|
|
|
ProgramInstructions to presenters 1. The authors have to prepare video presentations of their papers. These have to be videos of slides with narration. Displaying a talking head of the presenter is a possible option but it has to be done so that there will be a clear view of the slides. The videos have to be
2. 10 days before the conference, the authors have to upload their presentation videos to YouTube or, if YouTube is not available for them, to other streaming servers of their choice. The URL links to the video presentations have to be emailed to Alexei Sourin assourin@ntu.edu.sg for verification. After checking 3. One week before the conference, the conference program with URL links to the videos with the paper presentations will be published on the conference web page and advertised through Facebook and other information channels. Every visitor to the conference web page will be able to watch the video presentations. The conference delegates are expected to watch all the presentations in advance to be able to discuss the papers during the 3 conference days. The conference web page will remain available after the conference as well. 4. 3 days before the conference, all the authors and IPC members will received emails with the instructions how to join the Zoom webinar during the conference days. In each paper session, the presenting authors of each paper (full, short, poster) will be given 15 min per full and 10 min per short and poster paper to make a quick ~3 min presentation (live online with their screen shared) summarising the paper which will be immediately followed by Q&A. The delegates attending the conference will be able to ask questions live or send a chat message to the presenter, participate in discussions and share their screens if needed. The sessions will be automatically video recorded and the videos will be later shared with the participants. The videos can be downloaded. The papers will compete for the best paper awards in all paper categories which will be based on paper research merits, presentations and discussions. We will keep open break out rooms for delegates conversations. We will make a nice group photo collected from the participants photos on one page.
Keynote speakers Keynote Speaker 1 Pr. Rae Earnshaw (Department of Computer Sicence, University of Bradford, UK)
Abstract: Where do new ideas come from and how are they generated? Which of these ideas will be potentially useful immediately, and which will be more ‘blue sky’? For the latter, their significance may not be known for a number of years, perhaps even generations. The progress of computing and digital media is a relevant and useful case study in this respect. Which visions of the future in the early days of computing have stood the test of time, and which have vanished without trace? Can this be used as guide for current and future areas of research and development? If one Internet year is equivalent to seven calendar years, are virtual worlds being utilized as an effective accelerator for these new ideas and their implementation and evaluation? The nature of digital media and its constituent parts such as electronic devices, sensors, images, audio, games, web pages, social media, e-books, and Internet of Things, provides a diverse environment which can be viewed as a testbed for current and future ideas. Individual disciplines utilise virtual worlds in different ways. As collaboration is often involved in such research environments, does the technology make these collaborations effective? Have the limits of disciplinary approaches been reached? The importance of interdisciplinary collaborations for the future is proposed and evaluated. The current enablers for progressing interdisciplinary collaborations are presented. The possibility for a new Renaissance between technology and the arts is discussed. Biography: Rae Earnshaw is full Professor of Electronic Imaging at the University of Bradford since 1995 (now Emeritus). He gained his PhD at the University of Leeds and is a chartered engineer and chartered information technology professional. He was Dean of the School of Informatics (1999-2007) and Pro Vice-Chancellor (Strategic Systems Development) (2004-09). He has been a Visiting Professor at Illinois Institute of Technology, George Washington University, USA, and Northwestern Polytechnical University, China. He is a member of ACM, IEEE, CGS, and a Fellow of the British Computer Society and the Institute of Physics. He has authored and edited 43 books on computer graphics, visualization, multimedia, design, and virtual reality, and published over 200 papers in these areas. Book publishers include: Addison Wesley, Springer, Academic Press, Cambridge University Press, IEEE Computer Society Press, and John Wiley & Sons Inc. He is on a number of Editorial Boards of international journals and is a Top Management Programme Fellow of the Leadership Foundation. In his role as Pro Vice-Chancellor, he led a broad range of 60 linked projects over 5 years which developed the University’s electronic information and communications capability and infrastructure. Although playing a significant role in academic leadership and management over the past 15 years, he has maintained his research and publication record and has been included in all the UK RAEs/REFs since 1996. His current objectives are to further develop his research and development in the areas of digital media, HCI, mobile learning, digital convergence, computer graphics, visualization, multimedia, and related areas. He is a member of the Centre for Visual Computing at the University of Bradford which performs world-class research and development in the area of visual image data processing. 7 book publications have been produced in Data Science, Visual Computing, Art, Design, Creative Industries, and Digital Media in the period from 2015 to the present. https://www.bradford.ac.uk/staff/raearnshaw
Keynote Speaker 2 Dr. Matthias Wölfel (Karlsruhe University of Applied Sciences, Germany)
Abstract: The use of virtual worlds for learning purposes has been studied since the 1990s. Especially due to technological advancements, low-cost access, and simple development tools, learning in immersive, virtual worlds has experienced a new upswing in recent years. These new devices bridge the gap between the digital and the analog world and thus open up numerous possibilities in media-supported education and training. While most of the current mixed reality learning applications try to copy reality and have shown to be useful to learning they lack the opportunity to use the full potential of the digital. An understanding has to be developed where real and virtual worlds differ with respect to technology-related, conceptual, and didactic differences. While the former can be assumed to be reduced by technological progress conceptual and didactic concepts for learning in mixed realities have to be developed. This talk will present an overview of current developments in this direction. Biography: Matthias Wölfel is a Professor for Intuitive and Perceptive User Interfaces at Karlsruhe University of Applied Sciences, Germany, and associated with the Faculty of Business, Economics and Social Sciences at University of Hohenheim. His research interests include interaction design, human-computer and human-computer-human interaction, artificial intelligence, augmented and virtual reality, as well as digital culture. Dr. Wölfel was recognized in 2017 as one of the best professors in Germany by UNICUM.
