ICME2012 Tutorials

Tutorial Titles:

                                                                                                                                       

Title: "Multimedia Tagging: Past, Present and Future"

The tags have proved to be a very crucial mechanism to facilitate the effective sharing and organization of large scale of multimedia information. As a result, technical developments on intelligent multimedia tagging have attracted a substantial amount of efforts involving experts from information retrieval, multimedia computing and articial intelligence (particularly computer vision). The truly interdisciplinary research has resulted in many algorithmic and methodological developments. Meanwhile, many commercial web systems (e.g., Youtube, Last.fm, Facebook and Flickr) have successfully introduced a variety of toolkits to assist different users in discovering and exploring media content using tags.

Brief Biography:
Jialie Shen: Dr. Jialie Shen is an Assistant Professor in Information Systems and Lee Foundation Fellow, School of Information Systems, Singapore Management University, Singapore. He received his PhD in Computer Science from the University of New South Wales (UNSW), Australia in the area of large-scale media retrieval and database access methods. Dr. Shen’s main research interests include information retrieval, economic-aware media analysis, and statistical machine learning. His recent work has been published or is forthcoming in leading journals and international conferences including ACM SIGIR, ACM Multimedia, ACM SIGMOD, CVPR, ICDE, WWW, IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), IEEE Transactions on Multimedia (IEEE TMM), ACM Multimedia Systems Journal, ACM Transactions on Internet Technology (ACM TOIT) and ACM Transactions on Information Systems (ACM TOIS).

Meng Wang: Dr. Meng Wang is currently a research staff member in the National University of Singapore. Previously he worked as an associate researcher in Microsoft Research Asia and a research scientist in a start up in the Bay area. Dr. Wang's research interests include multimedia content analysis, tagging, search, and large-scale computing. Dr. Wang has authored about 80 technical papers in these areas. He is an associate editor of Information Sciences, an associate editor of Neorocomputing, and a guest editor of the special issues for Multimedia Systems Journal, Multimedia Tools and Applications, and Journal of Visual Communication and Image Representation. He received the Best Paper Award continuously from the ACM International Conference on Multimedia 2010 and 2009, and the Best Paper Award from the International Multimedia Modeling Conference 2010.

Xian-Sheng Hua: Dr. Hua is now a Principle Research and Development Lead with Microsoft Bing, working on multimedia search. Before that, he had been with Microsoft Research Asia, Beijing, for nine years, where he was a Lead Researcher with the media computing group. His current research interests are in the areas of image and video content analysis, multimedia search, management, authoring, sharing, mining, advertising and mobile multimedia computing. He has authored or co-authored more than 190 publications in these areas and has more than 60 filed patents or pending applications. He serves as an Associate Editor of IEEE Transactions on Multimedia, Associate Editor of ACM Transactions on Intelligent Systems and Technology, Editorial Board Member of Advances in Multimedia and Multimedia Tools and Applications, and editor of Scholarpedia (Multimedia Category).

^ Back to Top

Title: "Ambient Media Computation – A Service and Business Level Perspective"

Media evolved from media that can be described as integrated presentation in one form (multimedia). From multimedia, media evolved towards embedding the consumer in a computer graphic generated synthetic world (virtual reality). From this point on, media evolved to the consumers directly exposed to the media in their natural environment, rather than computer interfaces (ambient media). In addition, media will be evolving towards a fully real/synthetic world undistinguishable from pure media integrating human capacity (biomedia or bio-multimedia) somewhere in the very far distant future. The goal is to train and educate participants in new innovative service design for ambient computation. The course will cover potential and possibilities of this new multimedia field and its relation to other trends, such as ubicom, pervasive computation, affective computation, and tangible media. Specific key-concepts of ambient media are developed based on various business case studies.

