Multimedia Retrieval

Based on more than 10 years of teaching experience, Blanken and his coeditors have assembled all the topics that should be covered in advanced undergraduate or graduate courses on multimedia retrieval and multimedia databases. The single chapters of this textbook explain the general architecture of multimedia information retrieval systems and cover various metadata languages such as Dublin Core, RDF, or MPEG. The authors emphasize high-level features and show how these are used in mathematical models to support the retrieval process. For each chapter, there’s detail on further reading, and additional exercises and teaching material is available online.

At its very core multimedia information retrieval means the process of searching for and finding multimedia documents; the corresponding research field is concerned with building the best possible multimedia search engines. The intriguing bit here is that the query itself can be a multimedia excerpt: For example, when you walk around in an unknown place and stumble across an interesting landmark, would it not be great if you could just take a picture with your mobile phone and send it to a service that finds a similar picture in a database and tells you more about the building -- and about its significance, for that matter? This book goes further by examining the full matrix of a variety of query modes versus document types. How do you retrieve a music piece by humming? What if you want to find news video clips on forest fires using a still image? The text discusses underlying techniques and common approaches to facilitate multimedia search engines from metadata driven retrieval, via piggy-back text retrieval where automated processes create text surrogates for multimedia, automated image annotation and content-based retrieval. The latter is studied in great depth looking at features and distances, and how to effectively combine them for efficient retrieval, to a point where the readers have the ingredients and recipe in their hands for building their own multimedia search engines. Supporting users in their resource discovery mission when hunting for multimedia material is not a technological indexing problem alone. We look at interactive ways of engaging with repositories through browsing and relevance feedback, roping in geographical context, and providing visual summaries for videos. The book concludes with an overview of state-of-the-art research projects in the area of multimedia information retrieval, which gives an indication of the research and development trends and, thereby, a glimpse of the future world. Table of Contents: What is Multimedia Information Retrieval? / Basic Multimedia Search Technologies / Content-based Retrieval in Depth / Added Services / Multimedia Information Retrieval Research / Summary

Foreword by Karen Spärck Jones Intelligent multimedia information retrieval lies at the intersection of artificial intelligence, information retrieval, human-computer interaction, and multimedia computing. Its systems enable users to create, process, summarize, present, interact with, and organize information within and across different media such as text, speech, graphics, imagery, and video. These systems go beyond traditional hypermedia and hypertext environments to analyze and generate media, and support intelligent interaction with or via multiple media. The chapters of this volume, which grew out of the 1995 International Joint Conference on Artificial Intelligence Workshop on Intelligent Multimedia Information Retrieval, span a broad range of topics. The book is organized into seven sections: Content-Based Retrieval of Imagery, Content-Based Retrieval of Graphics and Audio, Content-Based Retrieval of Video, Speech and Language Processing for Video Retrieval, Architectures and Tools, Intelligent Hypermedia Retrieval, and Empirical Evaluations. Contributors Robert Adams, Phillipe Aigrain, Jonathan Ashley, Thom Blum, Shih-Fu Chang, Mei C. Chuah, W. Bruce Croft, Byron Dom, Ann Doubleday, Florence Dubois, Josef Fink, Myron Flickner, Jonathan Foote, Brian Frew, Monika Gorkani, Morgan Green, James Griffioen, Jon Alte Gulla, Jim Hafner, Qian Hang, Matt Hare, Alexander G. Hauptman, Stacie Hibino, Helmut Horacek, David House, Takafumi Inoue, Philippe Joly, Gareth Jones, Karen Spärck Jones, Douglas Keislaer, Stephen Kerpedjiev, Alfred Kobsa, Denis Lee, Véronique Longueville, Chien Yong Low, R. Manmatha, Inderjeet Mani, Mark T. Maybury, Bernard Mérialdo, Adrian Müller, Wayne Niblac, Andreas Nill, Alex Pentland, Dragutin Petkovic, Steven F. Roth, Neil C. Rowe, Elke A. Rundensteiner, Harpreet Sawhney, John R. Smith, Stephen W. Smoliar, David Steele, Adelheit Stein, Oliviero Stock, Carlo Strapparava, Alistair Sutcliffe, Atshushi Takeshita, Kazuo Tanaka, Ulrich Thiel, Michele Ryan, Julita Vassileva, James Wheaton, Michael J. Witbrock, Erling Wold, JianHua Wu, Peter Yanker, Rajendra Yavatkar, Steven J. Young, Massimo Zancanaro, HongJiang Zhang

Multimedia data require specialised management techniques because the representations of colour, time, semantic concepts, and other underlying information can be drastically different from one another. This textbook on multimedia data management techniques gives 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 colour, 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.

Several works on multimedia storage appear in literature today, but very little if any, have been devoted to handling long duration video retrieval, over large scale networks. Distributed retrieval of multimedia documents, especially the long duration documents, is an imperative step in rendering high-quality, high-fidelity, and cost-effective services for network service providers. Distributed Multimedia Retrieval Strategies for Large Scale Networked Systems presents an up-to-date research status in the domain of distributed video retrieval. This professional book will include several different techniques that are in place for long duration video retrieval. An experimentally tested technology under the JINI platform, demonstrates a practical working system which serves as a feasibility study, as well as the first step in realizing such a technology.

This book constitutes the thoroughly refereed post-proceedings of the 4th International Workshop on Adaptive Multimedia Retrieval, AMR 2006, held in Geneva, Switzerland in July 2006. The papers cover ontology-based retrieval and annotation, ranking and similarity measurements, music information retrieval, visual modeling, adaptive retrieval, structuring multimedia, as well as user integration and profiling.

Multimedia Information Retrieval: Content-Based Information Retrieval from Large Text and Audio Databases addresses the future need for sophisticated search techniques that will be required to find relevant information in large digital data repositories, such as digital libraries and other multimedia databases. Because of the dramatically increasing amount of multimedia data available, there is a growing need for new search techniques that provide not only fewer bits, but also the most relevant bits, to those searching for multimedia digital data. This book serves to bridge the gap between classic ranking of text documents and modern information retrieval where composite multimedia documents are searched for relevant information. Multimedia Information Retrieval: Content-Based Information Retrieval from Large Text and Audio Databases begins to pave the way for speech retrieval; only recently has the search for information in speech recordings become feasible. This book provides the necessary introduction to speech recognition while discussing probabilistic retrieval and text retrieval, key topics in classic information retrieval. The book then discusses speech retrieval, which is even more challenging than retrieving text documents because word boundaries are difficult to detect, and recognition errors affect the retrieval effectiveness. This book also addresses the problem of integrating information retrieval and database functions, since there is an increasing need for retrieving information from frequently changing data collections which are organized and managed by a database system. Multimedia Information Retrieval: Content-Based Information Retrieval from Large Text and Audio Databases serves as an excellent reference source and may be used as a text for advanced courses on the topic.

Everything you ever wanted to know about multimedia retrieval and management. This comprehensive book offers a full picture of the cutting-edge technologies necessary for a profound introduction to the field. Leading experts also cover a broad range of practical applications.