Keynote Speaker 3 Pr. Hassan Ugail (Department of Media, Design and Technology, University of Bradford, UK)
Abstract: Computer assisted face recognition, face analysis, age/gender perception and age progression/regression as well as emotion analysis are some of the prominent areas of research in computer vision, pattern recognition and artificial intelligence. The findings that come out of such research have diverse application areas including biometrics, surveillance, human/computer interaction, communication, entertainment, commerce, education and healthcare. Notably, rapid progress, over the years, has been achieved in this area - thanks to the recent advances in machine learning techniques and the accessibility of large experimental datasets. The talk will focus on the recent developments in computational techniques for human face analysis, especially in the area of face recognition and emotion analysis. The talk will attempt to highlight some of the key challenges in this area. The talk will also uncover some of the open problems and discuss areas where advances are needed to push the boundaries of the present state-of-the-art. Biography: Professor Hassan Ugail is the director of the Centre for Visual Computing at the University of Bradford in the UK. He is a mathematician and a renowned computer scientist in the area of visual computing and artificial intelligence (AI). He is an advocate of AI for helping to tackle real world issues in the areas of digital health, innovative engineering and sustainable societies in general. More specifically, he works in the field of human biometrics, especially the development of cutting edge AI solutions for biometric face recognition, emotion analysis and generation aspects of the computational face. A more detailed biography of Professor Ugail is available at, https://en.wikipedia.org/wiki/Hassan_Ugail
Keynote Speaker 4 Pr. Arun Ross (Department of Computer Science and Engineering, Michigan State University, USA)
Abstract: Biometrics is the science of recognizing individuals based on their physical and behavioral attributes such as fingerprints, face, iris, voice and gait. The past decade has witnessed tremendous progress in this field, including the deployment of biometric solutions in diverse applications such as border security, national ID cards, healthcare, access control, and smartphones. Despite these advancements, biometric systems have to contend with a number of challenges related to data quality, presentation attacks, and personal privacy. For example, a biometric system is vulnerable to “spoof attacks” where an adversary imitates the biometric trait (e.g., fingerprint) of another person. Further, issues related to “information leakage”, where the biometric data of an individual is processed to extract additional information (such as age, gender, race, etc.) beyond what was expressed at the time of data collection, can undermine personal privacy. This talk will highlight some of the recent progress made in the field of biometrics; present our lab’s work on presentation attack detection and privacy impartation to biometric data; and discuss some of the challenges that have to be solved in order to promote the widespread use of this technology. Biography: Arun Ross is a Professor in the Department of Computer Science and Engineering at Michigan State University, and is the Director of the Integrated Pattern Recognition and Biometrics (iPRoBe) Lab. He also serves as the Site Director of the NSF Center for Identification Technology Research (CITeR). Ross conducts research on the topic of biometrics, privacy, computer vision and pattern recognition. He is a recipient of the JK Aggarwal Prize and the Young Biometrics Investigator Award from the International Association of Pattern Recognition for his contributions to the field of Pattern Recognition and Biometrics. He was designated a Kavli Fellow by the US National Academy of Sciences by virtue of his presentation at the 2006 Kavli Frontiers of Science Symposia. Ross was an invited panelist at a counter-terrorism event organized by the United Nations Counter-Terrorism Committee (CTC) at the UN Headquarters in 2013. He has advocated for the responsible use of biometrics in multiple forums including the NATO Advanced Research Workshop on Identity and Security in Switzerland in 2018. He is a recipient of the NSF CAREER Award, the 2005 Biennial Pattern Recognition Journal Best Paper Award and the Five Year Highly Cited BTAS 2009 Paper Award. Ross is the co-author of the monograph “Handbook of Multibiometrics” and the textbook “Introduction to Biometrics”. (http://iprobe.cse.msu.edu/) |
