Home Latest News!!! CFP Final Submission Registration Album Invited Speakers Tutorials Workshops Sponsors Program Committee Venue


Invited Speakers

Home  /   Invited Speakers

Face and Soft Biometrics Recognition for Smart Cities Applications

Invited talk Josef Kittler University of Surrey, UK
Biometric technologies will play an important function in many smart cities security applications, including access control, verification of identity for secure transactions, and visual surveillance. Among different biometric modalities, face and soft biometrics are particularly attractive as they can easily be captured in an unobtrusive, noncontact fashion. We discuss the role of 3D face models in unconstrained face recognition in the context of deep learning approaches to face matching. We also consider the merit of soft biometrics for subject re-identification in CCTV footage in the scope of visual surveillance. We illustrate how linguistic description of suspects by witnesses can enhance the accuracy of re-identification. A new soft biometrics database collected in collaboration with Jiangnan University to enable studies of re-identification over time will be briefly described and future research discussed.

Self-awareness and Self-expression in Computing

Invited talk Xin Yao Southern University of Science and Technology, Shenzhen, China
CERCIA, School of Computer Science University of Birmingham, UK
This talk starts with a very briefly review of self-awareness in some psychology and cognitive science literature. Then working definitions of self-awareness and self-expression are given, in order to facilitate the application of such concepts in computing systems. The primary aim here is not to define the concepts comprehensively by considering all details in psychology and cognitive science, but to define concepts that can guide us in engineering relevant systems. To illustrate the ideas of self-awareness and self-expression and their potential use in real-world systems, a case study of designing an automated handover algorithm for fully decentralised smart camera networks will be presented. It is argued that in an open, complex, and fully decentralised system, static optimisation and learning are no longer the primary challenge. Such systems need to deal with a continuously changing environment and multiple conflicting goals, such as e.g. flexibility, performance, resource usage, security, reliability, rtc. The real challenge here is to dynamically manage trade-offs between goals at runtime.
Some technical details related to the talk can be found from the following:
L. Esterle, P. R. Lewis, B. Rinner and X. Yao, "Socio-Economic Vision Graph Generation and Handover in Distributed Smart Camera Networks," ACM Transactions on Sensor Networks, 10(2), Article No. 20, January 2014.
P. R. Lewis, L. Esterle, A. Chandra, B. Rinner, J. Torresen and X. Yao, "Static, Dynamic and Adaptive Heterogeneity in Distributed Smart Camera Networks," ACM Transactions on Autonomous and Adaptive Systems (TAAS), 10(2), Article No. 8, 30 pages, June 2015.
Xin Yao is a Chair Professor of Computer Science at the Southern University of Science and Technology, Shenzhen, China, and a part-time professor at the University of Birmingham, UK. His major research interests include evolutionary computation, ensemble learning and search-based software engineering. His work won the 2001 IEEE Donald G. Fink Prize Paper Award; 2010, 2016 and 2017 IEEE Transactions on Evolutionary Computation Outstanding Paper Awards; 2010 BT Gordon Radley Award for Best Author of Innovation (Finalist); 2011 IEEE Transactions on Neural Networks Outstanding Paper Award; and many other best paper awards. He received the prestigious Royal Society Wolfson Research Merit Award in 2012 and the IEEE Computational Intelligence Society Evolutionary Computation Pioneer Award in 2013. According to Thomson Reuters (ISI), he is one of the Highly Cited Reserachers in computer science. According to Google Scholar, his H-index is 84 and total citations >36,000, He was the President (2014-15) of IEEE Computational Intelligence Society.

Are we Building Smart Cities on Dumb City Information Systems?

Invited talk Mark Fox University of Toronto, Canada

The advent of Smart Cities has seen an explosion of research, development and deployment of applications that take advantage of the convergence of technologies such as Artificial Intelligence, Web-based information systems, mobile technologies, and the Cloud. But lurking underneath these applications is a city-wide information system whose architecture is rooted in the previous century. Just as cities have physical infrastructures that are over 100 years old, city information infrastructures are often legacy system over 20 years old. In this presentation a different view of city information systems will be presented. We explore the question of how smart city information systems should BEHAVE and not just how they are constructed.

Dr. Fox is a Distinguished Professor of Urban Systems Engineering, and Professor of Industrial Engineering and Computer Science at the University of Toronto. He received his BSc in Computer Science from the University of Toronto in 1975 and his PhD in Computer Science from Carnegie Mellon University in 1983. In 1979 he was a founding member of the CMU Robotics Institute as well as the founding Director of the Institute's Intelligent Systems Laboratory. He co-founded Carnegie Group Inc. in 1984, a software company that specialized in Artificial Intelligence-based systems. He was Associate Professor of Computer Science and Robotics at CMU from 1987 to 1991, In 1988 he was the founding Director of the Center for Integrated Manufacturing Decision Systems in CMU's Robotics Institute. In 1991, Dr. Fox returned to the University of Toronto where he was appointed the NSERC Research Chairholder in Enterprise Integration and Professor of Industrial Engineering and Computer Science. In 1993, Dr. Fox co-founded and was CEO of Novator Systems Ltd., a pioneer in E-Retail software and services. In 2014 he became the founding director of the Center for Social Services Engineering.
Dr. Fox pioneered the field of Constraint-Directed Scheduling within Artificial Intelligence and played a significant role in the development of Ontologies for modelling Enterprises. He was the designer of one of the first commercial industrial applications of expert systems: PDS/GENAID, a steam turbine and generator diagnostic system for Westinghouse, which was a recipient of the IR100 in 1985 and is still in commercial use at Siemens today. He was the co-creator of the Knowledge Representation SRL from which Knowledge CraftTM and ROCKTM, commercial knowledge engineering tools, were derived, and KBS from which several commercial knowledge based simulation tools were derived. His current research focuses on the ontologies, common sense reasoning and their application to Smart Cities.
Dr. Fox was elected a Fellow of Association for the Advancement of Artificial Intelligence in 1991, a Joint Fellow of the Canadian Institute for Advanced Research and PRECARN in 1992, and a Fellow of the Engineering Institute of Canada in 2009. Dr. Fox has published over 200 papers.


