ICME 2002 Program
Tuesday August 27
Multimedia CDNs: What's the next step?
Tue August 27, 2002, Salle
Polyvalente, 16h.30.
Chair/Moderator: Lisa Amini, IBM
Research, USA
Multimedia
content delivery represents a unique opportunity for technology and service
providers – unlike other content types, which are enhanced by delivery
from servers positioned at the edge of the network, rich media requires
edge delivery to attain reasonable user experiences.
While digital audio and video content brings additional complexities
(very large objects, isochronous delivery, and interactivity), the advantages of
edge delivery are exceptional. Attributes
making multimedia especially well-suited for edge delivery include: the need for
Quality of Service (QoS) for an adequate user experience, write-once-read-many
nature, high value to Content Providers, distribution and delivery revenue
potential to Service Providers – especially for pervasive and wireless
devices, the need for detailed usage statistics, and the potential for content
services to adapt and protect multimedia assets are best offered through
distributed techniques, to name a few.
The
technical advantages of Content Delivery Networks (CDN) for Internet accessible
multimedia are obvious to most in the rich media community. Likewise, in the
enterprise environment, e-Learning, collaboration, and corporate communications
applications are driving requirements for enterprise CDN (e-CDN) technology.
To meet these demands, researchers and developers are racing to create
innovative technology for a range of rich media services, including
personalization, annotation, transcoding, rights management, filtering, and a
host of other digital content "must-haves." And yet, recent
events have made it clear that the evolution of multimedia CDN’s is highly
dependent on a variety of business, as well as technical, issues.
This
panel brings key researchers who are creating multimedia distribution and
delivery technology together with experts who are leading the deployment of next
generation multimedia services. The goal of the panel is to explore, discuss,
and come to a better understanding of the issues shaping the multimedia CDN
space, including:
Panelists:
Dr.
Mark Stuart Day
is Senior Scientist at Cisco Systems, where he is technical lead for product
management of Cisco's CDN products. He joined Cisco with the acquisition of
SightPath in 2000. Previously, he
was at Lotus, where his work contributed to the creation of Lotus Sametime. In
the IETF, Mark is co-chair of the working groups on Content Distribution
Internetworking (CDI) and Instant Messaging and Presence Protocol (IMPP).
He received his Ph.D. from MIT in 1995.
Dr.
Minoru Etoh
received the B.E. and M.S.E.E. degrees from Hiroshima University, Hiroshima,
Japan, in 1983 and 1985, respectively. He received the Ph.D. degree from Osaka
University, Osaka, Japan, in 1993. In 1985 he joined the Matsushita Electric
Industrial Co., Ltd. From 1988 to 1990 he worked for the ATR Communication
Systems Research Laboratories, the Advanced Telecommunication Research
International, Kyoto. From 1991 to 1993, he was a Visiting Researcher at Osaka
University. In the period of the ATR and Osaka University, he was involved in
Computer Vision research. From 1994 to 1998, he was at the Central Research
Laboratories of Matsushita Electric, and in the meantime he participated the
MPEG-4 standardization. He was also Adjunct Professor of Nara Institute of
Science and Technology from 1997 to 2000. After moving to Matsushita Research
Institute of Tokyo in 1999, He joined Multimedia Laboratories of NTT DoCoMo,
Inc., Yokosuka, May 2000. He currently works for NTT DoCoMo as Director of
Signal Processing Laboratory and also serves as Adjunct Lecturer of Osaka
University. He is now conducting the research groups in charge of audio, speech
and video coding technologies, media delivery over mobile networks, MPEG, ITU-T,
3GPP, and W3C standardization activities. Dr. Etoh received the 1995 Best Paper
Award of IEICE Japan, the 14th Telecom System Technology Prize of the
Telecommunications Advancement Foundation(1998), the 7th Sakai Commemorative
Prize of IPSJ(1998), respectively. He is a member of IEEE, IEICE, and IPSJ.
Dr.
