Keynote Speeches
End-to-End Perspective on Distributed Multi-View Video Systems
Klara Nahrstedt,University of Illinois Urbana-Champaign
Wednesday, June 7th
Abstract: With the decrease in cost of 2D cameras and increase of their scale, the emergence of 3600 cameras and volumetric video content, and extensive deployment of VR/AR display devices, multi-view video content is becoming an integral part of our environments and with it the demand to address the underlying system and networking challenges. In this talk, we will discuss the end-to-end perspective of distributed multi-view video systems, ranging from multi-view video generation, navigation, streaming, to distribution and viewing, and their large bandwidth and low latency demands. Numerous potential system and network solutions are coming up to satisfy the end-to-end demands, including utilizing semantics in multi-camera resource management, designing view-based protocols, experimenting with viewport navigation and prediction techniques, and developing view/viewer management services to enable interactive viewing. Current results of distributed multi-view systems show promising new concepts and algorithms to address the bandwidth and latency challenges, and to enable user's interactive viewing with high quality of experience, but further challenges remain.
Biography: Klara Nahrstedt is the Grainger Chair in Engineering Professor in the Computer Science Department, and the Director of Coordinated Science Laboratory in the Grainger College of Engineering at the University of Illinois at Urbana-Champaign. Her research interests are directed toward tele-immersive systems, 360 video systems, end-to-end Quality of Service (QoS), resource management in large scale distributed systems and networks, and cyber-physical systems. She is the co-author of multimedia books "Multimedia: Computing, Communications and Applications", published by Prentice Hall, and "Multimedia Systems", published by Springer Verlag. She is the recipient of the IEEE Communication Society Leonard Abraham Award for Research Achievements, University Scholar, Humboldt Research Award, IEEE Computer Society Technical Achievement Award, ACM SIGMM Technical Achievement Award, TU Darmstadt Piloty Prize, the Grainger College of Engineering Drucker Award. She was the elected chair of the ACM Special Interest Group in Multimedia (SIGMM) from 2007-2013. She was the general co-chair and TPC co-chair of many international conferences including ACM Multimedia, IEEE International Conference on Pervasive Computing and Communications (Percom), IEEE/ACM Internet of Things Design and Implementation (IoTDI), IEEE SmartGridComm, IEEE Communications Society Conference on Sensor and Ad Hoc Communications and Networks (SECON), and others. Klara Nahrstedt received her Diploma in Mathematics from Humboldt University, Berlin, Germany in 1985. In 1995, she received her PhD from the University of Pennsylvania in the Department of Computer and Information Science. She is ACM Fellow, IEEE Fellow, AAAS Fellow, Member of the German National Academy of Sciences (Leopoldina Society), and Member of the US National Academy of Engineering.
AI for Compression and Compression for AI
Ihab Amer, AMD Fellow
Thursday, June 8th
Abstract: AI and compression are two technologies that exhibit an interesting mutually beneficial relationship. On one hand, compression technologies need to get smarter to deal with the continuously growing demand for low bandwidth ultra high-quality content delivery. On the other hand, AI systems are growing in size and compute requirements in a way that makes the application of data and model reduction techniques inevitable. This talk highlights the relationship between these two technologies, showing how each of them contributes to the advancements of the other. We overview examples where AI is applied to improve decision making at various stages of contemporary compression systems. We also peek at emerging initiatives to fully replace classical codecs with AI-based ones. Then, we overview compression-based techniques to reduce compute and memory requirements of DL training and inference engines before we touch on scenarios where compression techniques are used to improve other aspects of DL models beyond performance per watt. We conclude that such a special relationship between these two technologies needs to keep growing, leading to a continuous cycle of success.
