David Zhang graduated in Computer Science from Peking University. He received his MSc in 1982 and his PhD in 1985 in Computer Science from the Harbin Institute of Technology (HIT), respectively. From 1986 to 1988 he was a Postdoctoral Fellow at Tsinghua University and then an Associate Professor at the Academia Sinica, Beijing. In 1994 he received his second PhD in Electrical and Computer Engineering from the University of Waterloo, Ontario, Canada. He is a Chair Professor since 2005 and currently an Emeritus Professor at the Hong Kong Polytechnic University. He is Founder and Editor-in-Chief, International Journal of Image and Graphics (IJIG); Founder and Series Editor, Springer International Series on Biometrics (KISB); Organizer, the 1st International Conference on Biometrics Authentication (ICBA); Associate Editor of more than ten international journals including IEEE Transactions and so on. So far, he has published over 20 monographs, 400 international journal papers and 40 patents from USA/Japan/HK/China. According to Google Scholar, his papers have got over 49,000 citations and H-index is 99. He was listed as a Highly Cited Researcher in 2014, 2015, 2016 and 2017, respectively. Professor Zhang is a Croucher Senior Research Fellow, Distinguished Speaker of the IEEE Computer Society, and a Fellow of both IEEE and IAPR
Speech Title: Facial Multi-Characteristics and Applications
Abstract: What features could we extract from a face and how about their applications for each given feature? In fact, we could find multi-characteristics from a face, which may get two main kinds of features, e.g., original (or physiological) features and changed features during a lifetime. As a result, there will be some different applications, including?facial identification in original special features, beauty analysis in original common features, facial diagnosis by disease changed features, and expression recognition by affect changed features.?This presentation will define these different features extracted from a face and provide their typical applications. Experimental results of the performance under different application challenges have shown the superiority of these multi-characteristics.
Zhou Wang is a University Research Chair and Professor in the Department of Electrical and Computer Engineering, University of Waterloo, Canada. His research interests include image and video processing and coding; visual quality assessment and optimization; computational vision and pattern analysis; multimedia communications; and biomedical signal processing. He has more than 200 publications in these fields with over 40,000 citations (Google Scholar).
Dr. Wang is a Fellow of Canadian Academy of Engineering and a Fellow of IEEE. He is a recipient of 2017 Faculty of Engineering Research Excellence Award at University of Waterloo, 2016 IEEE Signal Processing Society Sustained Impact Paper Award, 2015 Primetime Engineering Emmy Award, 2014 NSERC E.W.R. Steacie Memorial Fellowship Award, 2013 IEEE Signal Processing Magazine Best Paper Award, and 2009 IEEE Signal Processing Society Best Paper Award. He serves as a Senior Area Editor of IEEE Transactions on Image Processing (2015-present), and an Associate Editor of IEEE Transactions on Circuits and Systems for Video Technology (2016-present). Previously, he served as a member of IEEE Multimedia Signal Processing Technical Committee (2013-2015), an Associate Editor of IEEE Transactions on Image Processing (2009-2014), Pattern Recognition (2006-present) and IEEE Signal Processing Letters (2006-2010), and a Guest Editor of IEEE Journal of Selected Topics in Signal Processing (2013-2014 and 2007-2009).
Speech Title: Video Quality-of-Experience: Towards a Unified End-to-End Solution
Abstract: Human kind has entered an era of experience. The research community and industry are striving to provide innovative technologies, products and services, aiming to enrich and enhance human experiences in consuming video content constantly streamed to millions of individuals¡¯ TVs, tablets, and smartphones. Since the human perceptual systems are the ultimate consumers of such content, video creation, distribution and presentation systems must be designed to optimize the perceptual quality-of-experience (QoE) of individual users. In practice, however, this is not remotely the case. In the past few decades, there has been an incredible growing interest in both academia and industry in developing objective QoE models that predict human perceptual QoE. In practice, however, the wide usage of such models has been largely hampered by a series of real-world challenges. Furthermore, a large body of applications require to use QoE models to guide the design and optimization of various algorithms and systems. Such design and optimization challenges encompass the greatest potentials of QoE research but have not been deeply exploited. In this talk, we will use visual communication as an example and show that how a unified end-to-end QoE measurement and optimization solution could revolutionize the field and change everyone¡¯s everyday viewing experiences.
