Workshop on Multimedia Discovery and Mining

- Call for Papers -

To be held at ECML/PKDD-2003, The 14th European Conference on Machine Learning (ECML) and the 7th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD), Dubrovnik, Croatia

Call for papers on the following topics is open until June 13, 2003.

Below are submission guidelines, attendance information, important dates and organization details.

Workshop Description

The increasing availability of various data sources in electronic form and the increasing capability of the data mining algorithms is advancing research in the area of multimedia mining. This is strongly supported by the variety of potential applications, including arts, design, education, entertainment industry, etc.

Data mining algorithms are able to process large databases and offer the chance to handle not only text but also multimedia data. Systems for handling multimedia data are able to extract information from various media such as text, speech, still images and video, index it, enable sophisticated search and retrieval, modeling, analysis, personalized information delivery, etc. The result may be used to retrieve multimedia data from databases or may be added to multimedia streams as added value. An emerging task is to select novel or interesting contents buried in multimedia streams or databases.

For Machine Learning and Knowledge Discovery, multimedia mining brings new challenges as data is extremely large in size, uses different modalities and has a rich internal structure. Required technologies are speech recognition, text mining, video and image analysis, information retrieval, and summarization.

Topics of interest

Addressing the above issues requires an awareness of the research achievements in various research and cross-disciplinary research efforts. Particular topics of interest for the workshop include but are not limited to:

• Theoretical framework for multimedia data mining;
• Complexity, and scalability of multimedia mining algorithms;
• Classification of multimedia documents;
• Clustering and proximity of multimedia documents;
• Detection of novel or interesting documents;
• Multimedia data mining methods and algorithms;
• Preprocessing and representation of multimedia data;
• Multimedia data representation and formats;
• Event or topic detection in multimedia data;
• Selection of novel or interesting documents;
• Learning using different data sources and modalities;
• Extraction and representation of semantic relations for multimedia;
• Working multimedia mining systems.

Submission Guidelines

Submissions should be sent by June 13, 2003, in the electronic form as a PDF or PostScript file to Gerhard.Paass@ais.fraunhofer.de, Subject: MultimediaMining-2003 workshop submission paper.

The papers should be formatted as for the main ECML/PKDD-2003 conference submissions. This is according to the Springer-Verlag Lecture Notes in Artificial Intelligence guidelines. Authors instructions and style files can be downloaded. The maximum length of papers is 12 pages.

Submitted papers will be reviewed by referees from the Program Committee. Accepted papers will be published in the working notes provided by ECML/PKDD-2003 and possibly the selected papers will be published as a Springer series book. The authors will be notified about the acceptance or rejection of their papers by July 4, 2003. Camera-ready versions of the papers are due July 11, 2003.

Attendance

Attendance is not limited to the paper authors. We strongly encourage interested researchers from related areas to attend the workshop. The intended audience for the workshop involves researchers and practitioners interested in mining different type of multimedia data. Firstly, we would like to attract potential users working in the media industry (e.g. broadcasters), which can clarify user demands on multimedia mining. Then we aim for experts on the technical background and standards (e.g. MPEG7) of multimedia. Finally data mining and machine learning researchers interested in audio, image, text and multimedia mining are expected to contribute to the workshop.

Important Dates

Organization

Dunja Mladenic
J.Stefan Institute, Jamova 39, 1000 Ljubljana, Slovenia
Dunja.Mladenic@ijs.si

Gerhard Paaß
Fraunhofer Institute Autonomous Intelligent Systems, Schloss Birlinghoven 53754 St. Augustin, Germany,
Gerhard.Paass@ais.fraunhofer.de

Program Committee

• Marie-Aude Aufaure, INRIA, Domaine de Voluceau, France
• Alberto Del Bimbo, Università degli Studi di Firenze, Italy
• Joachim Diederich, The University of Queensland, Australia
• Chabane Djeraba, University of Nantes, France,
• Stefan Eickeler, Fraunhofer Institute of Media Communication, Germany
• Gareth Jones, University of Exeter, UK
• Thorsten Joachims, Cornell University, USA
• Odej Kao, University of Paderborn, Germany
• Gholamreza Nakhaeizadeh , Daimler-Benz AG, Germany
• Simeon Simoff, University of Technology Sydney, Australia

This Workshop is partially supported by the European FP5 FET project called: "European Knowledge Discovery Network of Excellence".

Supported by EU project No. IST-2001-33086 Copyright © KDNet 2003 Web Design © Caatoosee