基本信息
兴军亮  男  硕导  中国科学院自动化研究所
电子邮件: jlxing@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403房间
邮政编码: 100190
部门/实验室:智能系统与工程研究中心

个人介绍

兴军亮,2012年毕业于清华大学计算机科学与技术系,获工学博士学位,同年进入中国科学院自动化研究所模式识别国家重点实验室工作,现为中科院自动化所研究员、博士研究生导师、特聘青年骨干。201212月至201312月期间新加坡国立大学访问研究员,20154月至11月微软亚洲研究院网络媒体组铸星计划访问教授,美国电器与电子工程学会(IEEE)高级会员,中国计算机学会(CCF)会员,计算机视觉专委会委员。研究领域为计算机视觉、机器学习和人工智能。目前已在重要国际期刊如TPAMIIJCVTIPTOMM以及重要国际会议上如ICCVCVPRECCVACM MultimediaAAAI上发表论文100多篇,出版计算机视觉译著3部,撰写深度学习及人工智能领域著作2部。在攻读博士期间,曾获得清华大学计算机系学术新秀、清华大学优秀博士毕业论文、谷歌学者、清华大学综合一等奖学金等荣誉称号和奖励,在博士后研究期间,带领学生完成的论文“WowYou Are so Beautiful Today获得了2013年多媒体领域重要国际会议ACM Multimedia最佳论文奖。多次获得相关研究方向的国际和国内挑战赛冠军。目前作为项目负责人正在主持国家自然科学基金面上项目一项,作为项目实际负责人和核心骨干参与了973863等多项国家重要研究课题,以及与惠普、英特尔、欧姆龙、富士通、华为等知名企业的多项合作研究课题。正在承担的研究课题主要包括人脸和人体视觉、网络敏感内容安全和大数据分析应用,关心的研究问题包括物体检测、跟踪和分割、图像识别检索以及大数据分析与建模等,关心的技术模型包括Boosting、支持向量机、稀疏表示和深度学习等。近年来重点围绕深度强化学习展开了深入的研究,在智能博弈等人工智能最前沿方向进行探索和研究。

招生信息

   
招生专业
081104-模式识别与智能系统
招生方向
计算机博弈
计算机视觉
深度强化学习

研究经历

2016-02--2016-08   360人工智能研究院   访问研究员
2015-04--2015-11   微软亚洲研究院   铸星计划访问教授
2012-12--2013-12   新加坡国立大学   博士后研究员
2007-09--2012-06   清华大学   工学博士
2003-09--2007-06   西安交通大学   工学理学双学士

工作经历

   
工作简历
2018-11~现在, 中国科学院自动化研究所, 研究员
2015-11~2018-10,中国科学院自动化研究所, 副研究员
2012-07~2015-10,中国科学院自动化研究所, 助理研究员
社会兼职
2020-04-30-今,中国科学院人工智能创新研究院, 创新专家组专家
2019-01-01-今,计算机学会, 高级会员
2017-01-01-今,计算机协会计算机视觉专委会委员, 委员
2008-12-31-今,国际电子与电气工程协会会员, 高级会员

教授课程

计算博弈原理与应用
博弈论

专利与奖励

   
奖励信息
(1) 人工智能城市挑战赛异常事件检测项目, 一等奖, 其他, 2018
(2) 微软百万名人识别挑战赛第一名, 一等奖, 其他, 2017
(3) IEEE CIG国际星际争霸挑战赛, 二等奖, 其他, 2017
(4) 微软百万名人识别挑战赛第一名, 一等奖, 其他, 2016
(5) ACM国际多媒体大会最佳论文奖, 一等奖, 其他, 2013
专利成果
( 1 ) 近似重复图像检测方法, 发明, 2016, 第 3 作者, 专利号: CN106570141A
( 2 ) 一种基于成分距离关系图的视频目标跟踪方法, 发明, 2013, 第 3 作者, 专利号: CN103646407B
( 3 ) 车辆碰撞的预警方法及装置, 发明, 2016, 第 3 作者, 专利号: CN106326866A
( 4 ) Skeleton-Based Action Detection Using Recurrent Neural Network, 发明, 2016, 第 4 作者, 专利号: US10019629B2
( 5 ) 一种网络环境下的近似重复图像搜索方法, 发明, 2017, 第 3 作者, 专利号: CN104462199B

