The ACM Multimedia 2002 conference will feature the following panel session:

Organizers: Chitra Dorai and Frank Nack

Introduction

Note: unfortunately, Dr. Zettl had to cancel his participation to the panel

As pointed out in the keynote address at the 2001 ACM Multimedia Conference [3], the current major goal of multimedia research is directed towards provisioning information for pervasive access and use. To achieve this, what will become important are technologies that help sift useful nuggets of information from torrents of media data, which can be turned into valuable knowledge just in time and need, and tools that help provide access to these nuggets in anytime - anywhere - any device mode to everyone ranging from enterprise customers to independent consumers. Further we need to treat various media on an equal basis in environments that provide multimedia-based interactions, where they ultimately add value to users, whatever the nature of the interactions may be and whatever the preferred mode of media access may be. Thus, there is a fundamental need to investigate the means to elucidate, sublimate, or rationalize information and knowledge from media data. However, current user expectations are far from being met owing to generic low-level content metadata available from automated processing that deal only with representing perceived content, and not the semantics of it.

The challenges in modeling and extracting media-intrinsic as well as extrinsic semantics are as complicated as the attendant problem of matching them with user needs in various domains in which we anticipate robust media usage [4]. Moreover, once information is gathered from various repositories in a federated fashion, we also need mechanisms to automatically process the disparate data for generating visually pleasing media presentations, and for need-oriented and device-appropriate media playback. The tools for designing and developing such technologies are in their infancy and their development depends very much on a better understanding of user requirements, domain needs, objective measurements of media items as well as subjective interpretations.

One promising approach at bridging the semantic gap and building high-level semantic descriptions for reliable content location, access, and navigation services is founded on an understanding of media elements and their roles in synthesizing meaning, manipulating perceptions, and crafting messages, with a systematic study of media productions [1]. The two broadest attempts for a standardized description of content, the Semantic Web from the W3C [5], and MPEG-7 from ISO [2], also provide some insight into these problems but only briefly touch on the problem of underlying semantics needs in different domains. The goal of this panel is to explore, discuss and come to a better understanding of the following issues:

• How do we relate the issue of semantic gap in media research with the market place need to build an effective "Media- Google"?
• What kinds of semantic descriptions do domains with real business needs require? Or in other words what are the appropriate levels of semantic descriptions to satisfy those needs of users?
• How do content creators craft semantics in their material, i.e., what are their processes to compose meaning?
• Which tools do they use and what do they still need?
• Which presentation/discourse tools do we need and which level of semantic descriptions do they require?
• How should the current state of the art in Semantic Web and MPEG-7 standards be extended in a way that makes user, domain, and presentation-specific ontologies applicable for describing multimedia content?
• How should domain and multimedia ontologies be related to ensure that terms from multiple ontologies could be used within a single instance?
• How far can the new approaches such as production knowledge and film grammar-based content analysis be pushed?
• How do we build technologies for production-time (just-intime) annotation tools, thus avoiding annotating material as an afterthought in the process of content creation?
• Which technologies do we need to finally allow general public, the access to annotated media material for the purpose of discourse in encyclopedic spaces?

The members of this panel are stakeholders representing the whole multimedia value chain, and involved in content creation, authoring, media production, content management, distribution, interactive knowledge spaces, media standards, and presentation. Each of these fields presents various facets of the issues outlined above that will help us to explore the need and importance of media semantics in the broadest sense, identify fruitful research directions and propose some exciting solutions.

Panelist: Andreas Mauthe

Dr. Andreas Mauthe holds a Master (Dipl-Wirtsch-Inf.) in Applied Economics and Computer Science from the University of Mannheim, Germany and a PhD in Computer Science from Lancaster University, UK. His research area has been multimedia systems, group and multipeer communications, and QoS. In 1997 he joined the Content Management Division of tecmath (now blue order) originally working on two European projects (CARO and OPAL) dealing with the problems of content exchange and management, collaboration and Web presence of radio and television broadcasters. Subsequently he became Chief Development Officer in the same company responsible for the development of media archive, a distributed content management system. In this capacity he also oversaw a number of large-scale customer projects at major public and private broadcasters throughout Europe. From January 2001 until March 2002 he was responsible for the UK Operations of the same company. As member of the division board he was also involved in the strategic planning of the product development and business development of the company. Since leaving blue order in March 2002 he has been pursuing research in the area of Content Delivery Networks, Peer2Peer Systems and Distributed Content Management Platforms.

