基本信息

山世光  博士/教授/博导  

中国科学院计算技术研究所/中国科学院大学

电子邮件: sgshan@ict.ac.cn

通信地址: 北京市海淀区科学院南路6号

邮政编码: 100190

研究方向:计算机视觉,模式识别,机器学习,基于视觉的情感计算


个人简介

**长期招聘博士后,从事Vision-based Deep Human Understanding相关方向,欢迎联络**

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,中国科学院大学岗位教授。他是基金委优青,第三批国家重要人才计划入选者,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,首届腾讯科学探索奖获得者,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80余篇,论文被谷歌学术引用18000余次。曾应邀担任过ICCV11,ACCV12/16/18,ICPR12/14,FG13/18/20,ICASSP14,BTAS18,AAAI20, CVPR19/20/21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(包括华为P20,V10,Mate20等手机)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。近年来开始关注基于视觉的情感计算研究,即所谓的“读心术”,包括表情识别、微表情分析、面部动作检测、生理指标测量、心理状态估计、精神状况分析等深刻理解人的计算机视觉方法。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、情感感知等带来的启示。


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

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

招生招聘信息

1、长期招聘博士后,要求博士期间研究方向为CV/PR/ML/NLP或神经科学领域,毕业于985高校者优先;

2、每年夏季招收免试研究生,研究方向为CV/PR/ML,学籍为中科院计算所;

3、招收优秀实习生,研究方向为CV/PR/ML,实习地点为中科院计算所。

教育背景

2013-12--2015-01   卡内基梅隆大学   访问学者
1999-09--2004-07   中国科学院计算技术研究所   博士
1997-09--1999-07   哈尔滨工业大学   硕士
1993-08--1997-08   哈尔滨工业大学   学士

工作经历与学术服务

工作简历
2013-03~现在, 中国科学院智能信息处理重点实验室, 常务副主任
2011-11~现在, 中国科学院智能信息处理重点实验室, 副主任
2010-10~现在, 中国科学院计算技术研究所, 研究员
2005-10~2010-09,中国科学院计算技术研究所, 副研究员
2004-08~2005-09,中国科学院计算技术研究所, 助理研究员
2002-08~2004-08,中国科学院计算技术研究所, 研究实习员
学术服务
2019-06-01-今,国际会议“AAAI2020”的Senior PC, Senior PC
2019-05-01-今,国际会议“FG2020”的领域主席(Area Chair), 领域主席(Area Chair)
2019-05-01-今,国际会议“CVPR2020”的领域主席(Area Chair), 领域主席(Area Chair)
2018-07-31-今,国际会议“国际计算机视觉与模式识别大会(CVPR)2019”的领域主席, 领域主席(Area Chair)
2018-01-01-2018-12-31,国际会议“亚洲计算机视觉大会(ACCV2018)”的领域主席, 领域主席(Area Chair)
2017-12-31-今,国际生物特征识别领域会议BTAS2018领域主席(Area Chair), 领域主席(Area Chair)
2017-08-31-今,国际会议“FG2018”的领域主席(Area Chair), 领域主席(Area Chair)
2016-12-31-今,国际刊物Computer Vision and Image Understanding的编委(Associate Editor), 编委(Associate Editor)
2016-12-30-2019-12-30,国际刊物Pattern Recognition Letters的编委(AE), 编委(Associate Editor)
2016-02-27-今,国际会议“亚洲计算机视觉大会(ACCV)2016”的领域主席, 领域主席(Area Chair)
2015-03-01-今,IEEE Senior member,
2013-05-01-今,刊物Frontier of Computer Science in China编委, Associate Editor
2013-02-27-2017-12-31,国际刊物IEEE Trans. on Image Processing的编委(AE), 编委(Associate Editor)
2012-05-22-2013-04-26,国际会议FG2013, Area Chair
2012-04-05-2013-09-30,国际会议ICPR2012的Area Chair,
2012-04-03-2012-10-06,国际会议ACCV2012的Area Chair,
2012-03-01-今,国际期刊Neurocomputing的Associate Editor,
2011-03-01-2012-11-08,国际会议ICCV2011的Area Chair,

