ACM MM 2006 Tutorials
Title: Peer-to-Peer Multimedia Applications
Full-day Tutorial at ACM Multimedia 2006, on Oct. 23, Monday
Speaker:
Jin Li, Microsoft Research
Intended Audience: Professionals, researchers and students interested in building P2P multimedia applications.
Overview:
In both academia and industry, peer-to-peer (P2P) applications have attracted great attention. Peer-to-peer file sharing applications, such as Napster, Gnutella, Kazaa, BitTorrent, Skype and PPLive, have witnessed tremendous success among end users. And the uses of peer-to-peer network for multimedia streaming, conferencing, gaming, file backup, information retrieval is on the rise. Recent statistics suggests that P2P traffic accounts for as much as 70% of Internet traffic. The purpose of the tutorial is to examine issues associated with the successful building and deployment of a P2P multimedia application. The technologies discussed can be applied to P2P file sharing, P2P conference, P2P media streaming, P2P VoIP, and P2P storage applications. We start by examining two popular P2P applications, BitTorrent and Skype. The study of the two P2P applications helps us to understand the design principles of P2P applications in general. We then investigate a number of tools for building P2P multimedia applications, such as the overlay network, the scheduling algorithm, the erasure resilient coding, and NAT/firewall traversal. Finally, we move on to critical deployment decisions that make or break the P2P applications, such as P2P economy, security issues in P2P application, peer selection, monitoring and debugging utilities in P2P application.
Speaker’s Bio:
Dr. Jin Li received his Ph.D. in electrical engineering from Tsinghua University (Beijing, China) in 1994. From 1994 to 1996, he served as a Research Associate at the University of Southern California (USC). From 1996 to 1999, he was a Member of the Technical Staff at the Sharp Laboratories of America (SLA), (Camas, WA), and represented the interests of SLA in the JPEG2000 and MPEG4 standardization efforts. He was a Researcher/Project Leader at Microsoft Research Asia (Beijing, China) from 1999 to 2000. He is currently a Senior Researcher at Microsoft Research Redmond. From 2000, Dr. Li has also served as an Adjunct Professor in the Electrical Engineering Department, Tsinghua University (Beijing, China). Dr. Li has personally built a number of P2P applications, such as P2P web hosting, P2P streaming and P2P distributed storage system. He was the driving force behind Microsoft’s strategy and application development in the peer-to-peer area. He is the lead guest editor of the special issue of “Content Storage and Delivery in Peer-to-Peer Networks” for IEEE Trans. on Multimedia and the guest editor of the special issue of “Advances in Peer-to-Peer Streaming Systems” for IEEE Journal on Selected Areas in Communication. He has organized a special session on “Peer-to-Peer Media Communication” for MMSP 2005, and has co-organized the workshop of “Advances in Peer-to-Peer Multimedia Streaming” in ACM Multimedia 2005, and the workshop of “Recent Advances in Peer-to-Peer Streaming” in QShine 2006. He holds 15 issued US patents, with many more pending.
Title: Interactive Digital Television and Multimedia Systems
Half-day Tutorial at ACM Multimedia 2006, on Oct. 23, Monday
Speakers:
Pablo Cesar, CWI AmsterdamKonstantinos Chorianopoulos, AUEB, Athens
Intended Audience: The level of the tutorial will be from introductory to intermediate.
Tutorial website: http://uitv.info/tutorials/acm-multimedia-06/
Overview:
Interactive digital television is an emerging field with a high impact in our societies: it offers interactive services to the masses. This tutorial aims to establish a common framework by summarizing the most significant results in this multidisciplinary field. The review includes topics such as content distribution, system software of the receivers, and user interaction. In addition, we will discuss current commercial events such as the next generation of optical discs (e.g., blue-ray), BBC peer-to-peer service, and mobile television. Based on this discussion, we will formulate an agenda for further research. The agenda includes, for example, end-user enrichment of television content and social television. This half-day tutorial will provide the attendee a solid understanding of the technologies currently in use and an introduction of the open questions in the field.
Speaker’s Bio:
Dr. Pablo Cesar holds a Ph.D. in interactive digital media (with the dissertation: A Graphics Software Architecture for High-End Interactive TV Terminals; 2005). Since 2000 he has participated in several iDTV-related projects. Currently, he is researching how TV viewers are becoming producers and distributors.
