Keynotes
(Ismail Khalil - Johannes Kepler University of Linz - Austria)
(Edward Chang - University of California - USA)
(Marcel Worring - University of Amsterdam - Netherlands)
(Sethuraman Panchanathan - University of Arizona - USA)
(Arif Ghafoor- Purdue University - USA)
(Abdulmotaleb El Saddik - University of Ottawa - Canada)
(Madjid Merabti - Liverpool John Moores University - UK)
Multimedia in the Mobile Age
(Ismail Khalil)
Advances in wireless communication networks, ambient intelligence, mobile computing, miniaturized computing devices, embedded systems, etc., have enabled a plethora of new types of multimedia applications and services. Interaction and communication technologies have opened wide horizons for new computing paradigms like pervasive and mobile computing, social networks, semantic Web and Web Intelligence which clearly showed a trend of using computing and communication power to overcome the physical limitations inherited from desktop computers. However, usage statistics showed that there is still a huge gap between the potential of such multimedia applications and services and their acceptance in practice.
In this talk, we will explain and highlight the factors, trends, and issues on how to deploy and utilize mobile multimedia for the design, development and deployment of a content rich, user and business friendly, integrated network of autonomous, mobile agents. One of the major questions to be answered is how to enable the human users to cope with this omnipresence of multimedia information. We already observe in the "traditional" Web, how people are suffering from information overflow, receiving too much, the wrong, or even unwanted information. Personalization and adaptively appear to be potential solutions to this problem but bear the risk of putting the user out of control. Approaches trying to overcome this conflict will be the focus of the presentation.
Ismail Khalil is a senior researcher and lecturer at the institute of telecooperation at Johanes Kepler University Linz, Austria since October 2002. He is the president of the international organization of Information Integration and Web-based Applications & Services @WAS (www.iiwas.org). He holds a PhD in computer engineering and received his habilitation degree in applied computer science on his work on agents interactions in ubiquitous environments in May 2008. He is the editor of the handbook of research on Mobile Multimedia series, the book Mobile Multimedia: Communication Engineering Perspective and the book Multimedia Transcoding in Mobile and Wireless Networks. He currently teaches, consults, and conducts research in Mobile Multimedia, Agent Technologies, and the Semantic Web and is also interested in the broader business, social, and policy implications associated with the emerging information technologies. Before joining Johannes Kepler University of Linz, he was a research fellow at the Intelligent Systems Group at Utrecht University, Netherlands from 2001-2002 and the project manager of AgenCom project at the Software Competence Center Hagenberg - Austria from 2000-2001. Dr. Khalil has authored around 100 scientific publications, books, and book chapters. He serves as the editor-in-chief of the International Journal on Web Information Systems (IJWIS), Journal of Mobile Multimedia (JMM), International Journal of Mobile Computing and Multimedia Communication (IJMcMc), Advances in Next Generation Mobile Multimedia book series, and Atlantis Ambient and Pervasive Intelligence book series. He is on the editorial board of several international journals. His work has been published and presented at various conferences and workshops.
Large-scale Photo Annotation Using Collective Wisdom of Data and Users.
(Edward Chang)
A large percentage of photos on the Internet cannot be reached by search engines because of their absence of keyword annotation. Despite of decades of research, neither model-based nor model-free approach can provide quality annotation to photos. In this talk, I present a hybrid approach and its subroutines. Given query photo q (querying for annotated words), we first suggest some words via a trained model. Though the trained model cannot always provide highly relevant words, we use these words to query a large Web image repository to obtain annotations of returned images. We then use perceptual features (e.g., color, texture, shape, and local characteristics) of photo q to match the returned images, and retain keywords of only those perceptually similar images as initial annotations of the query photo. Our empirical study shows that this hybrid pipeline of four steps can almost always suggest some relevant words to allow photos to be indexed and hence searched. An irrelevant annotation can subsequently be demoted or removed when that annotation seldom attracts user clicks. This hybrid approach takes advantage collective wisdom of data and users to effectively provide and improve annotations in a scalable way. This talk depicts also key subroutines including parallel distributed algorithms that can run on thousands of machines to handle billions of data instances.
