Call for Papers

Advances in computing performance, multimedia compression and communication technologies have led to a rapid expansion of digital film and video archives. Applications such as digital TV broadcast, video-on-demand, distance learning and film archiving generate and use large collections of video data. Home digital videos are also becoming increasingly popular due to the widespread use of digital cameras. However, video databases still lack the techniques for efficient indexing, search and retrieval. The biggest challenge in the current content-based video and image retrieval systems is the semantic gap - the gap between the high-level semantic concepts used by humans to describe visual content and query video databases, and the extracted low level visual features used by the system to index the video content. There has been a growing interest in applying machine learning techniques for building more effective and efficient content-based video retrieval systems and overcoming the semantic gap.

This special session aims at bringing together researchers working across fields such as machine learning, statistics, signal processing, pattern recognition, artificial intelligence, to share their experience and brainstorm possible solutions for a future generation of intelligent image and video processing systems. We hereby invite the submission of high-quality, original and unpublished research papers. Topics of interest include but are not limited to:

• New algorithms for clustering and classification of image and video data
• Feature extraction and selection
• Advanced descriptors and similarity measures
• Multidimensional scaling techniques
• Image segmentation
• Video segmentation and summarization
• Probabilistic modelling of semantics
• Multimedia content analysis and understanding
• Learning and relevance feedback in retrieval
• Web-based image and video retrieval systems
• Evaluation of image/video retrieval systems
• Mining of image and video data

Important Dates

Paper Submission

Please follow the instructions given at the KES'2005 site to format your paper. Note the page limit is SEVEN pages in LNCS/LNAI format. All submissions must be sent electronically to the session chair at 'dadeng at computer.org'. At least one of the authors must register and attend to present his/her paper at KES 2005.

Session Chairs

Da Deng
Department of Information Science
University of Otago
PO Box 56, Dunedin, New Zealand
Phone: +64 (3) 479 8090, fax: +64 (3) 479 8311

Irena Koprinska
School of Information Technologies
University of Sydney, Sydney, NSW 2006, Australia
phone: +61 (2) 9351 3764, fax: +61 (2) 9351 3838