Title: Flexible Modelling and Performance Debugging of Real-Time Embedded Multimedia Systems
Half-day Tutorial at ACM Multimedia 2006, on Oct. 23, Monday
Speaker:
Samarjit Chakraborty
Department of Computer Science
National University of Singapore
Intended Audience: The level of the tutorial will be from introductory to intermediate.
Tutorial website: http://www.comp.nus.edu.sg/~samarjit/mm06/
Overview:
This tutorial is primarily intended for an audience with a background in traditional real-time multimedia applications, who would like to establish a connection to embedded systems design for the multimedia domain. It would be useful to researchers, students, multimedia application developers, as well as engineers interested in getting an overview of recent developments in the area of multimedia processing on embedded System-on-Chip (SoC) platform architectures. The emphasis will be on tools and techniques for modelling and analyzing such architectures from the perspective of implementing multimedia applications on them. After attending the tutorial, the audience should get an overview of common design issues in the embedded multimedia domain and techniques for dealing with them. These would include handling real-time and throughput constraints associated with continuous media-processing, power/performance analysis and runtime platform-management techniques. No background in embedded systems or VLSI design automation techniques will be assumed and the lectures will focus on a diverse set of applications, with detailed self-contained examples.
Speaker’s Bio:
Samarjit Chakraborty is an Assistant Professor in the Department of Computer Science at the National University of Singapore. He obtained his Ph.D. from ETH Zurich in 2003. For his Ph.D. thesis, he received the ETH Medal and the European Design and Automation Association’s “Outstanding Doctoral Dissertation Award” in 2004. Samarjit’s research interests are primarily in the area of system-level design of real-time and embedded systems, with a focus on architectures for multimedia applications. He has served on the technical program committees of a number of conferences in the real-time embedded systems area, including CODES+ISSS, DATE, RTSS, ECRTS and RTCSA. He will also serve as the TPC Co-Chair of the 2006 IEEE Workshop on Embedded Systems for Real-Time Multimedia (ESTIMedia), which will be held in Seoul in October this year. In the last few years he has extensively worked on problems related to the topic of this tutorial and published both in real-time, as well as electronic design automation conferences and journals. Recently, his paper entitled “Approximate VCCs: A New Characterization of Multimedia Workloads for System-level MpSoC Design” was nominated for a Best Paper Award at the 2005 ACM Design Automation Conference (DAC).
Title: Computer Audition: An introduction and research survey
Half-day Tutorial at ACM Multimedia 2006, on Oct. 23, Monday
Speaker:
Shlomo Dubnov
Department of Music, University of California, San Diego
Intended Audience: The level of the tutorial will be from introductory to intermediate.
Tutorial website: http://music.ucsd.edu/~sdubnov/ComputerAudition.htm
Overview:
Computer Audition is an interdisciplinary field of audio understanding by machine that combines engineering, information processing and artificial intelligence, cognitive science, music theory and artistic creativity. The tutorial will survey the research in computer audition, focusing on the semantic gap between human and machine levels of audio understanding. Features and methods of audio classification will be covered from analysis-synthesis models and low-level signal features to perceptual and general audio basis representations. Examples will be given from applications of recognition, sound description, score alignment, musical summarization, affect, aesthetics and style modeling.
In the last part of the tutorial Dr. Dubnov will introduce an anticipatory listening model that offers a framework for investigating the relations between methods of computer audition, style modeling and human experience when listening to music, such as emotional force and familiarity.
Speaker’s Bio:
Shlomo Dubnov is an associate Professor in music technology at UCSD. Prior to this he served as researcher in Institute for Research and Coordination of Acoustics and Music (IRCAM) in Paris and was a senior lecturer in department of communication systems engineering in Ben-Gurion University in Israel. He holds PhD in Computer Science from Hebrew University and B.Mus in music composition from Rubin Academy in Jerusalem. His work on polyspectral analysis of musical timbre and his research on machine learning of musical style are widely acknowledged by the computer music community. He served as co-PI in several projects dealing with semantic analysis of audio, such as a recent EU sponsored "Semantic HiFi" project. Currently he is co-editing a book on "The Structure of Style: algorithmic approaches to understanding manner and meaning" and working on a textbook on semantic audio processing.
Title: Data Mining and Information Retrieval in Time Series and Multimedia Databases.
Half-day Tutorial at ACM Multimedia 2006, on Oct. 23, Monday
Speaker:
Eamonn Keogh, UC Riverside
Intended Audience: The level of the tutorial will be from introductory to intermediate.
