Keynote Speakers of 2017
Keynote Speaker I
Prof. Xudong Jiang, Nanyang Technological University, Singapore
Feature Extraction and Dimensionality Reduction: Solving Over-Fitting in Pattern Recognition
Abstract: Feature extraction and dimensionality reduction are critical steps in pattern recognition system. We understand well about various traditional approaches in handcrafted feature extraction while the objectives and purposes of machine learning to extract effective features may not be so straightforward. It is thus not a surprise that approaches of the learning-based dimensionality reduction emerge in various research journals, many of which are in prestige journals. Many researchers and engineers find it difficult and even confused in choosing a proper approach from numerous diverse techniques due to a lack of thorough understanding of the roles of feature extraction and dimensionality reduction in the statistical inference and recognition. The different roles and effects of various dimensionality reduction techniques on facilitating a better detection and recognition have not been studied. Many fundamental yet critical issues are still outstanding or not thoroughly analyzed. This talk analyzes the fundamental problems of feature extraction and dimensionality reduction for automated data analysis. Based on this, the speech clarifies doubts, confusions and misunderstandings about roles of the learning-based dimensionality reduction. It aims at helping audience have an in-depth understanding and gain a clear picture of machine learning-based feature extraction. A total novel concept will be presented in this talk: “Removing misleading information” to replace the conventional “Extracting discriminative information” in machine learning-based data analysis.
Prof. Xudong Jiang received the B.Sc. and M.Sc.
degree from the University of Electronic Science and
Technology of China, and received the Ph.D. degree
from Helmut Schmidt University Hamburg, Germany.
From 1986 to 1993, he worked as Lecturer at UESTC
where he received two Science and Technology Awards
from the Ministry for Electronic Industry of China.
He was a recipient of the German Konrad-Adenauer
Foundation young scientist scholarship. From 1993 to
1997, he was with Helmut Schmidt University
Hamburg, Germany as scientific assistant. From 1998
to 2004, He worked with the Institute for Infocomm
Research, A*Star, Singapore, as Senior Research
Fellow, Lead Scientist and appointed as the Head of
Biometrics Laboratory where he developed an software
that achieved the fastest and the second most
accurate fingerprint verification in the
International Fingerprint Verification Competition
(FVC2000). He joined Nanyang Technological
University, Singapore as a faculty member in 2003
and served as the Director of the Centre for
Information Security from 2005 to 2011. Currently,
Dr Jiang is a tenured Association Professor in
Nanyang Technological University. Dr Jiang has
published over 120 research papers, including 20
papers in top IEEE journals: TPAMI, TIP, TSP and
SPM, which are well-cited on Web of Science. He is
also an inventor of 7 patents (3 US patents). Dr
Jiang is a senior member of IEEE, elected voting
member of IFS technical committee of IEEE Signal
Processing Society, Associate editor of IEEE Signal
Processing Letters and IET Biometrics. He has been
serving as General Chair, Technical Program
Committee Chair, Keynote Speaker and Session Chair
of multiple international conferences. His research
interest includes pattern recognition, computer
vision, machine learning, image analysis, signal
processing, machine learning and biometrics.
Keynote Speaker II
Prof. Julian FIERREZ, Biometric Recognition Group, Escuela Politecnica Superior, Universidad Autonoma de Madrid, Spain
Behavioral Biometrics with Application to the FinTech Sector
Abstract: Services are migrating from the physical to the digital domain in the information society. Examples of this conversion to the digital domain can be seen in: e-government, banking, education, health, commerce and leisure. In this context, identity authentication has become a fundamental need to ensure proper use and access to digital resources. Biometric technologies have emerged to fill the gap of traditional recognition technologies based on passwords or cards. The advantages of biometric systems are clear in terms of security and convenience of use, which has led these technologies to take on a leading role in the last years. The most popular biometric technologies (such as fingerprint, face or iris) are linked in general to access control applications or forensic science. These technologies typically require specific one-shot imaging sensors, reducing this way their universality and interoperability. Moreover, there is currently an increasing demand for remote authentication solutions that cannot be adequately met with the already mentioned biometric technologies, e.g., web-based authentication. Therefore, there is a need for new technologies better suited for remote authentication. In this talk we will overview recent advances in biometric authentication based on user behavior and actions while interacting with certain devices or applications (such as common tasks with a smartphone). We will focus in behavioral biometrics like handwriting, keystroking and swipe touch interaction, with a practical application to the FinTech sector.