Biography: Ihab Amer (Ph.D. 07, M.Sc. 03, and B.Sc. 00) received his Ph.D. degree in Electrical and Computer Engineering from the University of Calgary (U of C, Calgary, AB, Canada), his M.Sc. degree in Computer Science from the American University in Cairo (AUC, Cairo, Egypt), and his B.Sc. degree in Computers and Systems Engineering from Ain Shams University (Cairo, Egypt). He is a fellow at Advanced Micro Devices, Inc. (AMD, Markham, ON, Canada) and a member of the Software Technologies and Architecture Team, responsible for innovative future-looking solutions. He joined AMD as a Principal Member of Technical Staff, responsible for designing and defining strategies of Video CODEC solutions. Before that, he worked as an Assistant Professor at the Department of Digital Media Engineering and Technology of the German University in Cairo (GUC, Cairo, Egypt). He also worked as an overseas research consultant with the Advanced Technology Information Processing Systems (ATIPS) Labs at the U of C. He spent a research visit at the Multimedia Architectures Research Group of Ecole Polytechnique Fédérale de Lausanne (EPFL, Lausanne, VD, Switzerland), and he spent a visiting period at the DSP division of Xilinx Inc. (Austin, TX, USA). Dr. Amer has been a member of the ISO/IEC Moving Picture Experts Group (MPEG) Standard Committee and the CAC for the SCC (Subcommittees 6 and 29). He has participated in the organization of several academic and professional events such as the 20th meeting of ISO/IEC JTC 1, IWSOC, and ICMENS. He served as the local co-chair of IWSOC'06 and ICMENS'06 (Cairo, Egypt). He organized/chaired the ICIP'09 Special Session on Reconfigurable Video Coding (RVC) (Cairo, Egypt) as well as the RVC Special Session at the ECSI Conference on Design and Architectures for Signal and Image Processing (Edinburgh, UK). He delivered half-day tutorials at both ISCAS'16 (Montreal, Canada) and ICECS'15 (Cairo, Egypt). He is a holder of several prestigious awards and highly competitive scholarships. This includes the 2015 AMD Innovation Award, the Alberta Ingenuity Fund (AIF), the Informatics Circle of Research Excellence (iCORE), and the ISO/IEC award for the "special contribution" as a project editor in the international MPEG standard (MPEG-4 Part 9). He has over 40 contributions to MPEG standards, and he has authored/coauthored over 40 peer-reviewed conference and journal papers, out of which six of them received (or were nominated to) the best paper/poster award. He is a Senior Member of IEEE and he is licensed as a Professional Engineer in Ontario. He has numerous issued and pending patents. His core research interests include (but are not limited to) application-specific video compression, intelligent algorithms for video systems, and efficient architectures for emerging technologies.
Moderating the Metaverse
Yvette Wohn, New Jersey Institute of Technology
Thursday, June 8th
Abstract: Online harassment is a problem that we still have been unable to solve in the social media age of Web 2.0. As we move deeper into Web 3.0, which includes 3D virtual worlds, moderation moves beyond content to include behavioral components such as embodied interactions. How do we design these systems to be creative and generative while maintaining safety and equity? This talk will discuss the challenges and opportunities, both social and technical, in creating the next wave of networked multimedia systems.
Biography: Dr. Wohn (she/her) is an associate professor of Informatics at New Jersey Institute of Technology and director of the Social Interaction Lab. Her research is in the area of Human Computer Interaction (HCI) where she studies the characteristics and consequences of social interactions in online environments such as virtual worlds and social media. Her main projects examine 1) moderation, online harassment, and the creation/maintenance of online safe spaces and 2) social exchange in digital economies & digital patronage (creator-supporter dynamics). Her work on moderation is supported by the National Science Foundation and Mozilla Foundation.
Networked Immersive Media: For Human and For Machine
Jiangchuan Liu, Simon Fraser University
Saturday, June 10th
Abstract: Cyberspace has long had an ambitious goal --- connecting the world, understanding the world, and interacting with the world, both physically and virtually, for human beings and machines, anytime and anywhere. This remained a dream a decade ago. With the unprecedented development in the Information and Communication Technology (ICT) sector in the past decade, however, it is now solid and reachable to a great extent, if not all. In this talk, we will discuss our recent works on immersive media over the Internet and advanced mobile networks, from synergized neuro and traditional compression, to personalized distribution, and to multi-modal interaction. Besides human beings as consumers, we will further explore the new world when machines act as consumers, with a focus on mobile video analytics. We will also examine their applications in extreme environments as well as the opportunities and challenges from the latest advances in communication and computing infrastructures, including streaming over low earth orbit (LEO) satellite constellations, batteryless spatial acoustic sensing, and cross-region analytics.
Biography: Jiangchuan Liu is a Full Professor in the School of Computing Science, Simon Fraser University, British Columbia, Canada. He is a Fellow of The Canadian Academy of Engineering, an IEEE Fellow, and an NSERC E.W.R. Steacie Memorial Fellow. In the past he worked as an Assistant Professor at The Chinese University of Hong Kong, a research fellow at Microsoft Research Asia, and an EMC-Endowed Visiting Chair Professor of Tsinghua University. He received the BEng degree (cum laude) from Tsinghua University, Beijing, China, in 1999, and the PhD degree from The Hong Kong University of Science and Technology in 2003, both in computer science. He is a co-recipient of the inaugural Test of Time Paper Award of IEEE INFOCOM (2015), ACM SIGMM TOMCCAP Nicolas D. Georganas Best Paper Award (2013), ACM Multimedia Best Paper Award (2012), and IEEE MASS Best Paper Award (2021). His research interests include multimedia systems and networks, cloud and edge computing, social networking, online gaming, and Internet of things/RFID/backscatter. He has served on the editorial boards of IEEE/ACM Transactions on Networking, IEEE Transactions on Network Sciences and Engineering, IEEE Transactions on Big Data, IEEE Transactions on Multimedia, IEEE Communications Surveys and Tutorials, and IEEE Internet of Things Journal. He is a Steering Committee member of IEEE Transactions on Mobile Computing and Steering Committee Chair of IEEE/ACM IWQoS (2015-2017). He was TPC Co-Chair of IEEE INFOCOM'2021.