Emmanuel Gouleau
has been involved within France Telecom R&D, the R&D labs of France
Telecom, as an R&D engineer in several development projects related to the
design of hosting architecture for multimedia streaming services since October
1997. Two kinds of architectures are currently considered, either centralized or
distributed also called CDN. This implication can be described in two contexts
with different timeframes. The first context is "short term" oriented.
It consists in the evaluation of current industrial solutions for the
key-components of a streaming hosting architecture: load balancing or
redirection with L7 switches, caching and splitting with streaming caches,
content management software. France Telecom business units expect from FTR&D
some recommendations in defining the consistency between the services they want
to offer and the industrial offer. The second context, "mid term"
oriented, is the follow-on of industrial roadmaps and their relationship with
standards design within MPEG and IETF. The main objective is to anticipate the
future needs of France Telecom and give some feedback to the industrial
manufacturers. A second working area in this context is the development of
prototype in order to get a better understanding of the on-going developments of
products and protocols.
Prof.
Keith W. Ross
is a professor in the Multimedia Communications Department at Institut Eurecom,
a research and graduate teaching institution in France.
Before joining Institut Eurecom, he was a professor in the Department of
Systems Engineering at theUniversity of Pennsylvania from 1985 through 1997.
Professor Ross has made significant research contributions to the theory and
practice of computer networking throughout his career. These contributions
include important papers in the areas of audio and video streaming, content
distribution, quality of service, and traffic modeling of computer networks. His
work on Web caching includes the co-development of the CARP protocol, which has
been implemented in Microsoft and Netscape caching products. His current
research focus is on peer-to-peer networking and content distribution networks.
Professor Ross has written two books, including the textbook, "Computer
Networking: A Top-Down Approach Featuring the Internet," co-authored with
James Kurose, which has been adopted by over 200 universities in the US and is
currently being translated into four languages. From July 1999 to July 2001,
Professor Ross took a leave from Institut Eurecom to found and lead Wimba, an
Internet technology start-up. Wimba develops Java-based streaming messaging
technologies for the Internet.
Wednesday August 28
Defining the Next Generation Challenges in Media Composition, Compression, and Communication R&D.
Wed August 28, 2002, Salle Polyvalente, 16h.15.
Chair/Moderator: Heather Yu, Panasonic Research, USA.
Organized by: Heather Yu, Panasonic Technologies; Wenjun Zeng, PacketVideo.
The Internet is a gigantic pool of rich media in the form of audio, images, video, and graphics, as well as text and hypertext. With the ability to enhance the user experience in an engaging and effective fashion, rich media are increasingly being incorporated into new network applications such as IP telephony, streaming multi-media, interactive advertisements, and Internet radio/TV.
In this panel, we intend to focus on rich media com-position, compression, and communication, as they relate to media content creation, media aggregation, media asset management, and media distribution methods and infrastructure. Panelists will draw on their substantial expertise, both in academia and industry, in addressing these issues. The goal is to raise, discuss, and possibly answer some critical questions to come to a better understanding of:
Media communication is a common theme of interest to all panelists. Motivated by the emerging trends of communication of real-time media over packet networks, deployment of broadband and content distribution networks, and deployment of integrated services networks for wireless and mobile devices, the panel would like to explore the following issues further: Where do we really need breakthroughs for media communication research, especially on real time and streaming media, to have a major impact on future information distribution and systems? What are the risky areas, where breakthroughs don't seem likely at the moment, but if research were successful then the impact would be enormous? Mobile devices are becoming platforms for multimedia communications. What business models make best sense for this emerging market? What are the technology challenges for wireless multimedia communication, especially streaming media and real time communication? If we look ahead five years, what will most surprise us in terms of rich media communication experience and technology?