Brief Biography:
Artur Lugmayr: Prof. Dr. Artur Lugmayr describes himself as a creative thinker of future media environemtns, and his scientific work is situated between art and science. His vision is to create innovative media experiences with emerging media platforms tagged with solid buisness models and processes. Starting from July 2009 he is full-professor for entertainment and media production management at the Department of Business Information Management and Logistics at the Tampere University of Technology (TUT) and founded the EMMi Lab. Besides many achievements, he is engaged in Dr.-Arts studies at Aalto Univ., Helsinki besides his completed Dr.-Techn. studies; was guest scientist at several universities and/or hold guest lectures/talks (e.g. Harvard Medical School/USA, QUT/Australia, KTH/Sweden, UFAM/Brasil, Univ. of Neuchatel/Switzerland); founder of the Ambient Media Association (AMEA); established several competitions situated between art and technology (e.g. Nokia Ubimedia MindTrek Award, EuroITV Grand Challenge); contributed numerous scientific works; and founded the production company LugYmedia Inc.

^ Back to Top

Title: "Advances in Perceptual Coding of Digital Pictures"

Traditional definition of digital picture coding covers compression of visual data in form of both still images and moving or motion pictures or image sequences or videos [1]. Digital picture compression products, systems and applications proliferated over the past two decades, at a pace which had never been witnessed since the pioneering work by Goodall at Bell Labs in 1949 [2], in visual communications and entertainment, including video telephony, video conferencing, digital television (TV) broadcasting including Standard Definition or SD, High Definition or HD and three-dimensional or 3-D video signals, IPTV (Internet Protocol TV), IP CCTV (Closed-Circuits TV), video streaming and on-demand services, PACS (Picture Archiving and Communication System) for biomedical imaging, satellite imaging, DVD and HD DVD/Blue-ray products, broadband wireless and multimedia communications (click here for more details).

Brief Biography:
K. R. Rao: Prof.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) (click here for more details).

Hong Ren Wu: Dr.Hong Ren Wu received his BEng. and MEng. degrees from University of Science and Technology, Beijing, China, in 1982 and 1985 respectively. He received his Ph.D. degree in electrical and computer engineering from The University of Wollongong, NSW, Australia, in 1990. Dr Wu was on academic staff of Monash University from 1990 to 2005, last as an associate professor. He has been a professor of visual communications engineering with Royal Melbourne Institute of Technology (RMIT University) since 2005 and concurrently served as Head of Computer and Network Engineering from Feb. 2005 to Jan. 2010 (click here for more details).

^ Back to Top

Title: "Human action analysis with 2D and 3D sensors"

Human action analysis is a critical task and emerging topic in many multimedia applications. In the past few years, there has been a lot of progress in action recognition with conventional 2D video cameras. Effective techniques have been developed to address many challenging issues in real world environments such as dynamic and cluttered background and occlusions. More recently, the availability of commodity depth cameras has brought a new level of excitement to this field. Rapid progress has been made that addresses new technical issues in action recognition with 3D depth cameras. In this tutorial, we introduce the basics for human action analysis, using both regular and depth cameras. The topics cover the action analysis using depth cameras, action and abnormal event detection in surveillance videos, as well as action analysis in user-generated consumer videos, such as movies and Youtube videos.

Brief Biography:
Zicheng Liu: Dr. Zicheng Liu is a senior researcher at Microsoft Research, Redmond. His current research interests include human activity recognition, face modeling and animation, and multimedia collaboration. He received a Ph.D. in Computer Science from Princeton University. He has published over 80 papers in peer-reviewed international journals and conferences, and holds over 50 granted patents. He co-authored a book entitled “Face Geometry and Appearance Modeling: Concepts and Applications”, Cambridge University Press, 2011. He has served in the technical committees for many international conferences. He is a technical co-chair of both 2010 and 2014 ICME, a co-organizer of 2011 and 2012 CVPR Workshops on Human Activity Understanding from 3D Data, and a general co-chair of 2012 IEEE Visual Communication and Image Processing. He is an associate editor of both Machine Vision and Applications journal and Journal of Visual Communications and Image Representation. He is a senior member of IEEE.

