
Jun Wan is a Professor at the State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA). He earned his Bachelor of Science (B.S.) degree from the China University of Geosciences, Beijing, in 2008, and his Doctor of Philosophy (Ph.D.) degree from the Beijing Jiaotong University, in 2015. His primary research expertise lies in computer vision and machine learning, with a particular focus on facial analysis, gesture recognition, and human action understanding.
Professor Wan has made significant contributions to his field, with over 100 peer-reviewed publications in top-tier journals such as IEEE TPAMI, IJCV, and JMLR, as well as premier conferences including AAAI, CVPR, ICCV, and IJCAI. He currently serves as an Associate Editor for IEEE Transactions on Information Forensics and Security (TIFS) (2024–present) and IET Biometrics (2020–present). Additionally, he has been a Guest Editor for special issues in IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), International Journal of Computer Vision (IJCV), and IEEE Transactions on Biometrics, Behavior, and Identity Science (TBOM).
Research Areas
Education
Sep. 2008 - Jan. 2015 Beijing Jiaotong University Ph.D.
Sep. 2004 - Jun. 2008 China University of Geosciences, Beijing B.S.
Experience
09/2024-present, Professor, State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences (CASIA)
01/2023-08/2024, Associate Professor, State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences (CASIA)
11/2018-12/2022, Associate Professor, National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA)
01/2015-10/2018, Assistant Professor, National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA)
Publications
Papers
(2) Relation-Aware Pedestrian Attribute Recognition with Graph Convolutional Networks, AAAI, 2020, 通讯作者
(3) CR-Net: A Deep Classification-Regression Network for Multimodal Apparent Personality Analysis, International Journal of Computer Vision, 2020, 通讯作者
(4) WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild, IEEE Transactions on Multimedia, 2019, 通讯作者
(5) Task-oriented Feature-fused Network with Multi-variate Dataset for Joint Face Analysis, IEEE Transactions on Cybernetics, 2019, 通讯作者
(6) Region-based Context Enhanced Network for Robust Multiple Face Alignment, IEEE Transactions on Multimedia, 2019, 第 3 作者
(7) Deeply-learned Hybrid Representation for Facial Age Estimation, IJCAI, 2019, 通讯作者
(8) A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofing, CVPR, 2019, 通讯作者
(9) Efficient Group-n Encoding and Decoding for Facial Age Estimation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 通讯作者
(10) Articulated Motion and Deformable Objects, Pattern Recognition, 2019, 第 1 作者
(11) Multi-modal Face Anti-spoo?ng Attack Detection Challenge at CVPR2019, CVPR workshop, 2019, 通讯作者
(12) Attention based Pedestrian Attribute Analysis, IEEE Transactions on Image Processing, 2019, 通讯作者
(13) CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing, IEEE Transactions on Biometrics, Behavior, and Identity Science, 2019, 通讯作者
(14) RGB-D-based Human Motion Recognition with Deep Learning: A Survey, Computer Vision and Image Understanding, 2018, 通讯作者
(15) Cooperative Training of Deep Aggregation Networks for RGB-D Action Recognition, AAAI, 2018, 通讯作者
(16) Auxiliary Demographic Information Assisted Age Estimation with Cascaded Structure, IEEE Transactions on Cybernetics, 2018, 第 1 作者
(17) A Unified Framework for Multi-Modal Isolated Gesture Recognition, ACM Transactions on Multimedia Computing Communications and Applications, 2017, 通讯作者
(18) Explore efficient local features from RGB-D data for one-shot learning gesture recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 第 1 作者
(19) 3D SMoSIFT: Three-dimensional Sparse Motion Scale Invariant Feature Transform for Activity Recognition from RGB-D Videos, Journal of Electronic Imaging, 2014, 第 1 作者
(20) Dimensionality Reduction Using Graph-embedded Probability- based Semi-supervised Discriminant Analysis, Neurocomputing, 2014, 第 3 作者
(21) CSMMI: Class-Specific Maximization of Mutual Information for Action and Gesture Recognition, IEEE Transactions on Image Processing, 2014, 第 1 作者
(22) Graph-preserving shortest feature line segment for dimension- ality reduction, Neurocomputing, 2013, 第 3 作者
(23) One-shot Learning Gesture Recognition from RGB-D Data Using Bag of Features, Journal of Machine Learning Research, 2013, 第 1 作者
Patents
( 2 ) 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 1 作者, 专利号: ZL201610856231.1
( 3 ) 基于 RGB-D 数据构成的少量训练样本的手势识别方法, 发明, 2016, 第 1 作者, 专利号: ZL201310522370.7