Prof. Kot has been with the Nanyang Technological University (NTU), Singapore since 1991. He headed the Division of Information Engineering at the School of Electrical and Electronic Engineering (EEE) for eight years. The Division¡¯s focuses are on signal processing for image, video, speech and audio. He was the Vice Dean Research and Associate Chair (Research) for the School of EEE for three years, overseeing the research activities for the School with over 200 faculty members. He is currently Professor and the Associate Dean (Graduate Studies) for the College of Engineering (COE) and Director of ROSE Lab [Rapid(Rich) Object SEearch Lab) with Peking University, Tencent and Inspur]. He has published extensively with over 200 technical papers in the areas of signal processing for communication, biometrics recognition, data-hiding, authentication and image forensics for digital media. He has two USA and one Singapore patents granted.
Dr. Kot served as Associate Editor for the IEEE Transactions on Signal Processing from 2000 to 2003, IEEE Transactions on Multimedia from 2008 to now, IEEE Transactions on Circuits and Systems for Video Technology from 2000 to 2005; IEEE Transactions on Circuits and Systems Part II from 2004 to 2006; IEEE Transactions on Circuits and Systems Part I from 2005 to 2007, IEEE Transactions on Image Processing, the Signal Processing Magazine, IEEE Signal Processing Letters, and the Senior Editorial Board of IEEE Journal of Special Topics in Signal Processing. He also served as Guest Editor for the Special Issues for the IEEE Transactions on CSVT and JASP. He was a member of the IEEE Transactions on Multimedia Steering Committee and a member of the IEEE SPS Image and Multi-dimensional DSP and IEEE SPS Information, Forensics and Security Technical Committees. Currently, he is in, the Editorial Board member for the EURASIP Journal of Advanced Signal Processing, and the IEEE Transactions on Information Forensics and Security.
He is a member of the IEEE CAS Visual Signal Processing and Communication Technical Committees. He has served the IEEE in various capacities such as the General Co-Chair for the 2004 IEEE International Conference on Image Processing (ICIP) and area/track chairs for several IEEE flagship conferences. He also served as the IEEE Signal Processing Society Distinguished Lecturer Program Coordinator and the Chapters Chair for IEEE Signal Processing Chapters worldwide. He received the Best Teacher of The Year Award at NTU, the Microsoft MSRA Award and as a co-author for the ICPR2008 Best Biometrics Student Paper Award in Florida, USA, the IWDW2010 Best Paper Award in Seoul, Korea and the ISCAS2010 Finalist for the Best Student Paper Award in Paris, France, the IEEE WIFS Best Student Paper Silver Award, the IEEE ICCT 2011 Best Paper Award and the ICECC 2012 Best Paper Award. He was elected as the IEEE CAS Distinguished Lecturer in 2005. He is now a Vice President in the Signal Processing Society, an IEEE Signal Processing Society Distinguished Lecturer, a Fellow of the Academy of Engineering, Singapore, a Fellow of IEEE and a Fellow of IES.
Speech Title: Is Seeing Believing and Face Spoofing?
Abstract: With the fast proliferation of digital cameras and other image acquisition devices due to the advancement in digital photography technology, photos from the public may have good news values for making journalist reports. However, one big challenge is how to authenticate the photo contents from the public, which may come from unreliable sources. A large variety of forensics works have been proposed to address various forensic challenges based on different types of tell-tale signs. This talk introduces several techniques for: (1) Accurate detection of image demosaicing regularity as a general type of image forensics features. (2) Identification of various common image source models including digital still cameras, RAW conversion tools and the low-end mobile cameras; (3) Universal detection of a wide range of common image tampering. (4) Tampering detection for blur images. (5) EXIF file tampering or content manipulations, (6) Tempering detection with blur images, and (7) Prevention of the image recapturing threat in spoofing, especially in face spoofing. These techniques help expose common image forgeries, especially those easy-to-make forgeries, which can be hardly seen directly by human eyes. The common theme behind these forensics techniques is through statistical detection of some intrinsic image regularity or tampering anomalies.
