The following tutorials will be given on topical research for VIE'08:
Statistical Design of Quantitative Vision Systems
Abstract : This tutorial is aimed at providing a general introduction to the use of
probability in the design of vision modiules and its use in
computational vision systems. Emphasis is placed on basic concepts and
quantitative use. This includes hypothesis testing, likelihood and Bayes
theorem. The importance of understanding data quality and the evaluation
of algorithm performance is addressed via the use of measurement error,
error propagation, covariance estimation and Monte Carlo techniques.
The limitations of established methods will be explained, where
necessary, in order to provide an in depth understanding of the use of
quantitative probability as a scientific tool. Taken together, these
methods form a framework for the design of computer vision algorithms,
leading to a better understanding of what constitutes appropriate
solutions to vision analysis tasks.
It is intended that by the end of the tutorial the student will have
sufficient familiarity with the basic concepts that they will be able to
begin to recognise genuine novelty in published work in this area, as
apposed to re-invention of existing statistical methods. They will also
understand the appropriate use of these techniques. This in turn should
facilitate, not only higher standards in their own work, but better
reviewing of conference and journal publications for the next generation
of vision researchers.
Intended Audience: The tutorial is designed for an audience with
intermediate level mathematical skills, while the coverage of
probability concepts ranges from introductory to intermediate. The
material is therefore suitable for students and researchers whishing to
gain a better understanding of the scientific basis for algorithm
Dr. Neil Thacker
University of Manchester, UK
Neil Thacker has a background training in experimental physics
followed by 20 years experience in the area of computer vision and image
analysis. During this time he has worked in areas as diverse as;
computer vision, neural networks and pattern recognition, medical image
analysis, and VLSI hardware design. He has published in excess of 200
(journal and conference) papers. This work is now distributed from the
TINA open source computer vision pages www.tina-vision.net in the form
of a three volume thesis on Visual Intelligence.
| [Back to Top] |
Mr. Don Braggins
Machine Vision Systems Consultancy
& Director, UKIVA
Don Braggins has been an independent consultant in Machine Vision since
1983. He helped to found the UK Industrial Vision Association in 1992
and the European Machine Vision Association in 2003. In 1991 the grade
of Fellow of SPIE was conferred on him, and in 2005 he was asked to take
on the role of Associate Editor for Machine Vision and Pattern
Recognition for SPIE's peer-reviewed journal Optical Engineering.
| [Back to Top] |
Sports Video Content Analysis and Applications
Abstract: In recent years extensive research efforts have been devoted to sports video
content analysis and applications due to their wide viewer-ship and high commercial
potentials. Technologies and prototypes have been developed to automatically or
semi-automatically analyze sports video content, extract semantic events or
highlights, intelligently adapt, enhance and personalize the content to meet users'
preferences and network/device capabilities. Many applications have been developed
and used in broadcasting video enhancement such as multi-camera based 3D virtual
sports events, virtual ads insertion for sports video, and motion analysis systems for
sports training, etc. The aim of this tutorial is to provide a brief overview of general
video content analysis techniques and a comprehensive overview of the technical
achievements in the research area of sports video analysis and applications. We first
cover feature extraction methods, which include low-level feature extraction, midlevel
representation creation and high-level semantics detection in sports videos.
Next, we present the state of the art in sports video analysis from the following three
aspects: structure analysis, event detection, content adaptation and enhancement. We
also address the issues concerning test data preparations and performance evaluations
for sports video analysis systems. Based on the current technologies used in sports
video analysis and the demands from real-world applications, future promising
directions and research challenges are discussed at the end of the tutorial.
Intended Audience: This tutorial is intended for educators, researchers, engineers,
students and people interested in gaining an overall understanding of video content
analysis and sports video analysis and applications. The audience is required to have
basic understanding of image, video, audio and text media and preliminary knowledge
of signal processing and machine learning.