Edward Chang Edward Chang joined the department of Electrical & Computer Engineering at University of California, Santa Barbara, in September 1999. Ed received his tenure in March 2003, and was promoted to full professor of Electrical Engineering in 2006. His recent research activities are in the areas of distributed data mining and their applications to rich-media data management and social-network collaborative filtering. His research group (which consists of members from UC, MIT, Tsinghua, PKU, and Google) recently parallelized SVMs (NIPS 07), PLSA and LDA (KDD 08), Association Mining (ACM RS 08), and Spectral Clustering (ECML 08) (see MMDS/CIVR keynote slides for details) to run on thousands of machines for mining large-scale datasets. Ed has served on ACM (SIGMOD, KDD, MM, CIKM), VLDB, IEEE, WWW, and SIAM conference program committees, and co-chaired several conferences including MMM, ACM MM, ICDE, and WWW. Ed is a recipient of the IBM Faculty Partnership Award and the NSF Career Award. He heads Google Research in China since March 2006. Ed received his M.S. in IEOR and M.S. in Computer Science from UC Berkeley and Stanford, respectively. Ed received his PhD in Electrical Engineering from Stanford University in 1999.
Interactive search in large video collections.
(Marcel Worring)
The amount of video in archives as well as on the web is growing to an enormous amount. Finding information in a large video collection is a difficult task. Tools are needed that support the user in posing queries and in understanding the query result. The tools should then provide ample opportunities for taking the output as a starting point for further exploration of the collection. Building these tools requires an intricate interplay among computer vision, machine learning, information visualization, and human computer interaction. In our system, automatically computed semantic indexes describe the visual content of individual video shots, dissimilarity spaces describe the relations between different shots, whereas various content based threads through the set of shots describe the collection as a whole. These additional metadata and structures added to the data provide the basis for a number of innovative interactive video browsers each geared towards different steps in the video search process. In this talk we will highlight the underlying methodologies and show how these can be applied in different applications.
Marcel Worring
Marcel Worring received the MSc degree (honors) and PhD degree, both in computer science, from the Vrije Universiteit, Amsterdam, The Netherlands, in 1988 and the University of Amsterdam in 1993, respectively. He is currently an associate professor in the Intelligent Systems Lab Amsterdam of the University of Amsterdam.
His interests are in multimedia search and systems. With the
MediaMill team he has been developing techniques for semantic video indexing as well as systems for interactively searching large video archives which have been successful over the last years in the TRECVID benchmark, the de-facto standard on the topic. The methodologies developed are now being applied to visual search in broadcast archives as well as in the field of
Forensic Intelligence
in particular for fighting child abuse and surveillance.
He has published over 100 scientific papers covering a broad range of topics from low-level image and video analysis up to applied papers in interactive search. He serves on the program committee of the major conferences in the field. He was the chair of the IAPR TC12 on Multimedia and Visual Information Systems and general co-chair of the 2007 ACM International Conference on Image and Video Retrieval in Amsterdam and co-organizer of the first and second VideOlympics, a real-time evaluation of video retrieval systems. He is associate editor of the IEEE Transactions on Multimedia and of the Pattern Analysis and Applications journal.
Human-centered multimedia computing inspired by focus on disabilities and impairments.
(Sethuraman Panchanathan)
Human Centered Multimedia Computing (HCMC) is a paradigm that enables sophisticated interactions between humans and computing devices/environments. Unlike Human Computer Interaction (HCI), which is targeted at improving the usability of computing devices, HCMC addresses a higher level of functionality where machines adapt to the users resulting in elegant interactions. While many theories have been proposed to advance this paradigm, it is our belief that a complete understanding of the issues surrounding HCMC requires a study of sensory/perceptual and cognitive/neuro-cognitive human disabilities, impairments and deficits. The understanding of human deficiencies in sensory, neural, and cognitive sensing/actuations could reveal innate components of human interaction which is bound to benefit researchers, designers and developers of new multimedia solutions. In addition, technological solutions that are motivated by assistive and rehabilitative goals have broader impacts to the general population. They open up new research issues that would otherwise not have been seen when the focus is only on the “able” population which in turn advances the vision and core principles of HCMC. At the Center for Cognitive Ubiquitous Computing (CUbiC) at Arizona State University, we are engaged in a project for individuals with sensory/perceptual/cognitive disabilities called Collaboratory for Assistive and Rehabilitative Systems (CAReS). This talk will present the core principles of HCMC, challenges in designing human centered assistive and rehabilitative systems through the example of the CAReS project.