Panelists:
Prof. Tsuhan Chen Since October 1997, Tsuhan Chen has been with the Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania, where he is now a Professor. He directs the Advanced Multimedia Processing Laboratory, striving to turn multimedia technologies from science fiction into reality. His research interests include multimedia signal processing and communication, audio-visual interaction, biometrics, processing of 2D/3D graphics, bioinformatics, and building collaborative virtual environments. From August 1993 to October 1997, he worked in the Visual Communications Research Department, AT&T Bell Laboratories, Holmdel, New Jersey, and later at AT&T Labs-Research, Red Bank, New Jersey, as a senior technical staff member and then a principle technical staff member. Tsuhan helped create the Technical Committee on Multimedia Signal Processing, as the founding chair, and the Multimedia Signal Processing Workshop, both in the IEEE Signal Processing Society. His endeavor later evolved into the founding of the IEEE Transactions on Multimedia and the IEEE International Conference on Multimedia and Expo, both joining the efforts of multiple IEEE societies. He has recently been appointed as the Editor-in-Chief for IEEE Transactions on Multimedia since 2002. Before serving as the Editor-in-Chief for IEEE Transactions on Multimedia, he also served in the Editorial Board of IEEE Signal Processing Magazine and as Associate Editor for IEEE Trans. on Circuits and Systems for Video Technology, IEEE Trans. on Image Processing, IEEE Trans. on Signal Processing, and IEEE Trans. on Multimedia. He has co-edited a book titled Advances in Multimedia: Systems, Standards, and Networks. Tsuhan received the B.S. degree in electrical engineering from the National Taiwan University in 1987, and the M.S. and Ph.D. degrees in electrical engineering from the California Institute of Technology, Pasadena, California, in 1990 and 1993, respectively. He received the Charles Wilts Prize for outstanding independent research in Electrical Engineering leading to a Ph.D. degree at the California Institute of Technology. He has published many technical papers and holds thirteen U.S. patents. He is a recipient of the National Science Foundation CAREER Award.
Dr.
Leonardo Chiariglione, a national of Italy, is Vice President,
Multimedia of Telecom Italia Lab, the Corporate Research Centre of the Telecom
Italia Group. In February 1999, he was appointed ExecutiveDirector of the Secure
Digital Music Initiative (SDMI), charged with developing technical
specifications for secure digital delivery of music, position he held until
March 2001. Dr. Chiariglione originated and chairs the Moving Pictures Experts
Group (MPEG), the ISO standardization group which produced the MPEG-1, MPEG-2
and MPEG-4 standards that support digital audio-visual applications on diverse
delivery systems, MPEG-7 and is producing MPEG-21. Dr. Chiariglione also
originated the Digital Audio-Visual Council (DAVIC), the Foundation for
Intelligent Physical Agents (FIPA) and the EURASIP journal "Image
Communications". Dr. Chiariglione obtained his Ph.D. from the University of
Tokyo, and graduated in Electronic Engineering from the Polytechnic of Turin.
Prof.
Bernd Girod is Professor of Electrical Engineering in the Information
Systems Laboratory of Stanford University, California. He also holds a courtesy
appointment with the Stanford Department of Computer Science. His research
interests include networked multimedia systems, video signal compression, and
3-d image analysis and synthesis. He received his M. S. degree in Electrical
Engineering from Georgia Institute of Technology, in 1980 and his Doctoral
degree "with highest honors" from University of Hannover, Germany, in
1987. Until 1987 he was a member of the research staff at the Institut für
Theoretische Nachrichtentechnik und Informationsverarbeitung, University of
