基本信息
雷震  男  硕导  中国科学院自动化研究所
电子邮件: zlei@nlpr.ia.ac.cn
通信地址: 北京市海淀区中关村东路95号智能化大厦1402
邮政编码: 100190
部门/实验室:模式识别国家重点实验室

研究领域

计算机视觉,模式识别,人脸识别,智能视频分析

招生信息

   
招生专业
081104-模式识别与智能系统
081203-计算机应用技术
招生方向
人脸分析与识别
智能视频分析

教育背景

2005-09--2010-06   中国科学院自动化研究所   工学博士
2001-09--2005-06   中国科学技术大学   工学学士
学历
研究生
学位
工学博士

工作经历

2011--今,中国科学院自动化研究所,助理研究员、副研究员
2010--2011, IBM中国研究院 研究员
社会兼职
2017-11-01-今,中国图象图形学会视频监控与安全专委会, 副秘书长
2012-02-28-2019-03-01,全国安防标委会人体生物特征识别应用技术委员会, 通讯委员

教授课程

视频监控及应用

专利与奖励

   
奖励信息
(1) FG2017微表情竞赛第一名, 一等奖, 其他, 2017
(2) CCBR2017最佳学生论文奖, 一等奖, 其他, 2017
(3) ICB2015最佳学生论文奖, 一等奖, 其他, 2015
(4) IJCB2014最佳学生论文奖, 一等奖, 其他, 2014
(5) ICCV2013 300-w人脸关键点定位竞赛第一名, 一等奖, 其他, 2013
(6) FG2013最佳学生论文奖提名, 二等奖, 其他, 2013
专利成果
( 1 )  双验证人脸防伪方法及装置, 发明, 2012, 第 3 作者, 专利号: 201210059454.7
( 2 ) 增强类局部二元模式特征人脸识别性能的滤波器设计方法, 发明, 2012, 第 2 作者, 专利号: 201210182809.1
( 3 ) 基于动态图匹配的目标跟踪方法, 发明, 2015, 第 2 作者, 专利号: 201210413974.3
( 4 ) 一种基于结构化模型的人脸检测方法, 发明, 2015, 第 2 作者, 专利号: 201310014629.7
( 5 ) 基于在线识别的特定人脸跟踪方法, 发明, 2015, 第 2 作者, 专利号: 201310014870.X
( 6 ) 在线视频浓缩装置、系统及方法, 发明, 2015, 第 3 作者, 专利号: 201080065438.8
( 7 ) 基于时空结构上下文关系在线学习的目标跟踪方法, 发明, 2016, 第 3 作者, 专利号: 201210359621.X
( 8 ) 一种基于多任务模型的多分辨率行人检测方法及其装置, 发明, 2016, 第 3 作者, 专利号: 201310196658.X
( 9 ) 一种人脸活体检测方法, 发明, 2017, 第 2 作者, 专利号: 201410122631.0
( 10 ) 一种基于目标多部件学习的视频分割方法, 发明, 2017, 第 1 作者, 专利号: 201410818534.5
( 11 ) 一种用于拥挤场景下的多个行人检测方法, 发明, 2015, 第 3 作者, 专利号: 201210187843.8

