Speaker: Prof. K. R. Rao, Dept. of Electrical Engineering, University of Texas at Arlington, USA
Title of Talk: High Efficiency Video Coding
Biography: K. R. Rao received the Ph.D degree in electrical engineering from The University of New Mexico, Albuquerque in 1966. He received B.S. E.E from the college of engineering, Guindy, India in 1952. Since 1966, he has been with the University of Texas at Arlington where he is currently a professor of electrical engineering. He, along with two other researchers, introduced the Discrete Cosine Transform (DCT) in 1975 which has since become very popular in digital signal processing. DCT, INTDCT, directional DCT and MDCT (modified DCT) have been adopted in several international video/image/audio coding standards such as JPEG/MPEG/H.26X series and also by SMPTE (VC-1)and by AVS China. He is the co-author of the books "Orthogonal Transforms for Digital Signal Processing" (Springer-Verlag, 1975), also recorded for the blind in Braille by the Royal National Institute for the blind. "Fast Transforms: Analyses and Applications"(Academic Press, 1982), “Discrete Cosine Transform-Algorithms, Advantages, Applications” (Academic Press, 1990). He has edited a benchmark volume, "Discrete Transforms and Their Applications" (Van Nostrand Reinhold, 1985). He has co-edited a benchmark volume, "Teleconferencing" (Van Nostrand Reinhold, 1985). He is co-author of the books, "Techniques and standards for Image/Video/Audio Coding" (Prentice Hall) 1996 “Packet video communications over ATM networks (Prentice Hall) 2000 and "Multimedia communication systems" (Prentice Hall) 2002. He has co-edited a handbook "The transform and data compression handbook," (CRC Press, 2001). Digital video image quality and perceptual coding, (with H.R. Wu)(Taylor and Francis 2006). Introduction to multimedia communications: applications, middleware, networking, (with Z.S. Bojkovic and D.A. Milovanovic), Wiley, (2006). He has also published a book, "Discrete cosine and sine transforms", with V. Britanak and P. Yip (Elsevier 2007). Wireless Multimedia Communications (publisher: Taylor and Francis) Nov. 2008. He has published extensively in refereed journals and has been a consultant to industry, research institutes, law firms and academia. He has reviewed 23 book manuscripts for book publishers. He is a Fellow of the IEEE. He is a member of the Academy of Distinguished Scholars, UTA.
Abstract: In the family of video coding standards, HEVC has the promise and potential to replace/supplement all the existing standards (MPEG and H.26x series including H.264/AVC). While the complexity of the HEVC encoder is several times that of the H.264/AVC, the decoder complexity is within the range of the latter. Researchers are exploring about reducing the HEVC encoder complexity . Kim et al have shown that motion estimation (ME) occupies 77-81% of HEVC encoder implementation. Hence the focus has been in reducing the ME complexity. Several researchers have implemented performance comparison of HEVC with other standards such as H.264/AVC , MPEG-4 Part 2 visual, H.262/PEG-2 Video , H.263, and VP9, THOR, DAALA and also with image coding standards such as JPEG, JPEG2000, JPEG-LS, JPEG-XT and JPEG-XR. Several tests have shown that HEVC provides improved compression efficiency up to 50% bit rate reduction for the same subjective video quality compared to H.264/AVC.
Besides addressing all current applications, HEVC is designed and developed to focus on two key issues: increased video resolution - up to 8kx4k – and increased use of parallel processing architecture. Brief description of the HEVC is provided. However for details and implementation, the reader is referred to the JCT-VC documents , overview papers , keynote speeches , tutorials , panel discussions , poster sessions , special issues , test models (TM/HM) , web/ftp site, open source software , software manuals, test sequences, anchor bit streams and the latest books on HEVC . Also researchers are exploring transcoding between HEVC and other standards such as MPEG-2 and H.264. Further extensions to HEVC are scalable video coding (SVC), 3D video/multiview video coding and range extensions which include screen content coding (SCC), bit depths larger than 10 bits and color sampling of 4:2:2 and 4:4:4. SCC in general refers to computer generated objects and screen shots from computer applications (both images and videos) and may require lossless coding. Some of these extensions have been finalized by the end of 2014 (time frame for SCC is late 2016). They also provide fertile ground for R & D. Iguchi et al have already developed a hardware encoder for super hi-vision (SHV) i.e., ultra HDTV at 7680x4320 pixel resolution. Also real-time hardware implementation of HEVC encoder for 1080p HD video has been done. NHK is planning SHV experimental broadcasting in 2016. A 249-Mpixel/s HEVC video decoder chip for 4k Ultra-HD applications has already been developed. Bross et al have shown that real time software decoding of 4K (3840x2160) video with HEVC is feasible on current desktop CPUs using four CPU cores. They also state that encoding 4K video in real time on the other hand is a challenge.
