帶來的啟示。
獲獎記錄
2019年9月，獲2019年“科學探索獎”（信息電子）。
2015年，國家自然科學二等獎，視覺模式的局部建模及非線性特徵獲取理論與方法研究（第2完成人）
2015年，中國計算機學會青年科學家獎
2012年，獲得國家自然科學基金委員會優秀青年科學基金支持
2009年，北京市科技新星獲得者
2008年，CVPR2008 best student poster award runner-up（第二作者）
2005年，國家科技進步二等獎，人臉識別理論、算法、技術及其套用（第3完成人）
2003年，上海市科技進步一等獎，人臉識別系統及套用
人物經歷
工作經歷
2013-03--今 中國科學院智慧型信息處理重點實驗室 常務副主任
2011-11--今 中國科學院智慧型信息處理重點實驗室 副主任
2010-10--今 中國科學院計算技術研究所 研究員
2005-10--2010-09 中國科學院計算技術研究所 副研究員
2004-08--2005-09 中國科學院計算技術研究所 助理研究員
2002-08--2004-08 中國科學院計算技術研究所 研究實習員
其他經歷
2018-01-01-今,國際生物特徵識別領域會議BTAS2018領域主席(Area Chair),
2017-09-01-今,國際會議“FG2018”的領域主席(Area Chair),
2017-01-01-今,國際刊物Computer Vision and Image Understanding的編委（Associate Editor）,
2016-12-31-2019-12-31,國際刊物Pattern Recognition Letters的編委(AE),
2016-02-29-今,國際會議“亞洲計算機視覺大會(ACCV)”的領域主席,
2015-03-01-今,IEEE Senior member,
2013-05-01-今,刊物Frontier of Computer Science in China編委, Associate Editor
2013-03-01-今,國際刊物IEEE Trans. on Image Processing的編委（AE）,
2012-05-22-2013-04-26,國際會議FG2013, Area Chair
2012-04-05-2013-09-30,國際會議ICPR2012的Area Chair,
2012-04-03-2012-10-06,國際會議ACCV2012的Area Chair,
2012-03-01-今,國際期刊Neurocomputing的Associate Editor,
2011-03-01-2012-11-08,國際會議ICCV2011的Area Chair,
教育背景
2013-12--2015-01 卡內基梅隆大學 訪問學者
1999-09--2004-07 中國科學院計算技術研究所 博士
1997-09--1999-07 哈爾濱工業大學 碩士
1993-08--1997-08 哈爾濱工業大學 學士
科研項目
（1） 視覺模式分析與識別，主持，部委級，2013-01--2015-12
（2） 跨姿態人臉識別研究，主持，部委級，2012-01--2015-12
（3） 人臉檢測與識別技術，主持，其他級，2011-11--2012-12
（4） 人臉識別技術研究，參與，其他級，2011-01--2015-12
（5） 面向公共安全的智慧型視頻監控新技術與新方法，主持，省級，2011-01--2013-12
（6） Research & Development on Object Detection and Re-，主持，其他級，2010-08--2013-12
（7） 基於視覺特性的圖像/視頻表示，主持，國家級，2009-01--2012-12
發表論文
（1）Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach,IEEE Trans. on Pattern Analysis and Machine Intelligence,2018,第4作者
（2）Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video,IEEE Trans. on Pattern Analysis and Machine Intelligence,2018,第3作者
（3）Discriminant Analysis on Riemannian Manifold of Gaussian Distributions for Face Recognition with Image Sets,IEEE Trans. on Pattern Analysis and Machine Intelligence,2018,第4作者
（4）Geometry-aware Similarity Learning on SPD Manifolds for Visual Recognition,IEEE Transactions on circuits and systems for video technology,2018,第5作者
（5）Recursive Spatial Transformer (ReST) for Alignment-Free Face Recognition,Proceeding of International Conference on Computer Vision,2017,第5作者
（6）Learning Discriminative Latent Attributes for Zero-Shot Classification,Proceeding of International Conference on Computer Vision,2017,第3作者
（7）Prototype Discriminative Learning for Image Set Classification,IEEE Signal Processing Letters,2017,第3作者
（8）Learning multifunctional binary codes for both category and attribute oriented retrieval tasks,Proceeding of IEEE/CVF International Conference on Computer Vision and Pattern Recognition,2017,第3作者
（9）Funnel-structured cascade for multi-view face detection with alignment-awareness,Neurocomputing,2017,通訊作者
（10）Discriminative Covariance Oriented Representation Learning for Face Recognition with Image Sets,Proceeding of IEEE/CVF International Conference on Computer Vision and Pattern Recognition,2017,第3作者
（11）Multi-View Discriminant Analysis,IEEE Trans. on Pattern Analysis and Machine Intelligence,2016,第2作者
（12）Relative Forest for Visual Attribute Prediction,IEEE Trans. on Image Processing,2016,通訊作者
（13）Spatial Pyramid Covariance-Based Compact Video Code for Robust Face Retrieval in TV-Series,IEEE Transactions on Image Processing,2016,通訊作者
（14）Learning Expressionlets via Universal Manifold Model for Dynamic Facial Expression Recognition,IEEE Transactions on Image Processing,2016,通訊作者