Hannover, working on moving image coding, human visual perception, and
information theory. In 1988, he joined Massachusetts Institute of Technology,
Cambridge, MA, USA, first as a Visiting Scientist with the Research Laboratory
of Electronics, then as an Assistant Professor of Media Technology at the Media
Laboratory. From 1990 to 1993, he was Professor of Computer Graphics and
Technical Director of the Academy of Media Arts in Cologne, Germany, jointly
appointed with the Computer Science Section of Cologne University. He was a
Visiting Adjunct Professor with the Digital Signal Processing Group at Georgia
Institute of Technology, Atlanta, GA, USA, in 1993. From 1993 until 1999, he was
Chaired Professor of Electrical Engineering/Telecommunications at University of
Erlangen-Nuremberg, Germany, and the Head of the Telecommunications Institute I,
co-directing the Telecommunications Laboratory. He has served as the Chairman of
the Electrical Engineering Department from 1995 to 1997, and as Director of the
Center of Excellence "3-D Image Analysis and Synthesis" from
1995-1999. He has been a Visiting Professor with the Information Systems
Laboratory of Stanford University, Stanford, CA, during the 1997/98 academic
year. As an entrepreneur, Prof. Girod has worked successfully with several
start-up ventures as founder, investor, director, or advisor. Most notably, he
has been a founder and Chief Scientist of Vivo Software, Inc., Waltham, MA
(1993-98); after Vivo's aquisition, since 1998, Chief Scientist of RealNetworks,
Inc. (Nasdaq: RNWK); and, since 1996, an outside Director of 8x8, Inc. (Nasdaq:
EGHT). Prof. Girod was elected Fellow of the IEEE in 1998 'for his contributions
to the theory and practice of video communications. He is the recipient, with
Joachim Eggers, of the 2001 EURASIP Best Paper Award and has been named
"Distinguished Lecturer" for the year 2002 by the IEEE Signal
Processing Society.
Dr. Philip A. Chou received the B.S.E. degree from Princeton University, Princeton, NJ, in 1980, and the M.S. degree from the University of California, Berkeley, CA, in 1983, both in electrical engineering and computer science, and the Ph.D. degree in electrical engineering from Stanford University, Stanford, CA, in 1988. Since 1977, he has worked for IBM, AT&T Bell Laboratories, Princeton Plasma Physics Lab, Telesensory Systems, Speech Plus, Hughes, Xerox, VXtreme, and Microsoft, where he was involved variously in office automation, motion estimation, character recognition, speech compression, LPC and text-to-speech synthesis, compression of digitized terrain, speech and document recognition, and multimedia network communication. His research interests are data compression, pattern recognition, and multimedia processing and communication. In 1994-95, he was a consulting associate professor at Stanford University. Since 1998, he has been an affiliate professor at the University of Washington. Currently, he is with Microsoft Corporation, in Redmond, WA. Dr. Chou serves on the IEEE Technical Committee for Image and Multidimensional Signal Processing (IMDSP). From 1998 to 2001, he served on the editorial board of the IEEE Transactions on Information Theory as an Associate Editor for Source Coding. He is a senior member of the IEEE, a member of Phi Beta Kappa, Tau Beta Pi, Sigma Xi, and the IEEE Computer, Information Theory, Signal Processing, and Communications societies, and was an active member of the MPEG committee. He is the recipient, with Tom Lookabaugh, of the 1993 Signal Processing Society Paper award.
Prof.
Edward J. Delp
was born in Cincinnati, Ohio. He received the B.S.E.E. (cum laude) and M.S.
degrees from the University of Cincinnati, and the Ph.D. degree from Purdue
University. In May 2002 he received a Doctor of Technology (Honoris Causa) from
the Tampere University of Technology in Tampere, Finland. From 1980-1984, Dr.