Dr. Sethuraman (Panch) Panchanathan is a Professor and Director of the School of Computing and Informatics, Director of the Institute for Computing & Information Sciences & Engineering, and Director of the Research Center on Ubiquitous Computing (CUbiC) at Arizona State University, Tempe, Arizona. He is also a Professor-Associate in the Department of Basic Medical Sciences at the University of Arizona College of Medicine- Phoenix. He is an Affiliate Professor in the Department of Electrical Engineering at ASU. He is co-founder and President of a start-up company MotionEase Inc. which is focused on developing video based motion capture solutions for rehabilitative applications.
He leads a team of Researchers and Graduate students working in the areas of Human-centered Multimedia Computing, Content-based and Compressed Domain Indexing and Retrieval of Images and Video. Multimedia Communication, Face/Gait Analysis and Recognition, Haptic User Interfaces, Confidence Measures for Medical Decisions, Medical Image Processing, Genomic Signal Processing, Media Processor Designs; and Ubiquitous Computing Environments for individuals with disabilities. CUbiC’s flagship project CARES designs diagnostic rehabilitative assistive technologies for individuals with physical, cognitive and neural impediments. The iCARE project for individuals who are blind and visually impaired won the Governor’s Innovator of the Year-Academia Award in Nov. 2004.
Dr. Panchanathan was the Chair of the Computer Science and Engineering Department (2003-2008) and the Founding Director of the new Biomedical Informatics department (2005-2007). He was an Adjunct Professor in the School of Information Technology and Engineering at the University of Ottawa (1997-2004). He was an Honorary Visiting Professor at the University of New South Wales in Sydney, Australia from (1997-1999). He was the Chief Scientific Researcher of Obvious Technology (1995-2004) and was a Scientific Advisor for Luxxon Corp., in San Jose (2000-2003).
Dr. Panchanathan has published over 300 papers in refereed journals and conferences and book chapters. He has been a Chair/Co-chair of over 25 International symposia, workshops, conferences and he was the general chair of ISCAS 2002. In addition, he is a program committee member of numerous conferences, organizer of special sessions in several conferences and an invited panel member of special sessions. Dr. Panchanathan has presented several invited talks in conferences, universities and industry.
Dr. Panchanathan is the Editor-in-Chief of the IEEE Multimedia Magazine and has been /is associate editor of seven other journals and transactions: IEEE Transactions on Multimedia, IEEE Multimedia Magazine, IEEE Transactions on Circuits and Systems for Video Technology, Journal of Visual Communications and Image Representation, Journal of Electronic Imaging, World Scientific Publishing Company Imperial College Press, International Journal on Systemics, Cybernetics and Informatics, and the International Journal on Artificial Intelligence Tools Architectures, Languages, Algorithms, He served as a guest editor of several special issues in Transactions and Journals.
Dr. Panchanathan is currently a PI/Co-PI of projects funded by the National Science Foundation (NSF), National Institute of Health (NIH), Department of Economic Security (Rehabilitation Services Administration), Banner Health and industry. He was also a PI of projects funded by Intel, Motorola, ARM and SUN.
Dr. Panchanathan was a member of the Electronic Health Steering Committee appointed by the Governor of Arizona. He is a member of the Academic Working group of the University of Arizona College of Medicine-Phoenix in partnership with Arizona State University
Dr. Panchanathan is a Fellow of the IEEE and SPIE. He is a member of the Association of Professional Engineers of Ontario (APEO), European Association for Signal Processing (EURASIP), Association of Computing Machinery (ACM) and American Society for Engineering Education (ASEE), American Medical Informatics Association (AMIA).
Dr. Panchanathan can be contacted by email at panch@asu.edu. His office address is School of Computing and Informatics, Arizona State University, Tempe, AZ 85287-8809.
Semantic Computing and Knowledge Discovery for Web Multimedia Information Systems.