（15）Learning Prototypes and Similes on Grassmann Manifold for Spontaneous Expression Recognition,Journal of Computer Vision and Image Understanding,2016,通訊作者
（16）Learning to Diffuse: A New Perspective to Design PDEs for Visual Analysis,IEEE Trans. on Pattern Analysis and Machine Intelligence,2016,第5作者
（17）A Benchmark and Comparative Study of Video-based Face Recognition on COX Face Database,IEEE Trans. on Image Processing,2015,第2作者
（18）Face Recognition on Large-scale Video in the Wild with Hybrid Euclidean-and-Riemannian Metric Learning,Pattern Recognition,2015,通訊作者
（19）Bi-shifting Auto-Encoder for Unsupervised Domain Adaptation,Proceeding of International Conference on Computer Vision (ICCV),2015,第2作者
（20）Leveraging Datasets with Varying Annotations for Face Alignment via Deep Regression Network,Proceeding of International Conference on Computer Vision (ICCV),2015,第3作者
（21）A Unified Multiplicative Framework for Attribute Learning,Proceeding of International Conference on Computer Vision (ICCV),2015,第3作者
（22）Log-Euclidean Metric Learning on Symmetric Positive Definite Manifold with Application to Image Set Classification,Proceedings of the 32 nd International Conference on Machine Learning,2015,第3作者
（23）Projection Metric Learning on Grassmann Manifold with Application to Video based Face Recognition,Proc. of The 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2015,第3作者
（24）Face Video Retrieval with Image Query via Hashing across Euclidean Space and Riemannian Manifold,Proc. of The 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2015,第4作者
（25）Discriminant Analysis on Riemannian Manifold of Gaussian Distributions for Face Recognition with Image Sets,Proc. of The 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2015,第4作者
（26）Shape Driven Kernel Adaptation in Convolutional Neural Network for Robust Facial Traits Recognition,Proc. of The 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2015,第4作者
（27）Domain Adaptation for Face Recognition: Targetize Source Domain Images Bridged by Common Subspace (TSC),International Journal of Computer Vision,2014,通訊作者
（28）Maximal Likelihood Correspondence Estimation for Face Recognition Across Pose,IEEE Trans. on Image Processing,2014,通訊作者
（29）Semi-supervised Hashing via Kernel Hyperplane Learning for Scalable Image Search,IEEE Transactions on circuits and systems for video technology,2014,第3作者
（30）Data-Driven Hair Segmentation with Isomorphic Manifold Inference,Image and Vision Computing,2014,通訊作者
（31）CovGa: A novel descriptor based on symmetry of regions for head pose estimation, Neurocomputing,2014,通訊作者
（32）Joint Sparse Representation for Video-based Face Recognition,Neurocomputing,2014,第3作者
（33）Adaptive Discriminant Learning for Face Recognition,Pattern Recognition,2013,通訊作者
（34）A Comparative Study on Illumination Preprocessing in Face Recognition,Pattern Recognition,2013,通訊作者
（35）Manifold-Manifold Distance and Its Application to Face Recognition with Image Sets,IEEE Transactions on Image Processing,2012,第2作者
（36）Coupled Bias-Variance Trade off for Cross-Pose Face Recognition,IEEE Transactions on Image Processing,2012,第2作者
（37）Maximal Linear Embedding for Dimensionality Reduction,IEEE Trans. on Pattern Analysis and Machine Intelligence,2011,第2作者
（38）High Resolution Face Fusion for Gender Conversion,IEEE Trans. on System, Man, and Cybernetics (Part A),2011,第3作者
（39）Classifiability-based Discriminatory Projection Pursuit,IEEE Trans. on Neural Network,2011,第2作者
（40）Cross-pose face recognition based on partial least squares. ,Pattern Recognition Letters,2011,第2作者
（41）WLD: A Robust Local Image Descriptor,IEEE Trans. on Pattern Analysis and Machine Intelligence,2010,第2作者