Bio: Julian Fierrez received the M.Sc. and the Ph.D. degrees in telecommunications engineering from Universidad Politecnica de Madrid, Spain, in 2001 and 2006, respectively. Since 2002 he has been affiliated with the Biometric Recognition Group (ATVS), first at Universidad Politecnica de Madrid, and since 2004 at Universidad Autonoma de Madrid, where he is currently an Associate Professor. From 2007 to 2009 he was a visiting researcher at Michigan State University in USA under a Marie Curie fellowship. His research interests include general signal and image processing, pattern recognition, and biometrics, with emphasis on signature and fingerprint verification, multi-biometrics, biometric databases, system security, and forensic applications of biometrics. Dr. Fierrez is actively involved in multiple EU projects focused on biometrics (e.g. TABULA RASA and BEAT), has attracted notable impact for his research (more than 6,000 citations with h-index = 42 in Google Scholar), and is the recipient of a number of distinctions, including: Best Paper Awards at AVBPA 2003, ICB 2006, ICPR 2008, and ICB 2015; Best PhD Thesis Award in Computer Vision and Pattern Recognition in 2005-2007 by the IAPR Spanish liaison (AERFAI), EBF European Biometric Industry Award 2006, EURASIP Best PhD Award 2012, Medal in the Young Researcher Awards 2015 by the Spanish Royal Academy of Engineering, and the Miguel Catalan Award to the Best Researcher under 40 in the Community in Madrid in the general area of Science and Technology.
Plenary Speaker I
Prof. Masayuki Arai, Teikyo University, Japan
General Introduction of Our Recent Research
Abstract: We have been studying pattern recognition, natural language processing and information visualization. In this speech, I'd like to introduce our recent research. Fist of all, I'd like to talk about following pattern recognition systems we've developed lately: followable user interface to hand behavior, textbook page recognition for self-study in distance learning, and pedestrial detection. Second, I'd like to introduce followinf TCP/IP protocol visualization tools: visualization tool for understanding the control method of TCP packet arrival order, visualization tool for understanding the difference between TCP and UDP, TCP/IP application protocol visualization tool,and secure socket layer visualization tool.
Bio: Professor in the Graduate School of Sciences and Engineering at Teikyo University. He received his B.E. degree from Tokyo University of Science in 1981 and Dr. Eng. degree from Utsunomiya University in 1995. His research interests include pattern recognition, natural language processing, and information visualization. He is a member of the Information Processing Society of Japan and IEEE.
Plenary Speaker II
Assoc. Prof. Kin Hong Wong, The Chinese University of Hong Kong, Hong Kong
3-D Computer Vision and Applications
Abstract: In this seminar, I will talk about various 3-D pose estimation and structure from motion techniques in engineering applications. First, I will discuss the general approaches of feature based pose estimation and structure from motion. Then I will introduce the techniques of Kalman filtering and trifocal tensor for real time pose tracking. Issues of 3-D vision approaches for virtual reality, projector-camera systems and automatically driving will be elaborated. During the talk, I will also give video demonstrations of some interesting vision based systems we developed in recently years. Finally the opportunities and challenges of 3-D computer vison in the modern mobile era will be discussed.
Bio: Professor Wong Kin Hong is an Associate Professor of the Department of Computer Science and Engineering of the Chinese University of Hong Kong. He received a PhD from the Department of Engineering of the University of Cambridge. His major research interest is in 3-D computer vision especially in pose estimation, structure from motion and tracking. He has investigated and developed many useful techniques in computer vision such as the four-point pose estimation algorithm and Kalman-trifocal pose estimation methods which are useful in many application areas such as automatic driving and virtual reality. He is also interested in pattern recognition, embedded applications, and computer music.
Invited Speaker I
Assoc. Prof. Andrew B.J. Teoh, Yonsei University, South Korea
Advances in Analytic Manifold for Structured Pattern Recognition Problems
Abstract: Statistical learning on analytic manifolds (Lie Group, Riemannian, Stiefel and Grassmann Manifolds) is a new emerging and powerful means for solving structured pattern recognition problems. Analytic manifold learning is particular useful for many applications whereby input is framed by structured patterns such covariance matrices, linear dynamic models and linear subspaces. Analytic manifold learning can be reliable and accurate for inference, clustering, classification as well as prediction problems. This talk gives an overview of common analytic manifolds employed in various pattern recognition and computer vision problems. In particular, we will showcase a solution based on Grassmann manifold for multi-view gait recognition.
