Title: “Discriminative Learning for Single‐Sample Face Recognition”
Date and time: Friday, 8 May 2015, 9:00-12:30
Room: M1
Presenters: Jiwen Lu and Weihong Deng

Tutorial Description: Single‐sample face recognition (SSFR) is an important and challenging problem in practical face recognition. Most existing face recognition methods usually require that there are multiple samples per person available for discriminative feature extraction in the training stage. In many real face recognition applications such as law enhancement, e‐passport, and ID card identification, however, this requirement does not hold as there is only one single sample per person enrolled or recorded in these systems. Hence, how to learn discriminative feature representations remains an important and challenging problem for SSFR.
In this tutorial, we will first review the state‐of‐the‐art SSFR techniques. Then, we will introduce some of our newly proposed SSFR methods two aspects: discriminative feature learning and discriminative classifier learning, which differ in learning discriminative descriptors and models for SSFR. Moreover, recent methods, such as deep metric learning and generic 3D model, are also tutored to address the occlusion and pose variations for unconstrained SSFR. Lastly, we will discuss some open problems to understand how to develop more advanced discriminative feature and classifier learning algorithms for single‐sample face recognition systems in the future. More details of this tutorial can be found at: www.whdeng.cn/FG15tutorial/index.html.

About the presenters:
Jiwen Lu is currently a Research Scientist at the Advanced Digital Sciences Center (ADSC), Singapore. His research interests include computer vision, pattern recognition, and machine learning. He has authored or co‐authored over 100 scientific papers in these areas, where more than 30 papers were published in the IEEE Transactions journals (PAMI/TIP/TCSVT/TIFS) and the top‐tier computer vision conferences (ICCV/CVPR/ECCV). He served as an Area Chair for the 2015 IEEE International Conference on Multimedia and Expo (ICME 2015) and the 2015 IAPR/IEEE International Conference on Biometrics (ICB 2015), and a Special Session Chair for 2015 IEEE Conference on Visual Communications and Image Processing (VCIP 2015). He organizes several workshops/competitions at some international conferences such as ICME2014, ACCV2014, IJCB2014 and FG2015. 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 2012 Best Student Paper Award from PREMIA of Singapore, the Top 10% Best Paper Award from MMSP 2014, respectively. Recently, he gives tutorials at CVPR 2015, ACCV 2014, ICME 2014 and IJCB 2014.

Weihong Deng received the B.E. degree in information engineering and the Ph.D. degree in signal and information processing from the Beijing University of Posts and Telecommunications (BUPT), Beijing, China, in 2004 and 2009, respectively. From Oct. 2007 to Dec. 2008, he was a postgraduate exchange student in the School of Information Technologies, University of Sydney, Australia, under the support of the China Scholarship Council. He is currently an associate professor in School of Information and Telecommunications Engineering, BUPT. His research interests include statistical pattern recognition and computer vision, with a particular emphasis in face recognition. He has published over 30 technical papers in international journals and conferences, including a technical comment on face recognition in SCIENCE magazine. He also serves as the reviewer for several international journals, such as IEEE TPAMI, IJCV, IEEE TIP, IEEE TIFS, PR, and IEEE TSMC‐B. His Dissertation titled “Highly accurate face recognition algorithms” was awarded the Outstanding Doctoral Dissertation by Beijing Municipal Commission of Education in 2011. He has been supported by the program for New Century Excellent Talents by the Ministry of Education of China since 2013.