（42）A Compositional and Dynamic Model for Face Aging,IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,第3作者
（43）Fusing Local Patterns of Gabor Magnitude and Phase for Face Recognition. ,IEEE Trans. on Image Processing,2010,第2作者
（44）Hierarchical Ensemble of Global and Local Classifiers for Face Recognition,IEEE Trans. on Image Processing,2009,第2作者
（45）Head Yaw Estimation from Asymmetry of Facial Appearance,IEEE Trans. on System, Man, and Cybernetics, Part B,2008,第2作者
（46）The CAS-PEAL Large-Scale Chinese Face Database and Baseline Evaluations,IEEE Trans. on System Man, and Cybernetics (Part A),2008,第3作者
（47）Locally Linear Regression for Pose Invariant Face Recognition. ,IEEE Trans. on Image Processing,2007,第2作者
（48）Histogram of Gabor Phase Patterns (HGPP): A Novel Object Representation Approach for Face Recognition. ,IEEE Transaction on Image Processing,2007,第2作者
（2）Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video,IEEE Trans. on Pattern Analysis and Machine Intelligence,2018,第3作者
（3）Discriminant Analysis on Riemannian Manifold of Gaussian Distributions for Face Recognition with Image Sets,IEEE Trans. on Pattern Analysis and Machine Intelligence,2018,第4作者
（4）Geometry-aware Similarity Learning on SPD Manifolds for Visual Recognition,IEEE Transactions on circuits and systems for video technology,2018,第5作者
（5）Recursive Spatial Transformer (ReST) for Alignment-Free Face Recognition,Proceeding of International Conference on Computer Vision,2017,第5作者
（6）Learning Discriminative Latent Attributes for Zero-Shot Classification,Proceeding of International Conference on Computer Vision,2017,第3作者
（7）Prototype Discriminative Learning for Image Set Classification,IEEE Signal Processing Letters,2017,第3作者
（8）Learning multifunctional binary codes for both category and attribute oriented retrieval tasks,Proceeding of IEEE/CVF International Conference on Computer Vision and Pattern Recognition,2017,第3作者
（9）Funnel-structured cascade for multi-view face detection with alignment-awareness,Neurocomputing,2017,通訊作者
（10）Discriminative Covariance Oriented Representation Learning for Face Recognition with Image Sets,Proceeding of IEEE/CVF International Conference on Computer Vision and Pattern Recognition,2017,第3作者
（11）Multi-View Discriminant Analysis,IEEE Trans. on Pattern Analysis and Machine Intelligence,2016,第2作者
（12）Relative Forest for Visual Attribute Prediction,IEEE Trans. on Image Processing,2016,通訊作者
（13）Spatial Pyramid Covariance-Based Compact Video Code for Robust Face Retrieval in TV-Series,IEEE Transactions on Image Processing,2016,通訊作者
（14）Learning Expressionlets via Universal Manifold Model for Dynamic Facial Expression Recognition,IEEE Transactions on Image Processing,2016,通訊作者
（15）Learning Prototypes and Similes on Grassmann Manifold for Spontaneous Expression Recognition,Journal of Computer Vision and Image Understanding,2016,通訊作者
（16）Learning to Diffuse: A New Perspective to Design PDEs for Visual Analysis,IEEE Trans. on Pattern Analysis and Machine Intelligence,2016,第5作者
（17）A Benchmark and Comparative Study of Video-based Face Recognition on COX Face Database,IEEE Trans. on Image Processing,2015,第2作者
（18）Face Recognition on Large-scale Video in the Wild with Hybrid Euclidean-and-Riemannian Metric Learning,Pattern Recognition,2015,通訊作者
（19）Bi-shifting Auto-Encoder for Unsupervised Domain Adaptation,Proceeding of International Conference on Computer Vision (ICCV),2015,第2作者
（20）Leveraging Datasets with Varying Annotations for Face Alignment via Deep Regression Network,Proceeding of International Conference on Computer Vision (ICCV),2015,第3作者