教授课程

数字图像处理
模式识别与机器学习
人机交互界面理论与技术

出版信息

   
发表论文
(1) Cross Attention Network for Few-shot Classification, Proceeding of the 33rd Conference on Neural Information Processing Systems (NeurIPS2019), 2019-12, 第 4 作者
(2) Multi-label Co-regularization for Semi-supervised Facial Action Unit Recognition, Proceeding of the 33rd Conference on Neural Information Processing Systems (NeurIPS2019), 2019-12, 第 3 作者
(3) S^2GAN: Share Aging Factors across Ages and Share Aging Trends among Individuals, IEEE/CVF International Conference on Computer Vision and Pattern Recognition (ICCV2019), 2019-11, 第 3 作者
(4) Weakly Supervised Object Detection with Segmentation Collaboration., IEEE/CVF International Conference on Computer Vision and Pattern Recognition (ICCV2019), 2019-11, 第 3 作者
(5) Transferable Contrastive Network for Generalized Zero-Shot Learning, IEEE/CVF International Conference on Computer Vision and Pattern Recognition (ICCV2019), 2019-11, 第 3 作者
(6) Temporal Knowledge Propagation for Image to Video Person Re-identification, IEEE/CVF International Conference on Computer Vision and Pattern Recognition (ICCV2019), 2019-11, 第 4 作者
(7) AttGAN for Arbitrary Facial Attribute Editing: Only Change What You Want, IEEE Transactions on Image Processing, 2019-11, 通讯作者
(8) Tattoo Image Search at Scale: Joint Detection and Compact Representation Learning, IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI), 2019-10, 第 4 作者
(9) Deep Supervised Hashing for Fast Image Retrieval, International Journal of Computer Vision (IJCV)., 2019-09, 第 3 作者
(10) Unifying Visual Attribute Learning with Object Recognition in a Multiplicative Framework, IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI), 2019-07, 第 4 作者
(11) Interaction-and-Aggregation Network for Person Re-identification, Proceeding of IEEE/CVF Conference on Computer Vision and Pattern Recognition 2019 (CVPR2019), 2019-06, 第 5 作者
(12) VRSTC: Occlusion-Free Video Person Re-Identification, Proceeding of IEEE/CVF Conference on Computer Vision and Pattern Recognition 2019 (CVPR2019), 2019-06, 第 5 作者
(13) Exploring Context and Visual Pattern of Relationship for Scene Graph Generation, Proceeding of IEEE/CVF Conference on Computer Vision and Pattern Recognition 2019 (CVPR2019), 2019-06, 第 3 作者
(14) Fully Learnable Group Convolution for Acceleration of Deep Neural Networks, Proceeding of IEEE/CVF Conference on Computer Vision and Pattern Recognition 2019 (CVPR2019), 2019-06, 第 3 作者
(15) Weakly Supervised Image Classification through Noise Regularization, Proceeding of IEEE/CVF Conference on Computer Vision and Pattern Recognition 2019 (CVPR2019), 2019-06, 第 3 作者
(16) Local Relationship Learning with Person-specific Regularization for Facial Action Unit Detection, Proceeding of IEEE/CVF Conference on Computer Vision and Pattern Recognition 2019 (CVPR2019), 2019-06, 第 5 作者
(17) Twin-Cycle Autoencoder: Self-supervised Representation Learning from Entangled Movement for Facial Action Unit Detection, Proceeding of IEEE/CVF Conference on Computer Vision and Pattern Recognition 2019 (CVPR2019), 2019-06, 第 3 作者
(18) Improving Cross-database Face Presentation Attack Detection via Adversarial Domain Adaptation, Proceeding of International Conference on Biometrics, 2019-05, 第 3 作者
(19) Robust Remote Heart Rate Estimation from Face Utilizing Spatial-temporal Attention, Proceeding of 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019), 2019-05, 第 6 作者
(20) LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild, Proceeding of 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019), 2019-05, 第 8 作者
(21) Deformable Face Net: Learning Pose Invariant Feature with Pose Aware Feature Alignment for Face Recognition, Proceeding of 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019), 2019-05, 第 3 作者
(22) Improving Face Sketch Recognition via Adversarial Sketch-Photo Transformation, Proceeding of 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019), 2019-05, 第 3 作者