出版信息

   
发表论文
(1) Robust Object Tracking based on Temporal and Spatial Deep Networks, IEEE Transactions on Image Processing (TIP), 2020, 通讯作者
(2) Recognizing Profile Faces by Imagining Frontal View, International Journal of Computer Vision (IJCV), 2020, 通讯作者
(3) Tracking-by-Fusion via Gaussian Process Regression Extended to Transfer Learning, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020, 第 3 作者
(4) Dual L1-Normalized Context Aware Tensor Power Iteration and Its Applications to Multi-object Tracking and Multi-graph Matching, International Journal of Computer Vision (IJCV), 2020, 第 4 作者
(5) Hybrid Learning for Multi-agent Cooperation with Sub-optimal Demonstrations, International Joint Conferences on Artificial Intelligence (IJCAI), 2020, 第 1 作者
(6) Potential Driven Reinforcement Learning for Hard Exploration Tasks, International Joint Conferences on Artificial Intelligence (IJCAI), 2020, 通讯作者
(7) Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020, 第 4 作者
(8) Asymmetric 3D Convolutional Neural Networks for action recognition, Pattern Recognition (PR), 2019, 第 5 作者
(9) Hierarchical Contextual Refinement Networks for Human Pose Estimation, IEEE Translations on Image Processing (TIP), 2019, 第 3 作者
(10) High Performance Person Re-identification via a Boosting Ranking Ensemble, Pattern Recognition (PR), 2019, 第 3 作者
(11) Temporal-Spatial Mapping for Action Recognition, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2019, 第 4 作者
(12) SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, 第 5 作者
(13) Multi-Prototype Networks for Unconstrained Set-based Face Recognition, International Joint Conferences on Artificial Intelligence (IJCAI), 2019, 第 6 作者
(14) View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019, 第 3 作者
(15) Dual L1-Normalized Context Aware Tensor Power Iteration and Its Applications to Multi-object Tracking and Multi-graph Matching, International Journal of Computer Vision (IJCV), 2019, 第 4 作者
(16) Learning Deep Decentralized Policy Network by Collective Rewards for Real-Time Combat Game, International Joint Conferences on Artificial Intelligence (IJCAI), 2019, 通讯作者
(17) 3D-Aided Dual-Agent GANs for Unconstrained Face Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019, 第 4 作者
(18) Deep Cost-Sensitive and Order-Preserving Feature Learning for Cross-Population Age Estimation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, 第 2 作者
(19) Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, 第 3 作者
(20) Towards Pose Invariant Face Recognition in the Wild, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, 第 9 作者
(21) Do not Lose the Details: Reinforced Representation Learning for High Performance Visual Tracking, International Joint Conferences on Artificial Intelligence (IJCAI), 2018, 第 3 作者
(22) 3D-Aided Deep Pose-Invariant Face Recognition, International Joint Conferences on Artificial Intelligence (IJCAI), 2018, 第 6 作者
(23) Deep Constrained Siamese Hash Coding Network and Load-Balanced Locality-Sensitive Hashing for Near Duplicate Image Detection, IEEE Transactions on Image Processing (TIP), 2018, 第 3 作者
(24) Online Multi-Target Tracking with Tensor-Based High-Order Graph Matching, International Conference on Pattern Recognition (ICPR), 2018, 第 2 作者
(25) Deep Age Estimation Model Stabilization from Images to Videos, International Conference on Pattern Recognition (ICPR), 2018, 第 4 作者
(26) DCFNet: Discriminant Correlation Filters Network for Visual Tracking, International Conference on Pattern Recognition (ICPR), 2018, 第 3 作者
(27) Spatio-temporal attention-based LSTM networks for 3D action recognition and detection, IEEE Transactions on Image Processing (TIP), 2018, 第 3 作者
(28) Multi-Modality Multi-Task Recurrent Neural Network for Online Action Detection, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2018, 第 4 作者
(29) Spatio-Temporal Attention Based LSTM Networks for 3D Action Recognition and Detection, IEEE Transactions on Image Processing (TIP), 2018, 第 3 作者
(30) Tracking-by-Fusion via Gaussian Process Regression Extended to Transfer Learning, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018, 第 3 作者
(31) Towards Robust and Accurate Multi-view and Partially-occluded Face Alignment, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017, 第 1 作者
(32) Diagnosing Deep Learning Models for High Accuracy Age Estimation from A Single Image, Pattern Recognition (PR), 2017, 第 1 作者
(33) A Fast, Adaptive, Tree-structured Region Extraction Approach, IEEE Transactions on Circuits, System and Video Technology (TCSVT), 2017, 第 1 作者
(34) Diagnosing Deep Learning Models for High Accuracy Age Estimation from A Single Image, Pattern Recognition (PR), 2017, 第 2 作者
