Advanced Query Processing on Large Multimedia Databases
by Dr. Jialie SHEN
| Speaker: |  |
Date: Time: Venue: |
23 November 2006 (Thursday)
|
Dr. Jialie SHEN Research Fellow Information Retrieval Research Group University of Glasgow |
We look forward to seeing you at this research seminar. |
Abstract
Having been applied for wide range of purposes such as entertainment and education, multimedia data pose huge challenges for informative retrieval, knowledge discovery and database management. Multimedia data could be huge, contains rich high level semantic meaning in nature and has much more complex structure in comparison to alphanumeric data. Consequently, to efficiently manage and explore multimedia information under a real life application environment, there is an urgent need for technological advances to facilitate the advanced query processing on large multimedia databases.
In the talk, the problem of multimedia information retrieval and data management will be discussed in three aspects: how to generate content descriptor, how to construct scalable indexing structure and how to evaluate retrieval system performance with less computational cost. Particularly, he will present several approaches recently developed: 1) fast nonlinear based method to generate small and effective multimedia object signature 2) the SMIF approach - a novel indexing framework for large multimedia databases with superior scalability 3) the statistical based approach to derive accurate estimations on performance evaluation results. The potential extensions of the above methods will be also addressed.
Biography
Jialie SHEN received the Ph.D. degree in Computing Science from University of New South Wales (UNSW), Australia, in 2006. He worked as an associate lecturer in UNSW from 2002 to 2005 and a part-time lecturer in University of New England in 2005-06 at Australia. He is currently a research fellow in information retrieval research group at University of Glasgow, UK. His research interests can be summarized as developing effective and efficient data analysis and retrieval techniques for novel data intensive applications. Particularly, he is currently interested in various techniques of multimedia data mining, multimedia information retrieval and database systems. His research results have been published in ACM SIGIR, ACM SIGMOD, ACM Multimedia, ICDE, CIKM and IEEE Transactions on Multimedia. He has served as a reviewer for a number of major journals and conferences such as ICDE, IEEE TMM, IEEE TKDE and ACM TOIS. He is also a member of ACM SIGMOD and SIGIR.