Tutorial website: http://www.cs.ucr.edu/~eamonn/tutorials.html
Overview:
Time series and multimedia data are ubiquitous; large volumes of such data are routinely created in scientific, industrial, entertainment, medical and biological domains. Examples include gene expression data, X-rays, electrocardiograms, electroencephalograms, gait analysis, stock market quotes, space telemetry, microarrays, CAT Scans etc. Because such data is intrinsically real valued, most of the work on information retrieval of text has little utility for such datasets.
In this tutorial, Dr. Keogh will outline the state of the art in mining and indexing such data, with particular emphasis on data representations, dimensionality reduction and similarity measures.
Speaker’s Bio:
Dr. Keoghs research interests are in Data Mining, Machine Learning and Information Retrieval. He has published more than 80 papers, including works in SIGIR, SIGMOD, SIGKDD, SIGGRAPH, VLDB, ICML, EDBT, PKDD, PAKDD, IEEE ICDM, IEEE ICDE, and SIAM SDM, conferences and in the TODS, DMKD, VLDB, KAIS and IJTAI journals. Several of his papers have won “best paper” awards. In addition he has won several teaching awards. He is the recipient of a 5-year NSF Career Award for “Efficient Discovery of Previously Unknown Patterns and Relationships in Massive Time Series Databases” and a grant from Aerospace Corp to develop a time series visualization tool for monitoring space launch telemetry.
Dr Keogh has given well-received tutorials on time series, machine learning and data mining all over the world, and his papers have been referenced well over 2,000 times.
Title: Recent developments in video compression standards and their impact on embedded platforms: from scalable to multi-view video coding
Half-day Tutorial at ACM Multimedia 2006, on Oct. 23, Monday
Speaker:
Iole Moccagatta, Ph.D.
Scientific Director Multimedia Group
IMEC, Belgium
Intended Audience: The level of the tutorial will be from introductory to intermediate.Overview:
This tutorial will focus on the impact and requirements of recent developments in video compression standards on embedded platforms. It will first present and discuss recent advances in standardized video coding technology, namely the Scalable Video Coding and the Multiple-view Video Coding, both currently developed collaboratively by ITU-T VCEG and ISO/IEC MPEG. The tutorial will then discuss the requirements imposed by these new video coding technologies on embedded platforms. Particular attention will be devoted on how to balance increase performance requirements and power consumption. In this context, the use of parallelization and dynamic (run-time) resource adaptation will be discussed as well.Speaker's Bio:
Iole Moccagatta received her M.Sc. from the University of Pavia, Italy, on 1990, and her Ph.D. from the Swiss Federal Institute of Technology in Lausanne, Switzerland, on 1995, both in electrical engineering. From 1995 to 1997 she was a member of technical staff at the Texas Instruments DSPS R&D Center in Dallas, Texas. From 1997 to 2000 she held a similar position at the Rockwell Science Center Multimedia Group in Thousand Oaks, California. From 2000 to 2003 she was a staff design engineer with the Broadband Entertainment Division at LSI Logic (previously C-Cube Microsystems) in Milpitas, California. In 2000, she joined nVIDIA in Santa Clara, California, as a video architect of the Handheld Division. She is currently the scientific director of the Multimedia Group at IMEC, Belgium. She is the author or co-author of more than 25 technical papers and holds 4 patents in the field of image and video compression.
Title: Multimedia Content Protection
Half-day Tutorial at ACM Multimedia 2006, on Oct. 23, Monday
Speakers:
Dulce Ponceleon and Nelly Fazio
IBM Almaden Research Center
San Jose, CA 95120-6099, USA
Intended Audience: The level of the tutorial will be from introductory to intermediate.Tutorial website: http://www.almaden.ibm.com/cs/people/dulce/MultimediaContentProtectionACMtutorial_2006.htm
Overview:
Multimedia content protection is a controversial topic. Content owners want to protect their rights while consumers want flexible usage and seamless content flow. In this tutorial we cover from cryptography fundamentals, to history, standards, state-of-the-art approaches and life demonstrations.