(35) Semi-Supervised Tensor-Based Graph Embedding Learning and Its Application to Visual Discriminant Tracking, IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2017, 第 3 作者
(36) An end-to-end spatio-temporal attention model for human action recognition from skeleton data, AAAI Annual Conference on Artificial Intelligence (AAAI), 2017, 第 3 作者
(37) Beyond Group: Multiple Person Tracking via Minimal Topology-Energy-Variation, IEEE Transactions on Image Processing (TIP), 2017, 第 3 作者
(38) Robust Object Tracking Based on Temporal and Spatial Deep Networks, IEEE International Conference on Computer Vision (ICCV), 2017, 第 2 作者
(39) View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data, IEEE International Conference on Computer Vision (ICCV), 2017, 第 3 作者
(40) Human Pose Estimation Using Global and Local Normalization, IEEE International Conference on Computer Vision (ICCV), 2017, 第 3 作者
(41) Pose-Driven Deep Convolutional Model for Person Re-identification, IEEE International Conference on Computer Vision (ICCV), 2017, 第 4 作者
(42) A Deep Regression Architecture with Two-Stage Re-initialization for High Performance Facial Landmark Detection, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, 第 3 作者
(43) Multi-Cue Illumination Estimation via a Tree-Structured Group Joint Sparse Representation, International Journal on Computer Vision (IJCV), 2016, 第 5 作者
(44) Robust Facial Landmark Detection via Recurrent Attentive-Refinement, European Conference on Computer Vision (ECCV), 2016, 第 3 作者
(45) Deep Attributes Driven Person Re-identification, European Conference on Computer Vision (ECCV), 2016, 第 3 作者
(46) Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks, European Conference on Computer Vision (ECCV), 2016, 第 3 作者
(47) Tensor Power Iteration for Multi-Graph Matching, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2016, 第 4 作者
(48) Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks, AAAI Annual Conference on Artificial Intelligence (AAAI), 2016, 第 3 作者
(49) Local Subspace Collaborative Tracking, IEEE International Conference on Computer Vision (ICCV), 2015, 第 4 作者
(50) Shape Driven Kernel Adaptation in Convolutional Neural Network for Robust Facial Traits Recognition, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2015, 第 2 作者
(51) Towards Multi-view and Partially-occluded Face Alignment, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, 第 1 作者
(52) Wow! You Are So Beautiful Today!, ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), 2014, 第 1 作者
(53) Circle & Search: Attribute-aware Shoe Retrieval, ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), 2014, 第 3 作者
(54) Scene Transformation for Detector Adaptation, Pattern Recognition Letters (PRL), 2014, 第 2 作者
(55) Transfer Learning Based Visual Tracking with Gaussian Process Regression, European Conference on Computer Vision (ECCV), 2014, 第 4 作者
(56) Multi-target Tracking with Motion Context in Tensor Power Iteration, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2014, 第 5 作者
(57) Robust Object Tracking with Online Multi-lifespan Dictionary Learning, IEEE International Conference on Computer Vision (ICCV), 2013, 第 1 作者
(58) Discriminant Tracking Using Tensor Representation with Semi-supervised Improvement, IEEE International Conference on Computer Vision (ICCV), 2013, 第 2 作者
(59) Multi-target Tracking by Rank-1 Tensor Approximation, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2013, 第 3 作者
(60) Scene Aware Detection and Block Assignment Tracking in Crowded Scenes, Image and Vision Computing (IVC), 2012, 第 3 作者
(61) Multiple Players Tracking in Sports Video: a Dual-Mode Two-Way Bayesian Inference Approach with Progressive Observation Modeling, IEEE Transactions on Image Processing (TIP), 2011, 第 1 作者
(62) Robust Crowd Counting Using Detection Flow, IEEE International Conference on Image Processing (ICIP), 2011, 第 1 作者
(63) Background Subtraction through Multiple Life Span Modeling, IEEE International Conference on Image Processing (ICIP), 2011, 第 1 作者
(64) Multiple Human Tracking Based on Multi-View Upper-Body Detection and Discriminative Learning, IEEE International Conference on Pattern Recognition (ICPR), 2010, 第 1 作者
(65) Multi-Object Tracking through Occlusions by Local Tracklets Filtering and Global Tracklets Association with Detection Responses, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2009, 第 1 作者
发表著作
(1) 计算机视觉—算法与应用, Computer Vision: Algorithms and Applications, 清华大学出版社, 2012-01, 第 2 作者
(2) 视觉机器学习20讲, Twenty Lectures in Vision and Learning, 清华大学出版社, 2015-06, 第 2 作者
(3) 图像处理、分析与机器视觉, Image Processing, Analyses, and Machine Vision, 清华大学出版社, 2016-01, 第 1 作者
(4) 人工智能:用AI技术打造智能化未来, 中国科学技术出版社, 2019-04, 第 5 作者