(Arif Ghafoor)
Multimedia technology has become an indispensable link for distributed information brokerage, along with user interfaces, and networking sub-systems; its richness in content allows capturing of complex application semantics, but it also presents enormous challenges in eliciting the embedded knowledge. Nevertheless, these challenges must be addressed as a paradigm shift to Web-based multimedia applications in almost all sectors of life appears inevitable. In addition, the richness of information embedded in multimedia data archives and its multiple origination sources exacerbate their semantic heterogeneity and their interpretations. As a result, it is extremely challenging to extract knowledge, develop ontologies, and allow sematic interoperability among multimedia data archives. The objective of this talk is to discuss these challenges and present a coherent multimedia semantic Web (MSW) framework that will provide a systematic methodology for extracting knowledge, semantically linking Web-based multimedia information, and allowing users to query/browse over the Internet for accessing multimedia information of interest. In particular, we will discuss the following issues and present the current state-of-the-art approaches aimed to address them:
- How scalable methodologies can be developed that allow extraction of useful semantics embedded in multimedia data archived at distributed Internet data sites?
- How valuable knowledge can be mined and extracted from such semantics and how such knowledge can be represented and made available to domain users in a manner that allows a universal access?
- How a standardized open domain knowledge representation can be developed to achieve semantic interoperability among multiple platforms?
- How a coherent MSW architecture can be developed that allow semantic interoperability among distributed multimedia data sites?
We conclude this talk by drawing examples from various multimedia application domains.
Arif Ghafoor is currently a Professor in the School of Electrical and Computer Engineering, at Purdue University, West Lafayette, IN, and is the Director of Distributed Multimedia Systems Laboratory. He has been actively engaged in research areas related to multimedia information systems, database security, and parallel and distributed computing. He has published numerous papers in these areas. Dr. Ghafoor has served on the editorial boards of various journals including ACM/Springer Multimedia Systems Journal, the Journal of Parallel and Distributed Databases, and the International Journal on Computer Networks. He has served as a Guest/Co-Guest Editor for various special issues of numerous journals including ACM/Springer Multimedia Systems Journal, the Journal of Parallel and Distributed Computing, International Journal on Multimedia Tools and Applications, IEEE Journal on the Selected Areas in Communications and IEEE Transactions on Knowledge and Data Engineering. He has co-edited a book entitled "Multimedia Document Systems in Perspectives" and has co-authored a book entitled "Semantic Models for Multimedia Database Searching and Browsing" (Kluwer Academic Publishers, 2000). He has been consultant to numerous organizations including UNDP, US Dept. of Defense, Bell Labs, and GE. Dr. Ghafoor is a Fellow of the IEEE. He has received the IEEE Computer Society 2000 Technical Achievement Award for his research contributions in the area of multimedia systems. In 2007 he has received an IEEE Technical Achievement Award in Bioinformtics.
Bringing Touch to Multimedia
(Abdulmotaleb El Saddik)
Multimedia and information technology are reaching limits in terms of what can be done in multimedia applications with only sight and sound. The next critical step is to bring the sense of "touch" over network connections, which is commonly known as Tele-haptics. Haptics, a term which was derived from the Greek verb "haptesthai" meaning "to touch", introduces the sense of touch and force into the human-computer interaction. Currently, research on haptics is broadly categorized into human haptics, machine haptics, and computer haptics. Human haptics is mostly conducted by psychologists to study the mechanism of the "touch" modality, while machine haptics refers to the design of haptic devices to reproduce the sense of "touch". Computer haptics covers all the aspects in haptics applications. The potential of haptics as a new media is quite significant for many applications such as tele-presence, tele-learning, tele-medicine, tele-operation in hazardous environments, industrial design and testing, gaming, and any related interactive virtual reality application. Haptics audio visual networks and architectures will be the main topic of this talk.