(23) FCSR-GAN: End-to-end Learning for Joint Face Completion and Super-resolution, Proceeding of 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019), 2019-05, 第 3 作者
(24) Occlusion aware facial expression recognition using CNN with attention mechanism, IEEE Transactions on Image Processing, 2019-05, 第 3 作者
(25) Hierarchical Attention for Part-Aware Face Detection, International Journal of Computer Vision (IJCV)., 2019-03, 通讯作者
(26) Face Recognition with Contrastive Convolution, European Conference on Computer Vision (ECCV 2018), 2018, 第 2 作者
(27) Generative Adversarial Network with Spatial Attention for Face Attribute Editing, European Conference on Computer Vision (ECCV 2018), 2018, 第 3 作者
(28) Learning Class Prototypes via Structure Alignment for Zero-Shot Recognition, European Conference on Computer Vision (ECCV 2018), 2018, 第 3 作者
(29) Facial Expression Recognition with Inconsistently Annotated Datasets, European Conference on Computer Vision (ECCV 2018), 2018, 第 2 作者
(30) Discriminant Analysis on Riemannian Manifold of Gaussian Distributions for Face Recognition with Image Sets, IEEE Transactions on Image Processing (TIP), 2018, 第 4 作者
(31) Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks, IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), 2018, 第 2 作者
(32) Duplex Generative Adversarial Network for Unsupervised Domain Adaptation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), 2018, 第 3 作者
(33) Mean-variance Loss for Deep Age Estimation from A Face, IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), 2018, 第 3 作者
(34) Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships, IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), 2018, 第 3 作者
(35) Attribute annotation on large-scale image database by active knowledge transfer, Image and Vision Computing, 2018, 第 5 作者
(36) Continuity-Discrimination Convolutional Neural Network for Visual Object Tracking, IEEE International Conference on Multimedia Expo, 2018, 第 4 作者
(37) Zero-Shot Facial Expression Recognition with Multi-Label Label Propagation, Asian Conference on Computer Vision, 2018, 第 3 作者
(38) Exemplar-Supported Generative Reproduction for Class Incremental Learning, Asian Conference on Computer Vision (ACCV), 2018, 第 3 作者
(39) Multi-label Learning from Noisy Labels with Non-linear Feature Transformation, Asian Conference on Computer Vision (ACCV), 2018, 第 3 作者
(40) VIPL-HR: A Multi-modal Database for Pulse Estimation from Less-constrained Face Video, Asian Conference on Computer Vision (ACCV), 2018, 第 3 作者
(41) Task-adaptive Feature Reweighting for Few Shot Classification, Asian Conference on Computer Vision (ACCV), 2018, 第 3 作者
(42) SynRhythm: Learning a Deep Heart Rate Estimator from General to Specific, International Conference on Pattern Recognition (ICPR), 2018, 第 3 作者
(43) Revised Contrastive Loss for Robust Age Estimation From Face, International Conference on Pattern Recognition (ICPR), 2018, 第 3 作者
(44) Patch-Gated CNN for Occlusion-aware Facial Expression Recognition, International Conference on Pattern Recognition (ICPR), 2018, 第 3 作者
(45) Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach, IEEE Trans. on Pattern Analysis and Machine Intelligence, 2018, 通讯作者
(46) Recursive Spatial Transformer (ReST) for Alignment-Free Face Recognition, Proceeding of International Conference on Computer Vision, 2017, 第 5 作者
(47) Learning Discriminative Latent Attributes for Zero-Shot Classification, Proceeding of International Conference on Computer Vision, 2017, 第 3 作者
(48) Prototype Discriminative Learning for Image Set Classification, IEEE Signal Processing Letters, 2017, 第 3 作者
(49) 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
(50) Funnel-structured cascade for multi-view face detection with alignment-awareness, Neurocomputing, 2017, 通讯作者
(51) 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
(52) Multi-View Discriminant Analysis, IEEE Trans. on Pattern Analysis and Machine Intelligence, 2016, 第 2 作者
(53) Relative Forest for Visual Attribute Prediction, IEEE Trans. on Image Processing, 2016, 通讯作者
