雷震

雷震  /  

  • 职  称: 正高级
  • 电子邮件: zhen.lei@ia.ac.cn

个人简历

姓名

雷震

性别

联系方式

zlei@nlpr.ia.ac.cn

专业技术职务

研究员

部门/实验室

模式识别国家重点实验室

通讯地址

北京市海淀区中关村东路95号

邮编

100190

研究领域

计算机视觉,模式识别,人脸识别,目标检测与识别,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

工作简历

2018-11~现在, 中国科学院自动化研究所, 研究员
2013-10~2018-10,中国科学院自动化研究所, 副研究员
2011-07~2013-09,中国科学院自动化研究所, 助理研究员
2010-07~2011-07,国际商业机器(IBM)有限公司中国研究院, 研究员

兼职经历

2019-09-01-今,中国人工智能学会模式识别专委会, 委员
2019-09-01-今,中国自动化学会模式识别与机器智能专委会, 委员
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
2017-10-31-今,中国图象图形学会机器视觉专委会, 委员
2016-01-01-今,中国计算机学会计算机视觉专委会, 委员
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

发表论文

(1) Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection, Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, (CVPR2020), 2020, 通讯作者
(2) PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes, Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, (AAAI 2020), 2020, 第 4 作者
(3) Relational Learning for Joint Head and Human Detection, Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, (AAAI 2020), 2020, 第 4 作者
(4) Learning Meta Face Recognition in Unseen Domains, Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, (CVPR2020), 2020, 通讯作者
(5) Domain Balancing: Face Recognition on Long-Tailed Domains, Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, (CVPR2020), 2020, 通讯作者
(6) Deep Spatial Gradient and Temporal Depth Learning for Face Anti-spoofing, Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, (CVPR2020), 2020, 第 9 作者
(7) AUTO-FAS: SEARCHING LIGHTWEIGHT NETWORKS FOR FACE ANTI-SPOOFING, Proceedings of the 45th International Conference on Acoustics, Speech, and Signal Processing, (ICASSP 2020), 2020, 第 6 作者
(8) Learning Meta Model for Zero- and Few-shot Face Anti-spoofing, Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, (AAAI 2020), 2020, 第 9 作者
(9) Context-Aware Attention Network for Image-Text Retrieval, Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, (CVPR2020), 2020, 通讯作者
(10) Domain Adaptive Person Re-Identification via Camera Style Generation and Label Propagation, IEEE Transactions on Information Forensics and Security, 2019, 第 5 作者
(11) Attention-Based Two-Stream Convolutional Networks for Face Spoofing Detection, IEEE Transactions on Information Forensics and Security, 2019, 第 3 作者
(12) Face Alignment In Full Pose Range: A 3D Total Solution, IEEE Transaction on Pattern Analysis and Machine Intelligence, 2019, 通讯作者
(13) Single-Shot Scale-Aware Network for Real-Time Face Detection, International Journal of Computer Vision, 2019, 通讯作者
(14) Large-Scale Bisample Learning on ID Versus Spot Face Recognition, International Journal of Computer Vision, 2019, 通讯作者
(15) Multi-view Subspace Clustering with Intactness-Aware Similarity, Pattern Recognition, 2019, 通讯作者
(16) FLDet: A CPU Real-time Joint Face and Landmark Detector, Proceedings of the 12th IAPR International Conference on Biometrics, (ICB2019), 2019, 第 4 作者
(17) Improving Face Anti-Spoofing by 3D Virtual Synthesis, Proceedings of the 12th IAPR International Conference on Biometrics, (ICB2019), 2019, 通讯作者
(18) Learning Lightweight Face Detector with Knowledge Distillation, Proceedings of the 12th IAPR International Conference on Biometrics, (ICB2019), 2019, 通讯作者
(19) Semantic Alignment: Finding Semantically Consistent Ground-truth for Facial Landmark Detection, Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, (CVPR2019), 2019, 第 6 作者
(20) AdaptiveFace: Adaptive Margin and Sampling for Face Recognition, Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, (CVPR2019), 2019, 通讯作者
(21) Clustering and Dynamic Sampling Based Unsupervised Domain Adaption for Person Re-identification, Proceedings of IEEE International Conference on Multimedia and Expo, (ICME 2019), 2019, 第 3 作者
(22) Selective Refinement Network for High Performance Face Detection, Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, (AAAI 2019), 2019, 第 4 作者
(23) Dependence-Aware Feature Coding for Person Re-Identification, IEEE Signal Processing Letters, 2018, 通讯作者
(24) Face Alignment In Full Pose Range: A 3D Total Solution, IEEE Transaction on Pattern Analysis and Machine Intelligence, 2017, 通讯作者
(25) Efficient Group-n Encoding and Decoding for Facial Age Estimation, IEEE Transaction on Pattern Analysis and Machine Intelligence, 2017, 第 3 作者
(26) Auxiliary Demographic Information Assisted Age Estimation with Cascaded Structure, IEEE Transactions on Cybernetics, 2017, 第 3 作者
(27) Deep Hybrid Similarity Learning for Person Re-identification, IEEE Transaction on Circuits and Systems for Video Technology, 2017, 第 4 作者
(28) Multi-label convolutional neural network based pedestrian attribute classification, mage and Vision Computing, 2017, 第 3 作者
(29) Multi-Camera Multi-Target Tracking with Space-Time-View Hyper-graph, International Journal of Computer Vision, 2017, 第 2 作者
(30) S3FD: Single Shot Scale-invariant Face Detector, Proceedings of IEEE International Conference on Computer Vision, 2017, 通讯作者
(31) Exclusivity-Consistency Regularized Multi-view Subspace Clustering, Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2017, 通讯作者
(32) Learning Stacked Image Descriptor for Face Recognition, IEEE Transaction on Circuits and Systems for Video Technology, 2016, 第 1 作者
(33) Exploiting Hierarchical Dense Structures on Hypergraphs for Multi-Object Tracking, IEEE Transaction on Pattern Analysis and Machine Intelligence, 2016, 通讯作者
(34) 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
(35) Face Alignment Across Large Poses: A 3D Solution, Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2016, 通讯作者
(36) CRAFT Objects from Images, Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2016, 通讯作者
(37) Metric Embedded Discriminative Vocabulary Learning for High-Level Person Representation, Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016, 第 2 作者
(38) Large Scale Similarity Learning Using Similar Pairs for Person Verification, Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016, 第 3 作者
(39) Person-Specific Face Anti-Spoofing with Subject Domain Adaptation, IEEE Transactions on Information Forensics and Security, 2015, 通讯作者
(40) Moving Object Detection Revisited: Speed and Robustness, IEEE Transaction on Circuits and Systems for Video Technology, 2015, 第 4 作者
(41) Convolutional Channel Features, Proceedings of IEEE International Conference on Computer Vision, 2015, 第 3 作者
(42) Subspace learning with frequency regularizer: its application to face recognition, Proceedings of the 8th IAPR International Conference on Biometrics, 2015, 第 1 作者
(43) Multi-label CNN Based Pedestrian Attribute Learning for Soft Biometrics, Proceedings of the 8th IAPR International Conference on Biometrics, 2015, 第 4 作者
(44) 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
(45) JOTS: Joint Online Tracking and Segmentation, Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2015, 通讯作者
(46) 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
(47) Shared Representation Learning for Heterogenous Face Recognition, Proceedings of 11th IEEE International Conference on Automatic Face and Gesture Recognition, 2015, 第 2 作者
(48) Learning Discriminant Face Descriptor, IEEE Transaction on Pattern Analysis and Machine Intelligence, 2014, 第 1 作者
(49) Robust Deformable and Occluded Object Tracking With Dynamic Graph, IEEE Transaction on Image Processing, 2014, 通讯作者
(50) Object Detection by Labeling Superpixels, Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2014, 第 4 作者
(51) Coupled Discriminant Analysis for Heterogeneous Face Recognition, IEEE Transactions on Information Forensics and Security, 2012, 第 1 作者
(52) Fast Multi-scale Local Phase Quantization Histogram for Face Recognition, Pattern Recognition Letters, 2012, 第 1 作者
(53) Feature Space Locality Constraint for Kernel based Nonlinear Discriminant Analysis, Pattern Recognition, 2012, 第 1 作者
(54) Contextual Constraints based Linear Discriminant Analysis, Pattern Recognition Letters, 2011, 第 1 作者
(55) Face Recognition by Exploring Information Jointly in Space, Scale and Orientation, IEEE Transaction on Image Processing, 2011, 第 1 作者

