Data Management for Multimedia Retrieval

Multimedia data require specialized management techniques because the representations of color, time, semantic concepts, and other underlying information can be drastically different from one another. The user’s subjective judgment can also have significant impact on what data or features are relevant in a given context. These factors affect both the performance of the retrieval algorithms and their effectiveness. This textbook on multimedia data management techniques offers a unified perspective on retrieval efficiency and effectiveness. It provides a comprehensive treatment, from basic to advanced concepts, that will be useful to readers of different levels, from advanced undergraduate and graduate students to researchers and to professionals. After introducing models for multimedia data (images, video, audio, text, and web) and for their features, such as color, texture, shape, and time, the book presents data structures and algorithms that help store, index, cluster, classify, and access common data representations. The authors also introduce techniques, such as relevance feedback and collaborative filtering, for bridging the “semantic gap” and present the applications of these to emerging topics, including web and social networking.

• Focuses in a balanced manner on both 'data structures/databases' and 'mining/retrieval' aspects of multimedia data management. Most other books in the area cover only one or the other
• Organized in terms of basic data models (vectors, strings, trees, graphs, and fuzzy/probabilistic representations) that cover a large spectrum of media types instead of being limited to one or two special media types (such as images)
• Each topic is covered from basic to advanced concepts; thus the book can be of interest to readers of different levels

About the Authors

K. Selçuk Candan is a Professor of Computer Science and Engineering at Arizona State University. He received his Ph.D. in 1997 from the University of Maryland at College Park. Candan has authored more than 120 conference and journal articles, 9 patents, and many book chapters and, among his other scientific positions, has served as program chair for ACM Multimedia Conference '08, the Int. Conference on Image and Video Retrieval (CIVR'10), and as an organizing committee member for ACM SIG Management of Data Conference (SIGMOD'06). Since 2005, he has also served as an editorial board member for the Very Large Databases (VLDB) journal.

Maria Luisa Sapino is a Professor in the Department of Computer Science at the University of Torino, where she also earned her Ph.D. There she leads the multimedia and heterogeneous data management group. Her scientific contributions include more than 60 conference and journal papers; her services as chair, organizer, and program committee member in major conferences and workshops on multimedia; and her collaborations with industrial research labs, including the RAI-Crit (Center for Research and Technological Innovation) and Telecom Italia Lab, on multimedia technologies.