Keynote Speakers


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.

Talk description: 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.

Books on HEVC:

  1. Book1. V. Sze, M. Budagavi and G.J. Sullivan (Editors), “High efficiency video coding: Algorithms and architectures”, Springer 2014.
  2. Book2. M. Wien, “High Efficiency Video Coding: Coding Tools and Specification”, Springer, 2014. 
  3. Book3. I.E. Richardson, “Coding video: A practical guide to HEVC and beyond”, Wiley, 2017.
  4. Book4 K.R. Rao, J.J. Hwang and D.N. Kim, “Video coding standards – MPEG-4 Part10, HEVC, VP6, DIRAC and VC-1”, Springer, 2014. Translated into Spanish by Dr. Carlos Pantsios M, Professor Titular/Telecommunicaciones, USB/UCA/UCV, Dept. of Electronica & Circuits, Simon Bolivar University, Caracas, Venejuela. Also being published in Chinese by China Machine press – approved by Springer.
  5. Book5. S. Wan and F. Yang, “New efficient video coding – H.265/HEVC – Principle, standard and application”, in Chinese, Publishing house of electronic industry, http://www.phei.com.cn, 2014.
  6. Book6. S. Okubo (Editor-in-Chief), H.265/HEVC Textbook”, in Japanese, Impress, Japan, 2013.

Speaker: Dr. Swagatam Das, Indian Statistical Institute, Kolkata, India

Title of Talk: Non-convex and Multi-modal Optimization with Differential Evolution: Foundations, Perspectives and Applications to Signal Processing

Biography: Swagatam Das is currently serving as an associate professor at the Electronics and Communication Sciences Unit of the Indian Statistical Institute, Kolkata, India. His research interests include evolutionary computing, pattern recognition, multi-agent systems, and wireless communication. Dr. Das has published one research monograph, one edited volume, and more than 250 research articles in peer-reviewed journals and international conferences. He is the founding co-editor-in-chief of Swarm and Evolutionary Computation, an international journal from Elsevier. He has also served as or is serving as the associate editors of the IEEE Trans. on Systems, Man, and Cybernetics: Systems, IEEE Computational Intelligence Magazine, IEEE Access, Pattern Recognition (Elsevier), Neurocomputing (Elsevier), Engineering Applications of Artificial Intelligence (Elsevier), and Information Sciences (Elsevier). He is an editorial board member of Progress in Artificial Intelligence (Springer), PeerJ Computer Science, International Journal of Artificial Intelligence and Soft Computing, and International Journal of Adaptive and Autonomous Communication Systems. Dr. Das has 12000+ Google Scholar citations and an H-index of 54 till date. He has been associated with the international program committees and organizing committees of several regular international conferences including IEEE CEC, IEEE SSCI, SEAL, GECCO, and SEMCCO. He has acted as guest editors for special issues in journals like IEEE Transactions on Evolutionary Computation and IEEE Transactions on SMC, Part C. He is the recipient of the 2012 Young Engineer Award from the Indian National Academy of Engineering (INAE).
He is also the recipient of the 2015 Thomson Reuters Research Excellence India Citation Award as the highest cited researcher from India in Engineering and Computer Science category between 2010 to 2014.

Talk description: Differential Evolution (DE) is arguably one of the most powerful population-based optimization algorithms of current interest for the continuous parameter spaces. DE operates through similar computational steps as employed by a standard Evolutionary Algorithm (EA). However, unlike traditional EAs, the DE variants perturb the current-generation population members with the scaled differences of distinct population members. Therefore, no separate probability distribution has to be used for generating the offspring. Since its inception in 1995, DE has drawn the attention of many researchers all over the world resulting in a lot of variants of the basic algorithm with improved performance. This talk will begin with a brief but comprehensive overview of the basic concepts related to DE, its algorithmic components and control parameters. It will subsequently discuss some of the significant algorithmic variants of DE for bound constrained single-objective optimization. The talk will finally discuss a few interesting applications of DE to signal processing and highlight a few open research problems.