Abdulmotaleb El Saddik (F'IEEE) received the Dipl.-Ing. and Dr.-Ing. degrees from the Technical University of Darmstadt, Darmstadt, Germany in 1995 and 2001, respectively. He is University Research Chair and Professor, SITE, University of Ottawa and recipient of the Professional of the Year Award (2008), the Friedrich Wilhelm-Bessel Research Award from Germany's Alexander von Humboldt Foundation (2007) the Premier's Research Excellence Award (PREA 2004), and the National Capital Institute of Telecommunications (NCIT) New Professorship Incentive Award (2004). He is the director of the Multimedia Communications Research Laboratory (MCRLab). He is a Theme co-Leader in the LORNET NSERC Research Network. He is Associate Editor of the ACM Transactions on Multimedia Computing, Communications and Applications (ACM TOMCCAP) and IEEE Transactions on Computational Intelligence and AI in Games (IEEE TCIAIG) and Guest Editor for several IEEE Transactions and Journals. Dr. El Saddik has been serving on several technical program committees of numerous IEEE and ACM events. He has been the General Chair and/or Technical Program Chair of more than 20 international conferences symposia and workshops on collaborative hapto-audio-visual environments, multimedia communications and instrumentation and measurement. He was the general co-chair of ACM MM 2008. He is leading researcher in haptics, service-oriented architectures, collaborative environments and ambient interactive media and communications. He has authored and co-authored two books and more than 200 publications. He has received research grants and contracts totaling more than $10 million and has supervised more than 90 researchers. His research has been selected for the BEST Paper Award three times. Dr. El Saddik is a senior member of ACM, an IEEE Distinguished Lecturer and a Fellow of the IEEE.
Sharing and Protecting Digital Memories in a Networked Environment
(Madjid Merabti)
The increasing power of computers, increasing capacity of digital memory and wider availability of a great variety of input devices such as cameras and video recorders, has resulted in an astonishing growth in the use of multimedia and the production of user generated content. It’s now becoming feasible to store a digital record of everything that a person sees and hears throughout their life, all using cheap and easily obtainable commodity hardware. Such possibilities have given rise to the idea of a digital human life memory, able to store all of the video, photographs, documents and communications that relate to us as we travel through our lives. In this talk we will explore how networked systems can be used to extend the capabilities of digital human life memory stores. Not only through the networking of the memory stores themselves, but also through the use of networked appliances, networked virtual worlds and wireless sensors network technologies. As well as the benefits, the massive increase in multimedia networking also presents drawbacks that include the potential for breaches of privacy and the need for content protection. We will also therefore discuss our work in the area of security that aims to address some of these challenges, and maintain a balance between the competing benefits of sharing and protection of multimedia and sensory data.
Madjid Merabti is Professor of Networked Systems and Director of the School of Computing & Mathematical Sciences, at Liverpool John Moores University, UK. He is a graduate of Lancaster University in the UK. He has over 20 years experience in conducting research and teaching in the areas of Computer Networks (fixed and wireless), Mobile Computing, and Computer Network Security. Prof. Merabti is widely published in these areas and leads the Distributed Multimedia Systems and Security Research Group, which has a number of UK Government, EU, and industry supported research projects. He is principal investigator in a number of current projects in Digital Rights Management, Games Technology, Multimedia Networking, Mobile Networks Security and Privacy Architectures and Protocols, Secure Component Composition in Ubiquitous Personal Networks, Networked Appliances, Mobile and Ad-Hoc Computing Environments, and Sensor Networks.
He is Associate Editor for IEEE Transactions on Multimedia, Area Editor for IEEE Communications Magazine series on Networked Appliances and Home Networking, Co-Editor in-Chief for the International Journal of Pervasive Computing and Communications (JPCC), Member of Editorial Boards for Springer Peer-to-Peer Networking and Applications Journal, Elsevier Journal on Computer Communications, and Wiley’s Communications and Security Journal. Madjid is Guest Editor for Springer Signal Processing special issue on “Advance in Peer-t-Peer Contents Management,” 2009. He was Guest Editor for the Special issue on “Research Developments in Consumer Communications and Networking”, Multimedia Tools and Applications: An International Journal, Kluwer, September 2005.
Madjid Merabti serves on the steering committee for the IEEE Consumer Communications and Networking (CCNC) series of conferences. He is Technical Programme Chair for: IEEE ICC Symposium on Special Areas of Communications, Germany 2009, and IASTED - EuroIMSA 2009 European Conference on Internet and Multimedia Systems and Applications. He is a member of a number of international conference programme committees on networking, security, networked appliances, digital rights management, and computer entertainment.