Jiwen Lu Department of Automation Tsinghua University, China Biography Jiwen Lu received the B.Eng. degree in mechanical engineering and the M.Eng. degree in electrical engineering from the Xi'an University of Technology, Xi'an, China, and the Ph.D. degree in electrical engineering from the Nanyang Technological University, Singapore, in 2003, 2006, and 2011, respectively. He is currently an Associate Professor with the Department of Automation, Tsinghua University, China. His current research interests include computer vision, pattern recognition, and machine learning, where he authored/co-authored over 130 scientific papers in these areas. He serves/has served as an Associate Editor of Pattern Recognition Letters, Neurocomputing, the IEEE Access and the IEEE Biometrics Council Newsletters, a Guest Editor of Image and Vision Computing and Neurocomputing, and an elected member of the Information Forensics and Security Technical Committee of the IEEE Signal Processing Society. He is/was an Area Chair for WACV'16, ICB’16, ICME'15, and ICB'15, a Workshop Co-Chair for ACCV’2016, and a Special Session Co-Chair for VCIP'15. He has given tutorials at several international conferences including CVPR'15, FG'15, ACCV'14, ICME'14, and IJCB'14. He was a recipient of the First-Prize National Scholarship and the National Outstanding Student Award from the Ministry of Education of China in 2002 and 2003, the Best Student Paper Award from Pattern Recognition and Machine Intelligence Association of Singapore in 2012, the Top 10% Best Paper Award from IEEE International Workshop on Multimedia Signal Processing in 2014, and the National 1000 Young Talents Plan Program in 2015, respectively. He is senior member of the IEEE. Talk I: Feature Learning for Face Recognition Face recognition is a longstanding computer vision problem and a variety of methods have been proposed for face recognition over the past two decades. Face representation significantly affects the performance of a face recognition system because face images captured in real world environments are usually affected by many variations such as varying poses, expressions, illuminations, occlusions, resolutions, and backgrounds. In this talk, I will overview the trend of feature learning techniques and discuss how they are employed to boost face recognition performance. First, we briefly introduce the basic concept of feature learning, and show the key advantages and disadvantages of existing feature learning methods in different face recognition tasks. Second, we introduce some of our newly proposed feature learning methods from two aspects: holistic feature learning and local feature learning, which are developed to improve face recognition performance from two different viewpoints. Lastly, I will discuss some open problems in feature learning to show how to further develop more advanced feature learning algorithms for real-world face recognition in the future. Talk II: Metric Learning for Face Recognition In this talk, I will overview the trend of metric learning techniques and discuss how they advance various face recognition applications. This talk includes three parts. First, I will briefly introduce the basic concept of metric learning, and show how they are used to improve the performance of different face recognition tasks in previous work. Second, I will introduce several our newly proposed metric learning methods from two aspects: single-metric learning and multi-metric learning. For single-metric learning, our methods include cost-sensitive metric learning, sparse reconstruction metric learning, ordinal preserving metric learning, locality repulsed metric learning, and discriminative deep metric learning. For multi-metric learning, we will present discriminative multi-metric learning, multi-view neighbourhood repulsed metric learning, localized multi-kernel metric learning, and multi-manifold metric learning. Third, I will present how these proposed metric learning methods are used to improve different face analysis tasks including face identification, face verification, video-based face recognition, single-sample face recognition, facial age estimation, kinship verification, and head pose estimation. Lastly, I will discuss some open problems to understand how to develop more advanced metric learning algorithms for human face analysis in the future. |
Lecturers >