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
( 12 ) 人脸检测方法及装置、计算机可读存储介质、设备, 发明, 2019, 第 1 作者, 专利号: 201710379478.3
( 13 ) 图像水印去除装置, 发明, 2020, 第 1 作者, 专利号: 201711123854.9
( 14 ) 人脸检测方法及装置、计算机可读存储介质、设备, 发明, 2020, 第 3 作者, 专利号: 201710541087.7
( 15 ) 基于多任务学习的卷积神经网络的人脸属性分析方法, 发明, 2019, 第 3 作者, 专利号: 201610856231.1
( 16 ) 基于卷积神经网络的人脸图像年龄估算方法, 发明, 2019, 第 3 作者, 专利号: 201610857697.3

荣誉及奖励

(1) CVPR2019低光照人脸检测挑战赛, 一等奖, 其他, 2019
(2) ICCV2019轻量级人脸识别挑战赛, 一等奖, 其他, 2019
(3) 国际模式识别协会(IAPR)青年学者奖, 一等奖, 其他, 2019
(4) 国家科学技术进步奖, 二等奖, 国家级, 2019
(5) CCBR2017最佳学生论文奖, 一等奖, 其他, 2017
(6) FG2017微表情竞赛第一名, 一等奖, 其他, 2017
(7) ICB2015最佳学生论文奖, 一等奖, 其他, 2015
(8) IJCB2014最佳学生论文奖, 一等奖, 其他, 2014
(9) FG2013最佳学生论文奖提名, 二等奖, 其他, 2013
(10) ICCV2013 300-w人脸关键点定位竞赛第一名, 一等奖, 其他, 2013

科研项目

( 1) 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
( 2 ) 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
( 3) 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
( 4 ) 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
( 5 ) 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
( 6 ) 基于可见光/红外融合传感的运动目标检测及行为预测系统研发, 主持, 国家级, 2020-07--2023-06