Delp was with the Department of Electrical and Computer Engineering at The
University of Michigan, Ann Arbor, Michigan. Since August 1984, he has been with
the School of Electrical and Computer Engineering and the Department of
Biomedical Engineering at Purdue University, West Lafayette, Indiana. In 2002 he
received a chaired professorship and currently is The Silicon Valley Professor
of Electrical and Computer Engineering and Professor of Biomedical Engineering
at Purdue University. His research interests include image and video
compression, multimedia security, medical imaging, multimedia systems,
communication and information theory. Dr. Delp is a Fellow of the IEEE, a Fellow
of the SPIE, and a Fellow of the Society for Imaging Science and Technology
(IS&T). In 2000 he was selected a Distinguished Lecturer of the IEEE Signal
Processing Society. From 1997-1999 he was Chair of the Image and
Multidimensional Signal Processing (IMDSP) Technical Committee of the IEEE
Signal Processing Society. From 1994-1998 he was Vice-president for Publications
of IS&T. He was Co-Chair of the SPIE/IS&T Conference on Security and
Watermarking of Multimedia Contents that was held in San Jose in January 1999,
January 2000, January 2001, and January 2002. Dr. Delp was the General Co-Chair
of the 1997 Visual Communications and Image Processing Conference (VCIP) held in
San Jose. He was Program Chair of the IEEE Signal Processing Society's Ninth
IMDSP Workshop held in Belize in March 1996. He was General Co-Chairman of the
1993 SPIE/IS&T Symposium on Electronic Imaging. He is the Program Co-Chair
of the IEEE International Conference on Image Processing that will be held in
Barcelona in 2003. From 1984-1991 Dr. Delp was a member of the editorial board
of the International Journal of Cardiac Imaging. From 1991-1993, he was an
Associate Editor of the IEEE Transactions on Pattern Analysis and Machine
Intelligence. From 1992-1999 he was a member of the editorial board of the
journal Pattern Recognition. From 1994-2000, Dr. Delp was an Associate Editor of
the Journal of Electronic Imaging. From 1996-1998, he was an Associate Editor of
the IEEE Transactions on Image Processing. In 1990 he received the Honeywell
Award and in 1992 the D. D. Ewing Award, both for excellence in teaching. In
2001 he received the Raymond C. Bowman Award for fostering education in imaging
science from the Society for Imaging Science and Technology (IS&T). In 1990
he received a Fulbright Fellowship to visit the Universitat Politecnica de
Catalunya in Barcelona, Spain. In 2002 he was awarded a Nokia Fellowship.
Dr.
Dorée Duncan Seligmann is currently the director of Collaborative
Applications Research at AvayaLabs. Seligmann studied anthropology at Harvard,
writing a thesis that compared Irish and Irish-American pubs. Afterward, she
moved to Paris, where she began a theater group. Upon returning to the United
States, she earned a Ph.D. in Computer Science at Columbia University and joined
Bell Labs. At Bell Labs, she helped build the Rapport multimedia conferencing
system and application sharing system. She then developed Archways, an
automatically generated virtual environment with 3D graphics and 3D sound. Her
interest is in developing new systems that enable people to communicate more
effectively and efficiently. Under the broad rubric of providing a rich user
experience, this work involves issues ranging from aesthetic considerations to
mechanisms to increase ease-of-use and a user's control over devices and
systems. More specifically her current work centers around context-aware
applications using presence, location, and the plethora of small and often
wireless devices. Other activities include founding board member of Thundergulch,
the Lower Manhattan Cultural Council's "new media laboratory," the
book “Life Into Art: Isadora Duncan and Her World” and editor the art and
technology column in IEEE Multimedia.
Thursday August 29
Multimedia Indexing: Promises and Problems.
Thu August 29, 2002, Salle Polyvalente, 16h.30
Chair/Moderator: John Smith, IBM Research, USA.
Organized by : John Smith, IBM Research, USA.
In
recent years, digital photos, music, video, and other forms of multimedia data
have become a regular part of modern life.
The incredible growth in the amount and importance of multimedia data is
continuing to be driven by further advances in multimedia-enabled computers and
networked consumer electronics devices, growing storage capacities, and
increasing penetration of broadband. Furthermore,
consumer and business applications such as on-line education, entertainment, and
medicine are driving requirements for indexing diverse kinds of multimedia data.
Multimedia
indexing holds great promise for allowing efficient and effective methods for
searching, retrieving, and summarizing multimedia data.
Some of the interoperability challenges are being addressed by the
recently developed MPEG-7 standard, which promises to enable interoperable
multimedia description by providing a rich set of standardized tools for
describing features of multimedia content in XML.
