Read more
Media understanding is the science/art of identifying semantic structures in digital media objects such as audio, biosignals, images, text and videos. This volume continues the work started in "Fundamental Media Understanding" (atpress, 2011). It covers methods employed in professional multimedia information retrieval such as audiovisual feature transformations based on discrete transforms, wavelet transforms, local interest points methods such as SIFT and MSER, flow-based motion description, information filtering by singular value decomposition, feature selection, principles of human learning and machine learning, categorization by risk minimization and kernel-based learning, dynamic optimization, mixture models, and evaluation based on cross validation and receiver operating characteristic curves. In contrast to related publications, this book does not focus on one type of media but considers all the above-named as well as a few others. The author endeavors to identify similarities between the methods employed in audio retrieval, image understanding, text summarization and many other research domains. It turns out that a number of significant parallels do exist. Structuring the methods along common criteria and discussing their similarities and differences breaks the ground for a new research discipline: true computational understanding of multimedia content.
About the author
Horst Eidenberger is associate professor of applied computer science at the Vienna University of Technology. He received his Doctor degree in 2000 from the University of Vienna and finished his Habilitation in 2005. He has published several books and more than 70 scientific papers in journals and at international conferences. His research interests include content understanding, machine learning and signal processing.