Key topics covered in the tutorial include:
o Legal, Technical and Business Components
o DRM, Conditional Access, Media Content Protection, Electronic Distribution, etc
o IP, Copyrights, Licensing
o Piracy and its Categories
o Confidentiality, Authentication, Data Integrity, Non-repudiation
o Matrix-based: CPRM
o Tree-based: NNL
o Watermarking and Tracing Traitors
o History of CP Systems
o Standards: 4C and AACS
o The digital home
o On-line and emerging models
We will demonstrate the following technologies and systems: CPRM Download, Kiosk Video Distribution, Digital Home Network, and Apple iPod/iTunes model.Speaker Bios:
Dr. Ponceleon holds an M.S. and a Ph.D. degree in Computer Science from Stanford University. While at Apple Computer Inc. she contributed to compression technologies to QuickTime. She is currently in the Content Protection Competency Center, at the IBM Almaden Research Center. She contributed to the ISO MPEG-7 standards. She is an IBM technical representative in the Advanced Access Content System (AACS), a content protection standard for the next generation of pre-recorded and recorded optical media for consumer use with PCs and CE devices. The “4C Entity” has developed content protection standards for recordable and pre-recorded media (CPRM/CPPM). Dr. Ponceleon is the Chair of the 4C Technical Group since 2004. She has co-authored several tutorials in multimedia information retrieval (SIGIR 2002, SIGIR 2005 and ICASPP 2006). This year she is organizing a workshop in content protection. She holds several patents and publications in content protection and related multimedia areas.
Nelly Fazio earned her M.Sc.(2003) and Ph.D.(2006) in Computer Science from New York University. During her studies, she also conducted research at Stanford University, Ecole Normale Superieure (Paris, France) and Aarhus University (Denmark). In 2003, she was awarded the CIMS Sandra Bleistein prize, for "notable achievement by a woman in Applied Mathematics or Computer Science." Dr. Fazio's research focuses on Cryptography and its applications to digital content protection. She has also done research on Zero-Knowledge, Multi-party Computation and Access Control. She is currently a postdoctoral fellow at IBM Almaden Research Center.
Title: Semantic Indexing and Retrieval of Video
Speaker: Marcel Worring and Cees Snoek, University of Amsterdam
Intended Audience: The tutorial is especially meant for people who are new to the field (introductory) or who have started in this direction (intermediate).
Overview:
The semantic gap between the low level information that can be derived from the visual data and the conceptual view the user has of the same data is a major bottleneck in video retrieval systems. It has dictated that solutions to image and video indexing could only be applied in narrow domains using specific concept detectors, e.g., “sunset” or “face”. This leads to lexica of at most 10-20 concepts. The use of multimodal indexing, advances in machine learning, and the availability of some large, annotated information sources, e.g., the TRECVID benchmark, has paved the way to increase lexicon size by orders of magnitude (now 100 concepts, in a few years 1,000). This brings it within reach of research in ontology engineering, i.e. creating and maintaining large, typically 10,000+ structured sets of shared concepts. When this goal is reached we could search for videos in our home collection or on the web based on their semantic content, we could develop semantic video editing tools, or develop tools that monitor various video sources and trigger alerts based on semantic events. This tutorial lays the foundation for these exciting new horizons. It will cover:
- Basic video analysis techniques
- Different methods for semantic video indexing.
- Interactive access to the data.
- Semantic retrieval
- Evaluation of indexing and interactive access in TRECVID
- The challenges ahead and how to meet them.
Speaker Bios:
Marcel Worring is Associate Professor of Computer Science at the University of Amsterdam, The Netherlands. He is the chair of the IAPR TC12 on Multimedia and Visual Information Systems. He is co-chair of the Conference on Image and Video Retrieval (CIVR 2007), co-organizer of the First International Workshop on Image Databases and Multi Media Search (1996), the International Conference on Visual Information Systems (1999) and the Conference on Multimedia & Expo (ICME, 2005). He is guest editor of the special issue on Semantic Image and Video Indexing in Broad domains for IEEE Transactions on Multimedia (2007). He is leading the successful MediaMill team which has been participating from the beginning of the TRECVID benchmark.
Cees Snoek received the M.Sc. degree in business information systems (2000) and the Ph.D. degree in computer science (2005) both from the University of Amsterdam, The Netherlands, where is currently a senior researcher at the Intelligent Systems Lab Amsterdam. He was a Visiting Scientist at Informedia, Carnegie Mellon University, USA in 2003. Dr. Snoek is a lead architect of the award-winning MediaMill Semantic Video Search Engine, which obtained state-of-the-art performance in recent NIST TRECVID evaluations. He is the local chair of the 2007 International Conference on Image and Video Retrieval in Amsterdam.