Panelist: Lloyd Rutledge

Dr. Lloyd Rutledge is a researcher at CWI, the Dutch national center for computer science and mathematics research. His research involves the Semantic Web, adaptive hypermedia and hypermedia standards. He received his Sc.D. from the University of Massachusetts, Lowell. Dr. Rutledge is a member of the W3C working group that developed SMIL. He is also a co-author of "SMIL: Interactive Multimedia on the Web", published in May by Pearson Education.

Panelist: Thomas Sikora

Prof. Thomas Sikora is the chair of the Communication Systems Department at Technical University Berlin, Germany. He received the Dipl.-Ing. degree and Dr.-Ing. degree in electrical engineering from Bremen University, Germany, in 1985 and 1989 respectively. In 1990 he joined Siemens Ltd. and Monash University, Melbourne, Australia, as a project leader responsible for video compression research activities in the Australian "Universal Broadband Video Codec" consortium. Between 1994 and 2001 he was the director of the "Interactive Media" Department at Heinrich-Hertz-Institute (HHI) Berlin GmbH, Germany. Dr. Sikora is co-founder and director of 2SK Media Technologies and Vis-a-Pix GmbH, two Berlin-based start-up companies involved in research and development of audio and video signal processing and compression technology. Dr. Sikora has been involved in international ITU and ISO standardization activities as well as in several European research activities for a number of years. As the chairman of the ISO-MPEG video group (Moving Picture Experts Group), he was responsible for the development and standardization of the MPEG-4 and MPEG-7 image and video algorithms. He also served as the chairman of the European COST 211 video compression research group. He frequently works as an industry consultant on issues related to interactive digital audio and video. He is an appointed member of the Advisory and Supervisory board of a number of German companies and international research organizations. Dr. Sikora is recipient of the 1996 German ITG award (German Society for Information Technology). He is appointed as an Associate Editor for a number of international journals including the IEEE Signal Processing Magazine and the EURASIP Signal Processing: Image Communication and EURASIP Signal Processing journals. He currently serves as the Editor-in-Chief of the IEEE Transactions on Circuits and Systems for Video Technology. He is a member of ITG and a senior member of IEEE.

Panelist: Gwendal Auffret

Dr. Chitra Dorai is a Research Staff Member at the IBM T.J. Watson Research Center, New York, where she leads the Media Semantics and e-Learning Media projects. She also serves as the IBM Research Relationship Manager for the media sector. Her research interests are in the areas of multimedia systems and digital video analysis, computer vision, pattern recognition and machine learning. Her current research focuses on developing technologies for digital media analysis in various domains such as education and training media and motion pictures, that are useful in content-based structuralization, annotation and search, and smart browsing. She received her Ph.D. from the Department of Computer Science at Michigan State University, where she was a recipient of the Distinguished Academic Achievement Award from the College of Engineering. Her work has received awards and recognition such as the Top-Ranked Paper at the 2002 Asian Conference on Computer Vision, the Best Paper Prize at the 2001 IEEE Pacific-Rim Conference on Multimedia, the Best Industry-related Paper Award at the 2000 International Conference on Pattern Recognition, and Honorable Mention in the 24th Annual Best Paper Award Contest of the Pattern Recognition Journal, 1997. She is a senior member of the IEEE and a member of the ACM.

Dr. Frank Nack is a senior researcher at CWI, currently working within the Multimedia and Human-Computer Interaction group. He obtained his Ph.D. in "The Application of Video Semantics and Theme Representation for Automated Film Editing", at Lancaster University, UK. The main thrust of his research is on video content representation, digital video production, multimedia systems that enhance human communication and creativity, interactive storytelling and media-networked oriented agent technology. He is a member of the MPEG-7 standardization group where he served as editor of the Context and Objectives Document and the Requirements Document, and chaired the MPEG-7 DDL development group. He is on the editorial board of IEEE Multimedia, where he edits the Media Impact column.

REFERENCES