Massive image collections are increasingly available on the Web. These collections often incorporate complementary nonvisual data such as text descriptions, comments, user ratings and tags. These additional data modalities may provide a semantic complement to the images' visual content, which could improve the performance of different image mining, retrieval and content analysis tasks. Non-negative Matrix Factorization (NMF) is a method that formed the basis of the winning solution in the Netflix Prize movie recommmendation competition. This talk will present an NMF-based approach that can be used to generate multimodal image representations that integrate visual features and text information in the same space. The NMF approach, developed in a collaboration between researchers at University of Louisville and National University of Colombia, works by computing a set of latent factors that correlate multimodal data in the same representation space. Outperforming the latent semantic spaces generated by Singular Value Decomposition, the NMF representation can be used in several applications, in particular, image retrieval and automated image annotation.
Olfa Nasraoui is the founding Director of the Knowledge Discovery and Web Mining Laboratory, at the University of Louisville, where she is also an Associate Professor of Computer Engineering and Computer Science and the Endowed Chair of e-Commerce. She received the Ph.D. degree in Computer Engineering
and Computer Science from the University of Missouri, Columbia, in 1999. From 2000 to 2004, she was an Assistant Professor at the University of Memphis. Her
research interests include data mining, Web mining, stream data mining, and computational intelligence. She is a member of IEEE, IEEE Women in Engineering, and in the last 10 years, has been active in the SIGKDD community, notably by organizing the WebKDD workshop on Web Mining and by serving as Vice-Chair on several leading Data Mining conferences, including KDD 2009, ICDM 2009-2010, SDM 2010, and WI 2009. She is a recipient of a US National Science Foundation Faculty Early Career Development (CAREER) Award, and a Best Paper Award in the Artificial Neural Networks in Engineering Conference. She has published more than 130 publications, and acquired close to $2M in
funding as Principal Investigator from NSF, NASA and other agencies, for data mining research, ranging from mining massive Web clickstreams, text streams and peer-to-peer network data exchanges to mining images of the solar corona.
