CALL FOR CHAPTERS
Proposals Submission Deadline: 6/30/2007
Full Chapters Due: 11/15/2007


Semantic Mining Technologies for Multimedia Databases
A book edited by 
Dr. Dacheng TAO, The Hong Kong Polytechnic University, HK
Dr. Dong XU, Columbia University, USA
Dr. Xuelong LI, University of London, UK

Introduction

With the explosive growth of multimedia databases in terms of both
size and variety, effective indexing and searching techniques for
large-scale multimedia databases have become an urgent research topic
in recent years.

For data organization, the conventional approach is based on key words
or text description of a multimedia datum. However to give all data
text annotation is tedious and almost impossible for people to
capture. Moreover, the text description is also not enough to
precisely describe a multimedia datum. For example, it is unrealistic
to utilize words to describe a music clip; an image says more than a
thousand words; and keywords-based video shot description cannot
characterize the contents for a specific user. Therefore, it is
important to utilize the content based approach (CbA) to mine the
semantic information of a multimedia datum.

The last ten years have witnessed very significant contributions of
CbA in semantics targeting for multimedia data organization. CbA means
that the data organization, including retrieval and indexing, utilizes
the contents of the data themselves, rather than keywords provided by
human. Therefore, the contents of a datum could be obtained from
techniques in statistics, computer vision, and signal processing. For
example, Markov random fields could be applied for image modeling;
spatial-temporal analysis is important for video shot representation;
and the Mel frequency cepstral coefficient has been shown to be the
most effective method for audio signal classification.

Apart from the conventional approaches mentioned above, machine
learning also plays an indispensable role in current semantic mining
tasks, e.g., random sampling techniques and support vector machine for
human computer interaction, manifold learning and subspace methods for
data visualization, discriminant analysis for feature selection, and
classification trees for indexing.

The Overall Objective of the Book

Recently, multimedia searching and management became very popular
because of the demanding applications and the competition among
several important companies. It is hot in both academia and industry,
while so far, there is no existing book, which covers from basic
knowledge to state-of-the-art techniques for multimedia searching and
management.

The major contributions of this book are: 1) collecting and seeking
the recent, most important research results in semantic mining for
multimedia data organization, 2) guiding new researchers a
comprehensive review on the state-of-the-art techniques for different
tasks for multimedia database management, and 3) providing
technologists and programmers important algorithms for multimedia
system construction.

The Target Audience
The objective of this book is to provide an introduction to the most
recent research techniques in multimedia semantic mining research for
new researchers, so that they can go step by step into this field. As
a result, they can follow the right way according to their specific
applications. The book should serve as an important reference for
researchers in multimedia, a handbook for research students, and a
repository for multimedia technologists.

Recommended topics include, but are not limited to, the following:

Part I (Multimedia Data Representation)


Global features for image representation

Local features for image representation

Audio segmentation representation

Video shot representation

Part II (Human Computer Interaction)


Support vector machine base relevance feedback

Feature selection in relevance feedback

Semi-supervised learning for performance enhancement

Active learning for human computer interaction

Clustering based relevance feedback

Multi-class classification in relevance feedback

Part III (Data Visualization)


Manifold learning for data visualization

Graph techniques for data visualization

Intelligent User Interface

3D visualization for data organization

Markov random fields for data visualization

Part IV (Database Indexing)


Point Access Methods, including trees

Dynamic indexing structure

Dimensionality reduction

Semantic classification for indexing
Part V (Applications)

SUBMISSION PROCEDURE
Prospective contributors are invited to submit on or before June 30,
2007, a 2-5 page manuscript proposal clearly explaining the mission
and concerns of the proposed chapter(s). Authors of accepted proposals
will be notified by July 31, 2007 about the status of their proposals
and sent chapter organizational guidelines. Full chapters are expected
to be submitted by November 15, 2008. All submitted chapters will be
reviewed on a double-blind review basis. The book is scheduled to be
published by IGI Global (formerly Idea Group, Inc),
http://www.igi-pub.com/, publisher of IGI Publishing (formerly Idea
Group Publishing), Information Science Publishing, IRM Press,
CyberTech Publishing and Information Science Reference (formerly Idea
Group Reference) imprints.

Inquiries and submissions can be forwarded electronically (Word document) or by mail to:

Dr Dacheng TAO
PQ702, 7/F, Building P
Department of Computing
The Hong Kong Polytechnic University
Hung Hom, Kowloon, Hong Kong.
Phone: +852 2764-2528
Fax: +852 2764-2528
csdct@comp.polyu.edu.hk
(cc: dacheng.tao@gmail.com)

Dr Dong XU
1300 S. W. Mudd, 500 West 120th Street,
New York, NY 10027, USA.
Phone: +1 (212) 854-7477
Fax : +1 (212) 854-7477
dongxu@ee.columbia.edu
(cc: dongxudongxu@gmail.com)

Dr Xuelong LI
Birkbeck, School of Computer Science and Information Systems
University of London
Malet Street, London WC1E 7HX, U.K.
Phone: +44 (20) 7631-6796
Fax: +44 (20) 7631-6727
xuelong_li@ieee.org