[Elsnet-list] SAMT 2006 Workshops

publicity at samt2006.org publicity at samt2006.org
Mon Jul 24 17:59:38 CEST 2006

[Apologies for cross-postings. Please forward this mail to anyone interested.]


First international conference on Semantics And digital Media Technology (SAMT 2006) 
Former European Workshop on the Integration of knowledge, semantic and digital Media Technologies (EWIMT)
December 6-8, 2006 - Athens, Greece

SAMT 2006 workshops provide an informal setting for participants to discuss technical issues, exchange research ideas, and develop a community in the field of the Multimedia and the Semantic Web. They encourage discussions on user requirements for multimedia access and how semantic web and multimedia technologies can be deployed together and operationalized in real world scenarios. SAMT 2006 features four workshops:

* Multimedia Analysis and Uncertainty Representation (MAUR 2006)
* Semantic-enhanced Multimedia Presentation Systems (SEMPS 2006)
* Knowledge Markup and Semantic Annotation (SemAnnot 2006)
* Learning the Semantics of Audio Signals (LSAS 2006)

Benefiting from small-group information exchange and discussion, workshops are intended to be genuine interactive events and not mini-conferences. Workshop attendees must pay the SAMT 2006 workshop registration fee, as well as the conference registration fee.

Half day workshop

* Giorgos Stoilos, NTUA, Greece
* Jeff Z. Pan, University of Aberdeen, UK
* Umberto Straccia, ISTI/CNR, Italy

Multimedia processing like analysis and retrieval are inherently difficult tasks. In order to assist multimedia processing algorithms and applications, researchers are proposing ways to enrich multimedia algorithms with knowledge representational formalisms. In this way the multimedia processing techniques could take advantage of formal representation and automated reasoning methods.

On the other hand multimedia processing algorithms are usually facing a huge amount of uncertain and imprecise knowledge. Hence knowledge representational formalisms must be equipped with mechanisms that are able to cope with such type of knowledge. The last couple of years a quite impressive number of uncertainty handling formalism have been developed, like fuzzy and probabilistic Description Logics, fuzzy, possibilistic and probabilistic Logic Programming languages etc. Such logical formalisms combine expressive power and decidable reasoning techniques. The use of such formalisms in multimedia applications would greatly benefit these applications and will provide new research results.

This workshop invites contributions on all topics related to knowledge based multimedia analysis and retrieval with a special emphasis on techniques that are using uncertainty handling mechanisms.

Half day workshop

* Lyndon Nixon, University of Berlin, Germany
* Ansgar Scherp, University of Oldenburg, Germany
* Susanne Boll, University of Oldenburg, Germany
* Lynda Hardman, CWI, Netherlands

It is almost 10 years since Intelligent Multimedia Presentation Systems (IMMPS) were formalised in a Standard Reference Model. Even then the role of knowledge bases and reasoning was recognised as a vital element for the adaptive and automated production of multimedia presentations. This decade has seen the rise of the Web as a platform for multimedia delivery and of Semantic Web research to enable the expression and manipulation of knowledge over the Web. 

The 1st International Workshop on Semantic-enhanced Multimedia Presentation Systems (SEMPS) aims to explore how Semantic Web technologies can be applied to Multimedia Presentation Systems in order to support Internet-based delivery of user and context personalised, rich media-based Web presentations and new innovative types of online service.

Half day workshop

* Siegfried Handschuh, DERI, Ireland
* Thierry Declerck, DKKI, Germany
* Elisabeth Andre, University of Augsburg, Germany

The main topic to be discussed at this issue of the SemAnnot Workshop is dedicated to the semantic indexing and searching of multimedia (and multilingual) data. As it is well-known, it is difficult to process completely the content of multimedia data, even with technologies based on a combination of image processing, machine vision, natural language processing, and speech recognition. Therefore, semantic annotation as a means of supplementing automatic multimedia processing is one of the promising methodologies to describe content semantically. Ideally the outcome of this Workshop should provide for some contributions to standardisation efforts on the semantic annotation for multimedia.

The workshop intends to bring together researchers and practitioners from research areas such as the Multimedia Analysis, Semantic Web, Knowledge Acquisition, and Human Language Technology, among others, to discuss various aspects of knowledge markup and semantic annotation in an interdisciplinary way. Further, following an in depth discussion that started at the former edition of the Workshop, SemAnnot 2006 will establish a forum on the evaluation of (automatic) semantic annotation (considering text, speech transcripts and audio-video content). To be discussed is the availability or the creation of appropriated corpora, joint Semantic Web application scenarios with common ontologies supporting an evaluation campaign for (automated) semantic annotation for knowledge mark up and ontology population, evaluation metrics etc.

Full day workshop

* Andreas Nürnberger, University of Magdeburg, Germany
* Sebastian Stober, University of Magdeburg, Germnay
* George Tzanetakis, University of Victoria, Canada
* Pedro Cano, Universitat Pompeu Fabra, Spain

Introduction of techniques for compressing and streaming of audio data in recent time has significantly changed the way music is consumed and archived. Personal music collections may nowadays comprise ten-thousands of music titles. Even mobile devices are able to store some thousands of songs. But these magnitudes are nothing compared to the vast amount of music data digitally available on the internet. Several features have been proposed to describe music on a low, signal-processing based level. Some of these have already been incorporated as description schemes for annotation of audio data into the MPEG-7 standard. However, in contrast to text documents that can be sufficiently well represented by statistics about the contained terms, audio data seems far too complex to be described by statistics on signals alone. Additionally, such a representation does only allow query-by-example.

Learning a mapping between audio features and contextual interpretations would be the key to solve this problem, enabling a user to formulate a query in a way that is close to his way of describing music contents, e.g. using natural language or at least combinations of terms. For this task, models describing how music is perceived are needed, as well as methods for the extraction, analysis and representation of linguistic descriptions of music.

The goals of the workshop are to intensify the exchange of ideas between the different research communities involved, to provide an overview of current activities in this area and to point out connections between them. The workshop focuses especially on researchers that are working on semantics, description, representation and understanding of music.


* Raphael Troncy <Raphael.Troncy at cwi.nl>, CWI, The Netherlands
* Vassilis Tzouvaras <tzouvaras at image.ntua.gr>, National Technical University of Athens, Greece

* http://www.cordis.lu/ist/ -- Information Society Technologies (IST), European Commission
* http://www.eurasip.org/   -- European Association for Signal, Speech and Image Processing (EURASIP)
* http://www.cost292.org/   -- European Cooperation in the field of Scientific and Technical Research, COST 292 Action - Semantic Multimodal Analysis of Digital Media
* http://www.iee.org/oncomms/pn/visualinformation/index.cfm -- Institution of Engineering and Technology (IET), Visual Information Engineering Professional Network (VIE PN)
* http://kspace.qmul.net/   -- K-Space Network of Excellence - Knowledge Space of Semantics inference for automatic annotation and retrieval of multimedia content
* http://muscle-noe.org/    -- Muscle Network of Excellence - Multimedia Understanding through Semantics, Computation and Learning
* http://www.atc.gr/home.aspx?Page=home&lang=EN -- Athens Technology Center (ATC)
* http://www.dw-world.de/   -- Deutsche Welle
* http://www.mesh-ip.eu/    -- Mesh Integrated Project

You are receiving this email because you have participated in a previous EWIMT or related event. If you would like to be removed from the SAMT publicity email list, please reply to this message with the word 'REMOVE' in the SUBJECT LINE.  This email should be addressed to: publicity at samt2006.org. You will be removed from this list when we receive your reply.

More information about the Elsnet-list mailing list