Junsong Yuan : Junsong Yuan is a Nanyang Assistant Professor at Nanyang Technological University (NTU), Singapore, and currently the program director of video analytics at Infocomm Center of Excellence, School of EEE, NTU. He received the EECS outstanding Ph.D. Thesis award from Northwestern University, USA, and the Doctoral Spotlight Award from IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'09). He has been invited to present his action detection work in a number of universities and industry labs in the past three years, including UIUC, Peking University, Chinese Academy of Science, Microsoft Research Redmond, Motorola Applied Research Center, Nokia Research Center etc. He has published 60 papers in peer-reviewed journals and conferences, and filed three US patents and one international patent. He is the co-chair of two workshops at IEEE CVPR’12 and has served as editor, co-chair, PC member and reviewer of many international journals and conferences/workshops/special sessions.

^ Back to Top

Title: "Network Coding for Efficient Multimedia Content Delivery"

With the increasing popularity of multimedia content such as ultra-high definition video, multi-view video, free viewpoint video etc., it is a challenge for network service providers to distribute such high volume content at a high throughput while maintaining the required standard of quality of service. Popular internet applications such as live streaming, IP TV, web conferencing, etc. require delivering high volume multimedia content among multiple receivers. The usage of multicast technologies enables to deliver content to multiple receivers much more efficiently compared to unicast, albeit the question arises, are network resources utilized optimally?

Network Coding is a novel concept of network coding to optimally utilize network bandwidth. This treats information transmitted in a multicast network quite distinctively to the notion of regarding information as fluids. In network coding, information packets are coded at intermediate nodes. This increases the throughput at which information is delivered to receivers in a multicast network and improves the robustness against packet errors and losses. Due to such advantages, it is appealing to utilize network coding in practical networks to enhance network resource utilization and increase the quality of service.(click here for more details).

Brief Biography:
Anil Fernando: Anil Fernando (SMIEEE) is a Reader and leads the Video Codec group at the University of Surrey, UK. He has been working in video coding and communications since 1998 and has published more than 250 international refereed journal and proceeding papers in this area. Furthermore, he has published more than 130 international refereed journal and conference papers in multimedia communications. He has contributed to several international projects and currently he is leading 3D video communications work in two large scale projects funded by the European Union on Media communications. Recently he won the IEEE Chester Sall award sponsored by the IEEE Consumer Electronic Society for one of his work on 3D video compression. Most Recent Tutorials (during last 4 years): IEEE ICME 2011, IEEE ICME 2010, ICME 2009, ICME 2008, ICME2007, IEEE ICASP 2009, IEEE ICIP 2007.

^ Back to Top

Title: "Learning and Mining with Visual Data on the Web"

Increasingly rich and large-scale image related data are being posted to social network and media sharing websites. Researchers from multidisciplinary areas, including machine learning, computer vision, data mining, and human machine interaction, are developing methods for various applications. This tutorial provides an overview of representative recent advances in this arena of opportunities and challenges.

First, we discuss Web 2.0 which gave rise to the enormous amount of visual data on the Web. Next, we describe a new computational machinery, Patch Alignment Framework (PAF), which was proposed to unifying various manifold learning based dimension reduction algorithms. Second, we review the recently popular data driven approaches that extends PAF for various settings, such as non-negative data analytics, sparse learning, multiview learning, transfer learning and active learning. Finally, we give example applications of PAF and its variants.

Brief Biography:
Dacheng Tao: Dacheng Tao is Professor of Computer Science with the Centre for Quantum Computation & Intelligent Systems and the Faculty of Engineering & Information Technology in the University of Technology, Sydney. He mainly applies statistics and mathematics for data analysis problems in computer vision, data mining, machine learning, multimedia, and video surveillance. He has authored and co-authored more than 100 scientific articles at top venues including IEEE T-PAMI, T-IP, T-NNLS, AISTATS, ICDM, CVPR, ECCV, ACM SIGKDD and Multimedia, with the best theory/algorithm paper runner up award in IEEE ICDM’07.

^ Back to Top