Bio: Andrew Beng Jin Teoh obtained his BEng (Electronic) in 1999
and Ph.D degree in 2003 from National University of Malaysia. He is
currently an associate professor in Electrical and Electronic
Engineering Department, College Engineering of Yonsei University,
His research, for which he has received funding, focuses on biometric applications and biometric security. His current research interests are Machine Learning and Information Security. He has published more than 250 international refereed journal papers, conference articles, edited several book chapters and edited book volume. He served and is serving as a guest editor of IEEE Signal Processing Magazine, associate editor of IEEE Biometrics Compendium and editor-in- chief of IEEE Biometrics Council Newsletter. He was a program co-chair of ICONIP 2014, area chair of ICPR 2016, track chair and TPC for several conferences related to computer vision, pattern recognition and biometrics.
Invited Speaker II
Prof. Jiande Sun, Shandong Normal University, China
Jiande Sun received the Ph.D. degree in communication and information system from Shandong University, Jinan, China, in 2005. He did the Postdoc work in both Peking University and Hisense Ltd from 2010 to 2013. He has been a visiting researcher in Technical University of Berlin, University of Konstanz, and Carnegie Mellon University. He is a full professor with the School of Information Science and Engineering, Shandong Normal University. He has published more than 60 journal and conference papers. He is the co-author of two books. He was authorized 17 patents. His research interests include multimedia content analysis, video hashing, gaze tracking, image/video watermarking, 2D to 3D conversion, and so on.
Invited Speaker III
Dr. Bo Jiang, Nanjing University of Posts and Telecommunications, China
Code Generation: Principles and Methods
Abstract: QR (Quick Response) code is a kind of two dimensional barcode that was first developed in automotive industry. Nowadays, QR code has been widely used in commercial applications like product promotion, mobile payment, product information management, etc. Traditional QR codes in accordance with the international standard are reliable and fast to decode, but are lack of aesthetic appearance to demonstrate visual information to customers. In recent years, various approaches have been proposed to make aesthetic QR code. In this talk, basic principles of QR code and its beautification strategies will be presented first. Then, recent advances in QR code beautification methods will be summarized, including the speaker's work. Finally, future work to improve the visual quality of aesthetic QR code will be shown.
Bio: He joined the Department of Digital Media Technology, School of Education Science and Technology, Nanjing University of Posts and Telecommunications as lecturer since Jul. 2014. Before that, he finished my Ph.D. study at State Key Lab of CAD & CG, Zhejiang University under the supervision of Prof. Xinguo Liu in Mar. 2014. He received my Bachelor's degree in School of Computer Science and Technology from Nanjing University of Posts and Telecommunications in 2006. In Sep. 2007, he became a Master student in State Key Lab of CAD & CG. Starting from Sep. 2008, he transfered to the Ph.D. program. During Nov. 2010 - Nov. 2011, he visited the Manufacturing System Research Lab, General Motors Research & Development at Warren, MI, USA under the supervision of Dr. Wuhua Yang (Sponsored by China Scholarship Concil and General Motors).
His research interests include digital geometry processing, shape analysis, computer vision based applications and virtual/augmented reality.
Invited Speaker IV
Dr. Juno Kim, University of New South Wales, Australia
Image properties for material appearance
Abstract: Surfaces reflect light that provides valuable information about their physical properties of 3D shape, colour, gloss and transparency. A major challenge for computational vision science is to understand how we perceive the material composition of objects from single images. Some researchers have proposed that image statistics can account for this experience, but evidence suggests that material perception can only be explained by theories that consider the structure of luminance variations in images. The presentation takes a revealing look at some of the geometric constraints that appear to account for our visual experience of objects and their material properties. The understanding to be gained has direct practical applications to the design of psychophysically-based artificial systems that can model human visual performance in a variety of real-world tasks (e.g., medical diagnosis and coordinating industrial processes using robotics).
Bio: Dr Kim is a Senior Research Fellow based in the School of Optometry and Vision Science at the University of New South Wales. Since completing his PhD in Psychology in 2005 (University of Sydney), he undertook postdoctoral studies on the perception of object form and motion at the University of Wollongong, the University of New South Wales, and the University of Sydney. In 2015, Dr Kim commenced an Australian Research Council (ARC) Future Fellowship awarded for his ongoing research on material appearance, which has collectively generated outputs featuring in Current Biology, i-Perception, Attention Perception & Psychophysics, Journal of Vision, and on the cover of Nature Neuroscience.