Dr. Changsheng Xu
Institute for Infocomm Research, Singapore
Prof. Qingming Huang
Chinese Academy of Sciences, China
Changsheng Xu received the Ph.D. degree from Tsinghua University, Beijing, China
in 1996. From 1996 to 1998, he was with the National Lab of Pattern Recognition,
Institute of Automation, Chinese Academy of Sciences, Beijing, China. He joined the
Institute for Infocomm Research (I2R), Singapore, in March 1998. His research
interests include multimedia content analysis, indexing and retrieval, digital
watermarking, computer vision and pattern recognition. He published over 150 papers
in those areas. He is an IEEE Senior Member and Member of ACM. He is an
Associate Editor of ACM/Springer Multimedia Systems Journal. He will serve as
Program Co-Chair of ACM Multimedia 2009, Short Paper Co-Chair of ACM
Multimedia 2008, General Co-Chair of 2008 Pacific-Rim Conference on Multimedia
(PCM2008) and 2007 Asia-Pacific Workshop on Visual Information Processing
(VIP2007), Program Co-Chair of VIP2006, Industry Track Chair and Area Chair of
2007 International Conference on Multimedia Modeling (MMM2007). He also served
as Technical Program Committee Member of major international multimedia
conferences, including ACM Multimedia Conference, International Conference on
Multimedia & Expo, Pacific-Rim Conference on Multimedia, and International
Conference on Multimedia Modeling.
Qingming Huang received the Ph.D. degree in computer science from Harbin
Institute of Technology, Harbin, China in 1994. He was a Postdoctoral Fellow in
National University of Singapore from 1995 to 1996, and worked in Institute for
Infocomm Research, Singapore as Member Research Staff from 1996 to 2002.
Currently, he is a professor in Graduate School of Chinese Academy of Sciences. He
has published over 80 scientific papers. His current research areas are image
processing, video analysis, video coding, and pattern recognition.
| [Back to Top] |
Building Semantic Detectors and Semantic Spaces for Concept-based Video Search
Abstract: Enabling semantic-based video retrieval has been one of the long-term goals in multimedia computing. Traditional content-based approaches of deriving semantics purely from low-level multimedia features have proven their limitation in conquering the so-called "semantic gap". Modern approaches enable the semantic search by pooling a set of concepts and forming a semantic space to facilitate the high-level understanding of user queries and low-level features. The search method is generally referred to as concept-based video search (CBVS).
In this tutorial, I will present two main components of CBVS: semantic detectors and semantic spaces . The techniques of building large-scale semantic concept detectors and utilizing the detectors for modeling semantic spaces will be introduced. In the first part, I will describe the development of VIREO-374 which is a publicly available detector set developed by exploiting the bag-of-visual-words representation. Under this representation, the detection of local interest points, choices of local features, design of word weighting and vocabulary size, stop word removal, feature selection, and impact of visual word linguistics will be fully discussed. The major differences between the "bag-of-words" video retrieval and text retrieval will be highlighted.
In the second part of the tutorial, I will present the effective building of semantic spaces with the available set of semantic detectors. The development will take into account the factors such as ontological relatedness of detectors, coverage of semantic space, observability and diversity of concepts, and reliability of detectors in videos. The techniques of utilizing the developed semantic spaces for query disambiguation, multi-modality fusion and video search will also be discussed.
Finally, the practical and empirical insights of building semantic detectors/spaces for large-scale video search will be demonstrated based on the TRECVID benchmark evaluations. The tutorial will be concluded by showing the challenges of video search in large-scale multimedia database.
Intended Audience: Researchers, postgraduate students and engineers in multimedia computing, information retrieval, video/image/audio processing, and machine learning, from both academia and industries. The level will be from intermediate to advanced. The audiences are expected to have the basic knowledge in multimedia and information retrieval.
Dr. Chong-Wah Ngo
Department of Computer Science
City University of Hong Kong
Chong-Wah Ngo received his PhD in Computer Science from the Hong Kong University of Science and Technology (HKUST). He received his MSc and BSc, both in computer engineering, from Nanyang Technological University (NTU) of Singapore. Before joining City University of Hong Kong in 2002, he was with Beckman Institute of University of Illinois in Urbana Champion. He was also a visiting researcher in Microsoft Research Asia (MSRA). His recent research interests include large-scale multimedia information retrieval and video computing. He has been serving as technical program committee in various major multimedia-related conferences including ACM Multimedia (MM), International Conf. on Image and Video Retrieval (CIVR) and International Conf. on Multimedia and Expo (ICME). He is the leader of video retrieval group (VIREO): http://vireo.cs.cityu.edu.hk/ in CityU. He also serves as the chairman of ACM (Hong Kong Chapter) recently.
| [Back to Top] |