MDM/KDD2003 : The Fourth International Workshop on Multimedia Data Mining
( currently updating)
in conjunction with 

KDD-2003: 9th ACM SIGKDD International Conference on  Knowledge Discovery & Data Mining August 24 - 27, 2003, Washington, DC, USA (
(August 24th, 2003)

MDM/KDD2003 WORKSHOP THEME : Integrated Media Mining


The workshop will address issues specifically related to mining information from multi-modality, multi-source, multi-format data in an integrated way. Many analysis domains collect data from several sources, including static databases, streaming data, web pages, or conditionally collected data.  Data appear in multiple forms, including structured, numeric, free text, video, image, speech, or combinations of several types. Analysis in these domains requires combining of techniques and integrating methods. Examples include using Text Mining to generate structured features that can be further used by Data Mining in conjunction with existing structured data, or combining information mined from a photo image with text data, meta-data, and web links to other pages.
On the other hand, researchers in multimedia information systems, in the search for techniques for improving the indexing and retrieval of multimedia information are looking into new methods for discovering indexing information. Variety of techniques from machine learning, statistics, databases, knowledge acquisition, data visualization, image analysis, high performance computing, and knowledge-based systems, have been used mainly as a research handcraft activity. The development of multimedia databases and their query interfaces recall again the idea of incorporating multimedia data mining methods for dynamic indexing. The emerging international standard for multimedia content description (MPEG-7) promises to foster the collaboration in the field giving a uniform data representation.
The aim of the workshop is to contribute in finding suitable answers to the following questions:
- What are the theoretical foundations of multimedia data mining?
- What are the problems and applications where multimedia data mining can have severe impact?
- What are the advanced architectures of multimedia data mining systems?
- What are the specific issues raised in integrated patterns extraction from multimedia data and its components, including images, sound, video, and other non-structured data?
- What are suitable multimedia representations and formats that can help data mining in multimedia data?

The major topics of the workshop include but are not limited to:
- Integrated mining of different data formats (text, speech, video, structured, image, relational data)
- Combining mining results from different sources
- Integrated mining methods for eBusiness
- Combined mining methods for engineering and manufacturing
- Integrated mining for Homeland Security
- Mining of data streams combined with structure data
- Visual data mining of multi-format/ Multimedia data
- Multi-relational Data Mining. The focus is on mining data residing in relational databases.
- Visual data mining of multi-format/multimedia data.
- Theoretical frameworks for multimedia data mining.
- Multimedia data mining methods and algorithms.
- Multimedia data sampling and preprocessing. 
- Data visualization and sonification.
- Representation and reuse of discovered knowledge.
- Multimedia data descriptions languages and formats.
- Evaluation of interestingness, novelty and validity of results.
- Topic and event detection in multimedia data (including video).
- Extracting semantics from multimedia databases.
- Mining scientific multimedia data.
- Integrated data mining in multimedia information systems.
- Knowledge discovery in facial data.
- Man-machine interfaces for multimedia data mining.
- Complexity, efficiency and scalability of multimedia data mining algorithms.
- Data mining virtual communities and virtual worlds.
- Data mining in collaborative virtual environments and virtual reality systems.
- Visual and audio support for multimedia mining.
- Visual data mining of multimedia data.
- Multi-agent environments for concurrent mining of heterogeneous data.
- Real-time multimedia data mining systems.
- Using MPEG-4 and MPEG-7 standards for multimedia data mining.

We encourage submissions of greenhouse work, which present early stages of a cutting-edge research and development. Software demonstrations are welcome.


Valery A. Petrushin, Accenture Technology Labs161 N. Clark St.Chicago, IL 60089, USA, 
Anne Kao, The Boeing Company, P.O. Box 3707 MC 7L-43Seattle, WA 98124-2207, USA,


Mihael Ankerst, Boeing, Seattle, WA 98124-2207, USA, 
Simeon J. Simoff, Faculty of Information Technology University of Technology, Sydney, Australia,
Chabane Djeraba, IRIN, Nantes University, 2, Rue de la Houssiniere, 44322 Nantes Cedex, France, 
Latifur Khan, Department of Computer Science, Erik Jonsson School of Eng. And Comp. Sci.Box 830688, EC 31University of Texas at Dallas, Richardson, TX 75083, USA,
Rod Tjoelker, Boeing, Seattle, WA 98124-2207, USA, Marko GrobelnikJ. Stefan InstituteJamova 39, 1000

PROGRAM COMMITTEE (some members to be confirmed).

Dulce Ponceleon   IBM Almaden, USA
Wensheng Zhou   Hughes Research Lab, USA
Jim Maar    Magnify Research, USA
John Risch   Battelle, USA
Les Davis    ARDA, USA
Dunja Mladenic   J. Stefan Institute, Slovenia
Marko Grobelnik   J. Stefan Institute, Slovenia
Zhaohui Tang   Microsoft, USA 
Sundar Venkataraman  Rockwell Scientific Corporation, USA
Daniel Barbara  George Mason University, USA
Terry Caelli,   University of Alberta, Canada
Claude Chrisment   University of Toulouse, France
K. Slecuk Candan  Arizona State University, USA
Chitra Dorai   IBM Thomas J. Watson Research Center, USA
Alex Duffy   University of Strathclyde, UK
Max J. Egenhofer   University of Maine, USA
Jiawei Han   University of Illinois, USA
Howard J. Hamilton  University of Regina, Canada
Alexander G. Hauptmann Carnegie Mellon University, USA
Oktay Ibrahimov  Institute of Cybernetics, Azerbaijan
Wynne Hsu   National University of Singapore, Singapore
Erik Granum   Aalborg University, Denmark
William Grosky  University of Michigan,USA
Odej Kao    Technical University of Clausthal, Germany
Nik Kasabov  University of Ottago, New Zealand
Flip Korn   AT&T Laboratories, USA
Brian Lovell   University of Queensland, Australia
Mike Maybury  MITRE Corporation
Dennis McLeod  University of Southern California, USA
Gholamreza Nakhaeizadeh  DaimlerChrysler, Germany
Mario Nascimento  University of Alberta, Canada
Monique Noirhomme-Fraiture Institut Informatique, FUNDP, Belgium
Vincent Oria,   New Jersey Institute of technology, USA
Jian Pei    Simon Fraser University, Canada
Cyrus Shahabi  University of Southern California, USA
Simone Santini  University of California, San Diego, USA
John R. Smith  IBM T. J. Watson Research Center, USA
Paul Kennedy   University of Technology-Sydney, Australia
Duminda Wijesekera  George Mason University, USA
Aidong Zhang   State University of New York at Buffalo, USA


There is no restriction on the length of submissions. Contact author and email address should be specified. Electronic submission of papers in PDF, PS, RTF or Microsoft Word Document formats are preferable. The electronic submission will be organized via e-mail or a conference management system. 


Peer-reviewed papers, accepted for presentation at the workshop will be published in the workshop proceedings. Depending on the quality of the papers and presentations, an edited collection of longer contributions, is planned to be published either as a special issue of related journal or as an edited book.


Submissions Due: May 31 
Acceptance: June 20 
Camera ready copy: July 11


Registration for the workshop is free for the registrants of KDD-2003. Workshop attendance is limited to 60 participants only during one day.
Updated information on the workshop will be available at :

Received on Tuesday, 22 April 2003 02:51:59 UTC