出版信息


发表论文
(1) Dependence-Aware Feature Coding for Person Re-Identification, IEEE Signal Processing Letters, 2018, 通讯作者
(2) Face Alignment In Full Pose Range: A 3D Total Solution, IEEE Transaction on Pattern Analysis and Machine Intelligence, 2017, 通讯作者
(3) Efficient Group-n Encoding and Decoding for Facial Age Estimation, IEEE Transaction on Pattern Analysis and Machine Intelligence, 2017, 第 3 作者
(4) Auxiliary Demographic Information Assisted Age Estimation with Cascaded Structure, IEEE Transactions on Cybernetics, 2017, 第 3 作者
(5) Deep Hybrid Similarity Learning for Person Re-identification, IEEE Transaction on Circuits and Systems for Video Technology, 2017, 第 4 作者
(6) Multi-label convolutional neural network based pedestrian attribute classification, mage and Vision Computing, 2017, 第 3 作者
(7) Multi-Camera Multi-Target Tracking with Space-Time-View Hyper-graph, International Journal of Computer Vision, 2017, 第 2 作者
(8) S3FD: Single Shot Scale-invariant Face Detector, Proceedings of IEEE International Conference on Computer Vision, 2017, 通讯作者
(9) Exclusivity-Consistency Regularized Multi-view Subspace Clustering, Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2017, 通讯作者
(10) Learning Stacked Image Descriptor for Face Recognition, IEEE Transaction on Circuits and Systems for Video Technology, 2016, 第 1 作者
(11) Exploiting Hierarchical Dense Structures on Hypergraphs for Multi-Object Tracking, IEEE Transaction on Pattern Analysis and Machine Intelligence, 2016, 通讯作者
(12) Embedding Deep Metric for Person Re-identifi cation: A Study Against Large Variations, Proceedings of European Conference on Computer Vision, (ECCV2016), 2016, 通讯作者
(13) Face Alignment Across Large Poses: A 3D Solution, Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2016, 通讯作者
(14) CRAFT Objects from Images, Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2016, 通讯作者
(15) Metric Embedded Discriminative Vocabulary Learning for High-Level Person Representation, Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016, 第 2 作者
(16) Large Scale Similarity Learning Using Similar Pairs for Person Verification, Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016, 第 3 作者
(17) Person-Specific Face Anti-Spoofing with Subject Domain Adaptation, IEEE Transactions on Information Forensics and Security, 2015, 通讯作者
(18) Moving Object Detection Revisited: Speed and Robustness, IEEE Transaction on Circuits and Systems for Video Technology, 2015, 第 4 作者
(19) Convolutional Channel Features, Proceedings of IEEE International Conference on Computer Vision, 2015, 第 3 作者
(20) Subspace learning with frequency regularizer: its application to face recognition, Proceedings of the 8th IAPR International Conference on Biometrics, 2015, 第 1 作者
(21) Multi-label CNN Based Pedestrian Attribute Learning for Soft Biometrics, Proceedings of the 8th IAPR International Conference on Biometrics, 2015, 第 4 作者
(22) High-Fidelity Pose and Expression Normalization for Face Recognition in the Wild, Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2015, 通讯作者
(23) JOTS: Joint Online Tracking and Segmentation, Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2015, 通讯作者
(24) Fine-grained Evaluation on Face Detection in the Wild, Proceedings of 11th IEEE International Conference on Automatic Face and Gesture Recognition, 2015, 第 3 作者
(25) Shared Representation Learning for Heterogenous Face Recognition, Proceedings of 11th IEEE International Conference on Automatic Face and Gesture Recognition, 2015, 第 2 作者
(26) Learning Discriminant Face Descriptor, IEEE Transaction on Pattern Analysis and Machine Intelligence, 2014, 第 1 作者
(27) Robust Deformable and Occluded Object Tracking With Dynamic Graph, IEEE Transaction on Image Processing, 2014, 通讯作者
(28) Object Detection by Labeling Superpixels, Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2014, 第 4 作者
(29) Coupled Discriminant Analysis for Heterogeneous Face Recognition, IEEE Transactions on Information Forensics and Security, 2012, 第 1 作者
(30) Fast Multi-scale Local Phase Quantization Histogram for Face Recognition, Pattern Recognition Letters, 2012, 第 1 作者
(31) Feature Space Locality Constraint for Kernel based Nonlinear Discriminant Analysis, Pattern Recognition, 2012, 第 1 作者
(32) Contextual Constraints based Linear Discriminant Analysis, Pattern Recognition Letters, 2011, 第 1 作者
(33) Face Recognition by Exploring Information Jointly in Space, Scale and Orientation, IEEE Transaction on Image Processing, 2011, 第 1 作者

科研活动

Keynote Speaker, “Multispectral Methods for Biometric Anti-spoofing” on 2011 FP7 RISE Beijing Conference.
Associate Editor, Neurocomputing, from 2017
Area Chair, 11th IAPR International Conference on Biometrics (ICB 2018)
Area Chair, IAPR/IEEE International Conference on Biometric (ICB 2016)
Area Chair, IAPR/IEEE International Conference on Biometric (ICB 2015)
Area Chair, 11th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2015)
Area Chair, International Joint Conference on Biometrics (IJCB 2014)
Publicity Co-Chair, 10th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS-2013)
Program Committee, International Joint Conference on Biometrics (IJCB 2017)
Program Committee, 8th IEEE International Conference on Biometrics: Theory, Applications, and Systems (BTAS 2016)
Program Committee, 10th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2013)
Program Committee, 1st ACCV Workshop on Computer Vision with Local Binary Pattern Variants (LBP 2012)
Program Committee, International Conference on Informatics, Electronics & Vision (ICIEV12)
Review for IEEE Trans. on Pattern Analysis and Machine Intelligence (T-PAMI), from 2007.


科研项目
( 1 ) 监控场景中的实用目标检测方法研究, 主持, 国家级, 2015-01--2018-12
( 2 ) 基于图像结构和空间分布的子空间分析方法, 主持, 国家级, 2012-01--2014-12
( 3 ) 面向海量视频信息的目标识别和研判技术与设备研发, 参与, 国家级, 2013-05--2015-12
( 4 ) 海量视频数据分析研判技术研发与系统集成, 参与, 国家级, 2012-05--2015-05
( 5 ) 无约束视频图像的判别特征学习与自适应方法研究, 参与, 国家级, 2016-01--2019-12
( 6 ) 基于场景感知的视频目标结构化描述与识别, 参与, 国家级, 2016-07--2019-06