Speaker: Prof. Schahram Dustdar, The TU Wien, Austria
Title of Talk: TBA
Biography: Prof. Schahram Dustdar is Full Professor of Computer Science and head of The Distributed Systems Group at the TU Wien, Austria. From 2004-2010 he was also Honorary Professor of Information Systems at the Department of Computing Science at the University of Groningen (RuG), The Netherlands. From Dec 2016 until Jan 2017 he was a Visiting Professor at the University of Sevilla, Spain and from January until June 2017 he was a Visiting Professor at UC Berkeley, USA. He is an Associate Editor of IEEE Transactions on Services Computing, ACM Transactions on the Web, and ACM Transactions on Internet Technology and on the editorial board of IEEE Internet Computing and IEEE Computer. He is the Editor-in-Chief of Computing (Springer). Dustdar is recipient of the ACM Distinguished Scientist award (2009), the IBM Faculty Award (2012), an elected member of the Academia Europaea: The Academy of Europe, and an IEEE Fellow (2016). More information at: http://www.infosys.tuwien.ac.at/staff/sd/
Speaker: Prof. Erol Gelenbe, Imperial College and Polish Academy of Sciences (Inventor of G-Networks and the Random Neural Network)
Title of Talk: Deep Learning with Spiking Random Neural Networks
Biography: Erol Gelenbe is a Fellow of IEEE, ACM and IET (UK), and a Professor in the Department of Electrical and Electronic Engineering at Imperial College, London. He has introduced computer and network performance models based on diffusion approximations, and invented the Random Neural Network Model, as well as G-Networks which are analytically solvable queueing models that incorporate control functions such as work removal and load balancing. His other contributions include the concept and prototype for FLEXSIM, an object oriented discrete event simulation approach for flexible manufacturing systems, and other commercially successful projects such as the QNAP tool for the Performance Evaluation of Computer Systems and Networks. His innovative designs include the first voice-packet switch SYCOMORE, the first fibre optics random access network XANTHOS, and the first implemented Cognitive Packet Network and its adaptive routing protocol. He also designed and published the first optimal protocol for random access communications, and an optimum check-pointing scheme for databases. For his work, he received several prizes from France, the UK, Hungary and Turkey, including the 2010 IET Oliver Lodge Medal, the 2008 ACM SIGMETRICS Life-Time Achievement Award, and the 1996 Grand Prix France Telecom of the French Academy of Sciences. He was awarded Knight of the Legion of Honour and Officer of the Order of Merit of France, and Grand Officer of the Order of the Star and Commander of Merit of Italy. He is a Fellow of the French National Academy of Engineering, the Royal Academy of Sciences, Arts and Letters of Belgium, the Science Academies of Hungary and Poland, and the Science Academy of Turkey. He was awarded Honoris Causa doctorates from the Universities of Liege (Belgium), Roma II (Italy) and Bogazici (Turkey). He has graduated over 73 PhD students, and his recent papers appear in the Physical Review, the Communications of the ACM, and several IEEE and ACM Transactions.
Abstract: Networks in mammalian brains are mainly of a spiking nature so that the manner in which such networks learn are of great philosophical, scientific and engineering interest. Thus several years ago, we developed the first O(n^3) gradient descent learning algorithm for recurrent networks using the spiking and random behaviour of biological neuronal cells. In this presentation we will details how these dense structures can be exploited in deep learning and how they can achieve significantly better performance than standard models. The presentation will be illustrated with numerous practical examples.
Speaker: Ronald P. Luijten, Data Motion Architect, IBM Research - Zurich
Title of Talk: Objective, innovation and impact of the energy-efficient DOME MicroDataCenter
Biography: Ronald P. Luijten, senior IEEE member, is the initiator and senior technical project leader of the IBM DOME microDataCenter project. Ronald’s personal research interests are in datacenter architecture, design and performance (‘Data Motion in Data Centers’). He holds more than 25 issued patents, and has co-organized 7 IEEE conferences. Over the years (32), IBM has awarded Ronald with three outstanding technical achievement awards and a corporate patent award..
Abstract: The DOME MicroDataCenter technology, developed by IBM Zurich Research and ASTRON Netherlands Institute for Radio Astronomy, brings together the embedded and data-center computing technologies resulting in the densest general purpose computing capability with best energy-efficiency. My presentation will cover how this project went from an initial idea and obtaining funding to a small dedicated team building innovative hard and software. I will explain how we used first principles in physics to motivate our decisions, a few practical technical obstacles we needed to overcome and key lessons we learnt along the way. Our result, which we are currently bringing to market thru a startup company, addresses the needs of edge-computing for the Internet of Things, a opportunity that we did not foresee when we started the project 5 years ago. I will close with a technology roadmap..