（21）A Unified Multiplicative Framework for Attribute Learning,Proceeding of International Conference on Computer Vision (ICCV),2015,第3作者
（22）Log-Euclidean Metric Learning on Symmetric Positive Definite Manifold with Application to Image Set Classification,Proceedings of the 32 nd International Conference on Machine Learning,2015,第3作者
（23）Projection Metric Learning on Grassmann Manifold with Application to Video based Face Recognition,Proc. of The 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2015,第3作者
（24）Face Video Retrieval with Image Query via Hashing across Euclidean Space and Riemannian Manifold,Proc. of The 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2015,第4作者
（25）Discriminant Analysis on Riemannian Manifold of Gaussian Distributions for Face Recognition with Image Sets,Proc. of The 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2015,第4作者
（26）Shape Driven Kernel Adaptation in Convolutional Neural Network for Robust Facial Traits Recognition,Proc. of The 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2015,第4作者
（27）Domain Adaptation for Face Recognition: Targetize Source Domain Images Bridged by Common Subspace (TSC),International Journal of Computer Vision,2014,通訊作者
（28）Maximal Likelihood Correspondence Estimation for Face Recognition Across Pose,IEEE Trans. on Image Processing,2014,通訊作者
（29）Semi-supervised Hashing via Kernel Hyperplane Learning for Scalable Image Search,IEEE Transactions on circuits and systems for video technology,2014,第3作者
（30）Data-Driven Hair Segmentation with Isomorphic Manifold Inference,Image and Vision Computing,2014,通訊作者
（31）CovGa: A novel descriptor based on symmetry of regions for head pose estimation, Neurocomputing,2014,通訊作者
（32）Joint Sparse Representation for Video-based Face Recognition,Neurocomputing,2014,第3作者
（33）Adaptive Discriminant Learning for Face Recognition,Pattern Recognition,2013,通訊作者
（34）A Comparative Study on Illumination Preprocessing in Face Recognition,Pattern Recognition,2013,通訊作者
（35）Manifold-Manifold Distance and Its Application to Face Recognition with Image Sets,IEEE Transactions on Image Processing,2012,第2作者
（36）Coupled Bias-Variance Trade off for Cross-Pose Face Recognition,IEEE Transactions on Image Processing,2012,第2作者
（37）Maximal Linear Embedding for Dimensionality Reduction,IEEE Trans. on Pattern Analysis and Machine Intelligence,2011,第2作者
（38）High Resolution Face Fusion for Gender Conversion,IEEE Trans. on System, Man, and Cybernetics (Part A),2011,第3作者
（39）Classifiability-based Discriminatory Projection Pursuit,IEEE Trans. on Neural Network,2011,第2作者
（40）Cross-pose face recognition based on partial least squares. ,Pattern Recognition Letters,2011,第2作者
（41）WLD: A Robust Local Image Descriptor,IEEE Trans. on Pattern Analysis and Machine Intelligence,2010,第2作者
（42）A Compositional and Dynamic Model for Face Aging,IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,第3作者
（43）Fusing Local Patterns of Gabor Magnitude and Phase for Face Recognition. ,IEEE Trans. on Image Processing,2010,第2作者
（44）Hierarchical Ensemble of Global and Local Classifiers for Face Recognition,IEEE Trans. on Image Processing,2009,第2作者
（45）Head Yaw Estimation from Asymmetry of Facial Appearance,IEEE Trans. on System, Man, and Cybernetics, Part B,2008,第2作者
（46）The CAS-PEAL Large-Scale Chinese Face Database and Baseline Evaluations,IEEE Trans. on System Man, and Cybernetics (Part A),2008,第3作者
（47）Locally Linear Regression for Pose Invariant Face Recognition. ,IEEE Trans. on Image Processing,2007,第2作者
（48）Histogram of Gabor Phase Patterns (HGPP): A Novel Object Representation Approach for Face Recognition. ,IEEE Transaction on Image Processing,2007,第2作者
