中央研究院 資訊科學研究所

In this talk, I will describe how metric learning techniques are used for different face analysis tasks such as face recognition, face verification, facial age estimation, kinship verification, and head pose estimation. I will describe metric learning techniques from two aspects: single-metric learning and multi-metric learning, and show some of our recently proposed metric learning algorithms in different face analysis applications. Lastly, I will discuss some open problems to understand how to develop more advanced metric learning algorithms for human face analysis in the future.

Jiwen Lu is currently a Research Scientist at the Advanced Digital Sciences Center (ADSC), Singapore. His research interests include computer vision, pattern recognition, machine learning, and biometrics. He has published over 90 scientific papers in these areas, where 16 papers were in the IEEE Transactions journals (TPAMI/TIP/TCSVT/TIFS) and 9 papers were in top-tier computer vision conferences (ICCV/CVPR/ECCV). He serves as area chair for 2015 IEEE International Conference on Multimedia and Expo (ICME2015), and 2015 IAPR/IEEE International Conference on Biometrics (ICB2015), program committee for over 20 international conferences such as ICCV, CVPR, ECCV, ICPR, and reviewer for over 40 international journals such as TPAMI, TIP, TIFS, TCSVT, TMM, TNNLS, TSMC and TGRS. He organizes several workshops/competitions at some international conferences such as ICME2014, ACCV2014, IJCB2014 and FG2015. He was a recipient of the Best Student Paper Award from PREMIA of Singapore in 2012, the Top 10% Best Paper Award from MMSP 2014, and the Best Paper Award Nominations from ICME 2011 and ICME 2013, respectively. Recently, he gives/will give tutorials at many international conferences such as FG 2015, ACCV 2014, ICME 2014 and IJCB 2014.