Since MPEG-7 does not standardize methods for extracting the
descriptions, nor for matching and searching, we are left with having to develop
the corresponding technologies. Some
of the technical challenges for multimedia indexing are being addressed in
recent work on automatic feature extraction and similarity searching,
multi-modal analysis and semantic classification, active learning and relevance
feedback searching, and so on. At
the same time, recent multimedia retrieval benchmarking trials have revealed
that usability gap still remains for multimedia retrieval systems, which
indicates that we are not quite there yet.
The
objective of this panel is to address critical questions concerning the promise
and problems of multimedia indexing including the following:
In
this panel, we examine these different dimensions of the problems and promise of
multimedia indexing. We examine the
technical challenges and discuss research projects aimed at addressing them.
Finally, we conclude by making assessments about the nature and timing of
technology developments in relation to the consumer and business needs for
multimedia indexing
Panelists:
Prof. Edward Chang received his Ph.D. in Electrical Engineering at Stanford University in 1999. He is an Assistant Professor at the department of Electrical and Computer Engineering at the University of California, Santa Barbara. His research interests include multimedia databases and interactive TV. He is a recipient of the IBM Faculty Partnership Award in 2000, 2001, and the NSF Career Award in 2002. He is a co-founder and CTO of a multimedia database company.
Dr.
Giridharan Iyengar is a
Research Staff member at IBM's T.J. Watson Research Center in Yorktown Heights,
New York. He is with the
Human Language Technologies department, working on multimodal information
fusion, audio-visual speech technologies, and AV speech event detection.
Prior to joining IBM Research, he completed his Ph.D. (1999) from the MIT
Media Laboratory where he worked on video indexing and retrieval.
His thesis, "Characterization of Unstructured Video" looked at
distributional clustering algorithms for video retrieval applied to cataloguing
of home videos. The focus of this work was to build a set of tools that analyze,
characterize and prepare casually shot footage for interesting reuse such as
making short summaries, video postcards etc.
Giri is interested in semantic analysis and statistical modeling of
video, multimodal information fusion, and multimedia indexing and retrieval.
Dr.
Rainer Lienhart
received a Master's degree in Computer Science and Applied Economics and a Ph.D.
in computer science from the University of Mannheim, Germany on 'Methods for
Content Analysis, Indexing and Comparison of Digital Video Sequences'. He was a
core member of the Movie Content Analysis Project (MoCA). Since 1998 he is a
Staff Researcher at Intel Labs in Santa Clara. His research interests includes
image/video/audio content analysis, machine learning, scalable signal
processing, scalable learning, ubiquitous and distributed media computing in
heterogeneous networks, media streaming, peer-to-peer networking and mass media
sharing. (http://www.lienhart.de,
http://www.videoanalysis.org).
Dr.
Malcolm Slaney
is a research staff member at IBM Almaden Research Center and a visiting
instructor at Stanford's CCRMA. He
received his PhD in electrical engineering from Purdue University.
He is coauthor of the book "Principles of Computerized Tomographic
Imaging (IEEE Press, and recently republished as a SIAM Classic in Applied
Mathematics) and coeditor of the book "Computational Models of Auditory
Function" (IOS Press). While
at Apple Computer, he was one of the first two users of the QuickTime software,
creating a Cray port of the software for use in scientific visualization. Lately
his work has been applying signal processing techniques to text and multimedia
to create indexing tools.
Dr. HongJiang Zhang joined Microsoft Research Asia in 1999, where he is a Senior Researcher and the Assistant Managing Director. He has been with the Institute of Systems Science, National University of Singapore, and HP Labs, USA, as a Research Manger. Dr. Zhang is well known in the multimedia research community for his pioneering work in video and image content analysis, representation, retrieval and browsing. He has authored 3 books, 200 referred papers and book chapters, over 30 US patents and pending applications, and numerous special issues of professional journals in multimedia processing, content-based media retrieval, and video content analysis. "Image and Video Processing in Multimedia Systems", the book he co-authored and published by Kluwer in 1995, was the first one addressed content-based image and video retrieval research. He currently serves on the editorial boards of five international journals and a dozen committees of international conferences. He was the Program Committee Co-chair of the ACM Multimedia Conference, 1999.