简介: |
Large image archives present very valuable applications with high impact in biometrics, medical archives, remote sensing archives, and biological applications. This talk addresses three open problems in an integrated content-based image retrieval (CBIR) system. Such problems are (i) distance learning for similarity estimation, (ii) learning of high dimensional data with small samples, and (iii) bridging the semantic gap.
To address these open problems, we proposed (i) a dynamic framework for distance learning and feature selection; (ii) an adaptive subspace learning framework for robust and accurate modeling of image data with small samples; and (iii) a semantic manifold learning framework for bridging the semantic gap. Our proposed methods are tested on Corel and other image datasets and showed superior results compared to other state-of-the-art methods. Though we tested the proposed algorithms on image databases, it should be noted the proposed approaches are generic and can be applied to many other similarity search applications such as biometrics-based person recognition and gene-expression based microarray analysis.
In the end of the talk, I will also discuss current trends and potential directions in Multimedia Information Retrieval.
BIO:
Dr. Qi Tian is an Assistant Professor in the Department of Computer Science, the University of Texas at San Antonio (UTSA). He received his Ph.D . in Electrical and Computer Engineering in 2002 from the University of Illinois at Urbana-Champaign (UIUC), and his B.E. in Electronic Engineering in 1992 from Tsinghua University, China.
He was a Visiting Professor at the UIUC-MIAS Center (2007), a Visiting Researcher at MSRA Web Mining and Search Group (2007), and a Visiting Professor in NEC Laboratories of America, Inc.(2003). He was a Summer Intern (2000, 2001) and Visiting Researcher (2001) in MERL, Cambridge, MA. His research interests include multimedia information retrieval, computer vision, and pattern recognition. He was the co-author of a Best Student Paper in IEEE ICASSP 2006. He was Program Chairs of VIP (2007), IMAI (2007), MIR (2005), SPIE Internet Multimedia Management Systems (2005), and Multimedia Systems and Applications VIII, SPIE's International Symposium on Optics East (2006), and Special Session Chair, Track Chair and Publicity Chair in ACM Multimedia, ICME, CIVR, PCM, and TPC and Session Chairs in many IEEE and ACM conferences. He was the Guest Editor of Computer Vision and Image Understanding for a Special Issue on Similarity Matching in Computer Vision and the Guest Editor of IEEE Transactions on Multimedia for a Special Issue on Integration of Context and Content for Multimedia Management and Multimedia and is an Editor of Journal of Multimedia. He is a Senior Member of IEEE (2003) and a Member of ACM (2004).
|