Speaker: Dr. Rajesh M. Hegde, Department of Electrical Engineering, IIT Kanpur, India

Title of Talk: Surrounded by Sound : 3D Audio Signal Processing

Biography: Rajesh M. Hegde is a Professor with the Department of Electrical Engineering at IIT Kanpur. He heads the Multimedia Information Processing Systems Lab and Wireless Sensor Networks Lab at IIT Kanpur. He was also a P. K. Kelkar Research Fellow in the same department from 2009-2012. He holds a Ph.D in Computer Science and Engineering from IIT Madras . His current areas of research interest include multi-media signal processing, multi-microphone speech processing, spatial audio processing, pervasive multimedia computing, ICT for socially relevant applications in the Indian context, and applications of signal processing in wireless networks with specific focus on emergency response and transportation applications. He has also worked on NSF funded projects on ICT and mobile applications at the University of California San Diego, USA, where he was a researcher and lecturer in the Department of Electrical and Computer Engineering between 2005–2008. He has successfully completed several research and development projects both for Government and Industry. He has developed and transferred socially relevant multimedia technologies especially developed for the cell phone to the Industry including BSNL. He was also a member of the National working group of ITU-T (NWG-16) on developing multimedia applications. He has published extensively in reputed journals and served on the program committee of several reputed International conferences. Additional biographic information can be found at the URL: http://home.iitk.ac.in/~rhegde

Talk description: Story Telling was revolutionized for the first time by a "sound film" in 1927, called the "The Jazz Singer". Introduction of sound on moving pictures was exciting since it added a new dimension at that point in time. On to 2017, and we have a new disruptive technique called 3D spatial audio that is taking people into a new world of virtual reality. This technique can bring flat and dumb objects to life by making them talk and lets you perceive both the location and depth of the sounds they emit. In this talk, the exciting topic of 3D spatial audio processing will be addressed. Spatial audio processing broadly encompasses the capture of spatial sound using microphone arrays and their subsequent rendering using loudspeaker arrays. Binaural 3D sound rendering is also a very popular technique where spatial sound is rendered via headphones and has applications in virtual reality (VR) and Augmented Reality (AR). This talk will give a flavor of both Binaural and Loudspeaker array based 3D spatial audio processing and synthesis to the audience. Modeling of Head related transfer function (HRTF) for 3D binaural audio synthesis and its applications to VR will be discussed. Loudspeaker array based spatial audio techniques like Stereophony, Dolby, 8.1 and 10.1 surround sound will also be described. State of the art techniques like DiRAC and Higher order Ambisonics for 3D audio generation will be presented. The talk will conclude with a brief discussion on the exciting future of 3D audio.

Speaker: Dr. Bartosz Krawczyk, Department of Computer Science, Virginia Commonwealth University, Richmond VA, USA

Title of Talk: One-Class Classification: a tour through learning in the absence of counterexamples

Biography Bartosz Krawczyk is an assistant professor in the Department of Computer Science, Virginia Commonwealth University, Richmond VA, USA, where he heads the Machine Learning and Stream Mining Lab. His research is focused on machine learning, data streams, ensemble learning, class imbalance, one-class classification, computer vision, and interdisciplinary applications of these methods. He has authored 35+ international journal papers and 80+ contributions to conferences. Dr Krawczyk was awarded with prestigious awards for his scientific achievements, including IEEE Richard E. Merwin Scholarship, IEEE Outstanding Leadership, START award from Foundation for Polish Science (twice), scholarship for excellent research achievements from Polish Minister of Science and Higher Education (twice), Czeslaw Rodkiewicz Foundation award for merging technical and medical sciences, and Hugo Steinhaus award for achievements in computer science among others. He served as a Guest Editor in four journal special issues (including Information Fusion and Neurocomputing) and as a chair of ten special session and workshops (organized at such conferences as ECML-PKDD or ICCS). He is a member of Program Committee for over 40 international conferences and a reviewer for 30 journals.

Talk description: The objective of one-class classification is to train a classifier considering only examples from a target class, whereas examples from the other class (or classes) are left aside (they may be insufficient for a proper representation or too difficult to gather). This allows to create a data description that captures the properties of the given class in order to dichotomize between its representatives and anything else. Once the classifier is learned, new examples are classified as either target instances or outliers. Important aspect of one-class classification is the fact that no a priori knowledge about the nature of outliers is needed, therefore making it a useful tool for cases where gathering counterexamples is costly, time-consuming, or even impossible, as well as for open-set recognition scenarios (e.g., in computer vision), where potential non-target instances are too numerous. This talk will offer an introduction to one-class classification, describing basic concepts and popular algorithms. Then special attention will be given to recent developments in this area, especially considering usage of the ensemble learning paradigm. Additionally, other areas of applicability of one-class classifiers will be discussed, including data stream mining, imbalanced learning and multi-class decomposition. Finally, the talk will provide a discussion and suggestions concerning lines of future research in this field.