AI: Research and Applications

Invited talk Stan Z. Li Institute of Automation Chinese Academy of Sciences, China
In this talk, I will tell stories about my personal experiences with AI research and real applications.

\ Stan Z. Li (IEEE Fellow, the Founder of AuthenMetric Co. Ltd) received his B.Eng from Hunan University, China, M.Eng from National University of Defense Technology, China, and PhD from Surrey University, UK. He is currently a Professor at the National Laboratory of Pattern Recognition and the Director of the Center for Biometrics and Security Research (CBSR), Institute of Automation (CASIA), and the Director of the Center for Visual Internet of Things Research (VIOT), Chinese Academy of Sciences. He worked at Microsoft Research Asia as a researcher from 2000 to 2004. Prior to that, he was an associate professor at Nanyang Technological University, Singapore. He was elevated to IEEE Fellow for his contributions to the fields of face recognition, pattern recognition and computer vision.
His research interest includes pattern recognition and machine learning, image and vision processing, face recognition, biometrics, and intelligent video surveillance. He has published over 400 papers in international journals and conferences, and authored and edited 8 books among which "Markov Random Field Models in Image Analysis" (Springer, 1st edition 1995, 2nd edition 2001, 3rd edition 2009) has been cited more than 3000 times (by Google Scholar). Other works include Handbook of Face Recognition (Springer, 1st edition 2005, 2nd edition 2011) and Encyclopedia of Biometrics (Springer Reference Work, 2010). He served as an associate editor of IEEE Transactions on Pattern Analysis and Machine Intelligence, and a co-chair of International Conference on Biometrics (2007,2009,2013,2014,2015,2016) and has been involved in organizing other international conferences and workshops in the fields of his research interest.
Stan Z. Li is an expert in computer vision, face recognition, biometrics and intelligent video surveillance. The EyeCU face recognition system he developed at Microsoft Research Asia was demonstrated by Bill Gate on a CNN interview. He has been leading several national and international projects in biometrics and intelligent video surveillance. The AuthenMetric face recognition system and intelligent video surveillance system have been deployed in several national projects, including Beijing 2008 Olympic Games, Shanghai 2010 World Expo, and immigration control at China borders. He is a co-chair of SAC/TC100/SC2 for biometrics standardization in China and delivered a plenary speech on Biometrics in China at ISO/IEC JTC1/SC37 on behalf of the China National Body.


Title: Integrating Weather Information for Connected Vehicles: A Big Data Application

Invited talk Sue Ellen Haupt National Center for Atmospheric Research, USA

Operating modern surface transportation systems is becoming increasingly automated. One aspect necessary for successful operation is real-time and forecasted weather information. Providing such information requires a system that is capable of blending large amounts of observational and model data that arrives quickly, in disparate formats and times, and blends and optimizes their use via machine learning algorithms. Quality control of the data is essential. Historical data is required to train the machine learning models. This paper reports on the Pikalert® system that brings together weather information and real-time data to provide crucial real-time information to enhance the safety of surface transportation systems.
This paper describes the Pikalert® systems built by the National Center for Atmospheric Research (NCAR) and how it address this Big Data challenge. The Pikalert systems are designed to be functional prototypes to address needs of the road weather community and to fulfill the following goals:
• Pikalert Vehicle Data Translator - VDT: Collect, quality check, and aggregate mobile data along with ancillary weather observations. The additional Road Weather Hazard (RWH) module was designed to take output from the VDT and produce hazard assessments of precipitation, road conditions, and visibility along the configured road segments.
• Enhanced Maintenance Decision Support System - EMDSS: The EMDSS provides an assessment and forecast along road segments of road weather conditions as well as treatment recommendations (where/when to plow and/or apply chemical) for maintenance supervisors.
• Motorist Advisory Warning System - MAW: Provide road weather assessments and forecasts along configured road segments for the traveling public to aid in decision making processes about when/where/if to travel during adverse weather.
This Pikalert system assesses road conditions, including determining road hazard conditions for each road segment that may include a precipitation type, a pavement condition, and a visibility level. This talk lays out the needs and issues for application of weather forecasting to surface transportation and its application in the Pikalert system as a way to enhance transportation in smart cities of the future.

Dr. Sue Ellen Haupt is a Senior Scientist and Director of the Weather Systems and Assessment Program with the Research Applications Laboratory of the National Center for Atmospheric Research. She also serves as Director of Education for the World Energy and Meteorology Council, Adjunct Professor of Meteorology at The Pennsylvania State University, and a Councilor for the American Meteorological Society. She earned her Ph.D. in Atmospheric Science from the University of Michigan (1988), M.S. in Mechanical Engineering from Worcester Polytechnic Institute (1984), M.S. in Engineering Management from Western New England College (1982), B.S. in Meteorology from Penn State (1978), and did a postdoctoral fellowship with the Advanced Study Program of NCAR. She has also been on the faculty of the University of Colorado/Boulder; the U.S. Air Force Academy (visiting); University of Nevada, Reno; and Utah State University and previously worked for the New England Electric System and GCA Corporation. She is an expert in meteorology applied to renewable energy, boundary layer meteorology, large scale atmospheric dynamics, dynamical systems, numerical methods, artificial intelligence methods, and computational fluid dynamics. Dr. Haupt has authored and edited several books and published numerous journal articles on these topics.