(54) Spatial Pyramid Covariance-Based Compact Video Code for Robust Face Retrieval in TV-Series, IEEE Transactions on Image Processing, 2016, 通讯作者
(55) Learning Expressionlets via Universal Manifold Model for Dynamic Facial Expression Recognition, IEEE Transactions on Image Processing, 2016, 通讯作者
(56) Learning Prototypes and Similes on Grassmann Manifold for Spontaneous Expression Recognition, Journal of Computer Vision and Image Understanding, 2016, 通讯作者
(57) 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
(58) A Benchmark and Comparative Study of Video-based Face Recognition on COX Face Database, IEEE Trans. on Image Processing, 2015, 第 2 作者
(59) Face Recognition on Large-scale Video in the Wild with Hybrid Euclidean-and-Riemannian Metric Learning, Pattern Recognition, 2015, 通讯作者
(60) Bi-shifting Auto-Encoder for Unsupervised Domain Adaptation, Proceeding of International Conference on Computer Vision (ICCV), 2015, 第 2 作者
(61) 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
(62) A Unified Multiplicative Framework for Attribute Learning, Proceeding of International Conference on Computer Vision (ICCV), 2015, 第 3 作者
(63) 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
(64) 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
(65) 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
(66) 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
(67) 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
(68) Domain Adaptation for Face Recognition: Targetize Source Domain Images Bridged by Common Subspace (TSC), International Journal of Computer Vision, 2014, 通讯作者
(69) Maximal Likelihood Correspondence Estimation for Face Recognition Across Pose, IEEE Trans. on Image Processing, 2014, 通讯作者
(70) 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
(71) Data-Driven Hair Segmentation with Isomorphic Manifold Inference, Image and Vision Computing, 2014, 通讯作者
(72) CovGa: A novel descriptor based on symmetry of regions for head pose estimation,  Neurocomputing, 2014, 通讯作者
(73) Joint Sparse Representation for Video-based Face Recognition, Neurocomputing, 2014, 第 3 作者
(74) Adaptive Discriminant Learning for Face Recognition, Pattern Recognition, 2013, 通讯作者
(75) A Comparative Study on Illumination Preprocessing in Face Recognition, Pattern Recognition, 2013, 通讯作者
(76) Manifold-Manifold Distance and Its Application to Face Recognition with Image Sets, IEEE Transactions on Image Processing, 2012, 第 2 作者
(77) Coupled Bias-Variance Trade off for Cross-Pose Face Recognition, IEEE Transactions on Image Processing, 2012, 第 2 作者
(78) Maximal Linear Embedding for Dimensionality Reduction, IEEE Trans. on Pattern Analysis and Machine Intelligence, 2011, 第 2 作者
(79) High Resolution Face Fusion for Gender Conversion, IEEE Trans. on System, Man, and Cybernetics (Part A), 2011, 第 3 作者
(80) Classifiability-based Discriminatory Projection Pursuit, IEEE Trans. on Neural Network, 2011, 第 2 作者
(81) Cross-pose face recognition based on partial least squares. , Pattern Recognition Letters, 2011, 第 2 作者
(82) WLD: A Robust Local Image Descriptor, IEEE Trans. on Pattern Analysis and Machine Intelligence, 2010, 第 2 作者
(83) A Compositional and Dynamic Model for Face Aging, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 第 3 作者
(84) Fusing Local Patterns of Gabor Magnitude and Phase for Face Recognition. , IEEE Trans. on Image Processing, 2010, 第 2 作者
(85) Hierarchical Ensemble of Global and Local Classifiers for Face Recognition, IEEE Trans. on Image Processing, 2009, 第 2 作者
(86) Head Yaw Estimation from Asymmetry of Facial Appearance, IEEE Trans. on System, Man, and Cybernetics, Part B, 2008, 第 2 作者
(87) 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
(88) Locally Linear Regression for Pose Invariant Face Recognition. , IEEE Trans. on Image Processing, 2007, 第 2 作者
(89) Histogram of Gabor Phase Patterns (HGPP): A Novel Object Representation Approach for Face Recognition. , IEEE Transaction on Image Processing, 2007, 第 2 作者
(90) 
发表著作
(1) 《人工智能导论》, 中国科学技术出版社, 2018-08, 第 5 作者