Abstract: In the talk, Jimmy will update the ocular imaging research work in the past years. He will share his AI-based image processing work on various ocular imaging modalities on the following 4 areas: ocular disease screening, robot assisted eye micro-surgery, ocular biometrics, as well as ocular medical informatics using genome study. He will introduce the current issues, technologies and approaches in this inter-disciplinary research area.
Biography: Prof. Jimmy Liu Jiang joined Chinese Academy of Sciencesin March 2016 through the China¡°Thousand Talent Program¡±. He graduated from the University of Science and Technology of China with a computer engineering bachelor degree, and obtained his Master and Ph.D degrees from the National University of Singapore majoring in Computer Science.Jimmy is currently holding the position of an Honorary Professor in Dundee University and is an adjunct principle research scientist in the Singapore National Eye Research Institute. Jimmy has served many years in IEEE EMBS (Engineering in Medicine and Biology Society) society, and was the 2014 chairman of the IEEE EMBS society of Singapore.
Jimmy has spent 27 years in Singapore before 2016. Jimmy established the Intelligent Medical Imaging Program (iMED), which was once the largest ocular imaging research team in the world, in A*STAR (Agency for Science, Technology and Research) Singapore.
Ever since joining the Chinese Academy of Sciences, he put in much time and effort helping to establish a new institute focusing on biomedical Engineering in Ningbo with support from government and Chinese Academy of Sciences. In June 2016, he established an international joint lab ¡°Sino-US Eye-Brain joint research lab¡± with North Carolina University United States to conduct eye and brain diseases diagnosis research; in August 2016, he established a joint lab with Electronics University of China to conduct big medical image data analytics. In Feb 2017, he signed a MOU with Singapore Eye Research Institute to jointly conduct ocular imaging research, and in April 2017, he signed an agreement with Singapore National Health Group in Ningbo to jointly conduct medical technology research as well as explore translational and clinical research in China and Singapore. Recently, in May 2017, Jimmy established a new joint laboratory with world leading ophthalmological equipment manufacture TOPCON Inc. in China focusing on new areas such as advanced ocular medical equipment manufacturing and Artificial Intelligence based Chinese ¡°big¡± medical image and data research.
Abstract: Humans are making communication each other, not only verbally but also non-verbally. The non-verbal communication is not necessarily intentional. For example, when a person talks to another person, their attitude such as confident, joyful, fear or anxious is expressed unintentionally. These intentional or unintentional attitude is expressed as a persons voice quality, gaze, gesture or other behavior, which affects communication between the persons. From communication point of view, these phenomena are kinds of communication that affects verbal communication, thus we call these kinds of communication "meta-communication." The meta-communication is very important factor when establishing, keeping and finishing communication and most people do that unconsciously. Nowadays, speech recognition technology has been developed and spoken dialog systems are realized such as Siri or Alexa. However, these dialog systems lack ability of meta-communication, which prevents the systems behave like a human. In this talk, I explain the concept of meta-communication, and introduce several attempts to reproduce human-like meta-communication by a computer system.
Biography: Akinori Ito was born in Yamagata, Japan on 1963. He received B.E., M.E., and Ph.D. degrees from Tohoku University, Sendai, Japan, on 1986, 1988 and 1991, respectively. Since 1991, he has worked with Research Center for Information Sciences and Education Center for Information Processing, Tohoku University. He was with the Faculty of Engineering, Yamagata University, from 1995 to 2002. From 1998 to 1999, he worked with the College of Engineering, Boston University, MA, USA, as a Visiting Scholar. He is now a Professor of the Graduate School of Engineering, Tohoku University. He is engaged in speech signal processing, human machine communication, music signal processing and speech-based language learning system. He is a member of the Acoustical Society of Japan, the Information Processing Society of Japan, IEICE, and the IEEE. He was a vice-president of the Acoustical Society of Japan from 2013 to 2014, a chair of IEEE Signal Processing Society Sendai Chapter from 2013 to 2016, and the editor-in-chief of the Acoustical Science and Technology from 2015 to 2016.