LEADER 05372nam 2200649Ia 450 001 9910877728103321 005 20200520144314.0 010 $a1-280-24183-7 010 $a9786610241835 010 $a0-470-33918-7 010 $a0-470-01261-7 010 $a0-470-85763-3 035 $a(CKB)1000000000356083 035 $a(EBL)241144 035 $a(OCoLC)475955541 035 $a(SSID)ssj0000206529 035 $a(PQKBManifestationID)11166798 035 $a(PQKBTitleCode)TC0000206529 035 $a(PQKBWorkID)10214601 035 $a(PQKB)10561931 035 $a(MiAaPQ)EBC241144 035 $a(EXLCZ)991000000000356083 100 $a20040330d2005 uy 0 101 0 $aeng 135 $aur|n|---||||| 181 $ctxt 182 $cc 183 $acr 200 10$aMultimedia content and the semantic Web $emethods, standards and tools /$fedited by Giorgos Stamou and Stefanos Kollias 210 $aChichester, England ;$aHoboken, NJ $cWiley$dc2005 215 $a1 online resource (416 p.) 300 $aDescription based upon print version of record. 311 $a0-470-85753-6 320 $aIncludes bibliographical references and index. 327 $aMultimedia Content and the Semantic Web; Contents; List of Contributors; Foreword - Rudi Studer; Foreword - A. Murat Tekalp; Introduction; Part One: Knowledge and Multimedia; 1 Multimedia Content Description in MPEG-7 and MPEG-21; 1.1 Multimedia Content Description; 1.2 MPEG-7: Multimedia Content Description Interface; 1.3 MPEG-21: Multimedia Framework; 1.4 Final Remarks; Acknowledgments; References; 2 Ontology Representation and Querying for Realizing Semantics-Driven Applications; 2.1 Introduction; 2.2 Requirements; 2.3 Ontology Representation; 2.4 Ontology Querying; 2.5 Implementation 327 $a2.6 Related Work2.7 Conclusion; References; 3 Adding Multimedia to the Semantic Web: Building and Applying an MPEG-7 Ontology; 3.1 Introduction; 3.2 Building an MPEG-7 Ontology; 3.3 Inferring Semantic Descriptions of Multimedia Content; 3.4 Semantic Querying and Presentation; 3.5 Conclusions; References; Appendix A; Appendix B MPEG-7 Description of a Fuel Cell; Appendix C OME Description of Fuel Cell Image; Appendix D FUSION Description of a Fuel Cell Image; Appendix E XML Schema for FUSION; 4 A Fuzzy Knowledge-Based System for Multimedia Applications; 4.1 Introduction 327 $a4.2 Knowledge Base Formalization4.3 Fuzzy Propositional Rules Inference Engine; 4.4 Demonstration; 4.5 Conclusion and Future Work; References; Part Two: Multimedia Content Analysis; 5 Structure Identification in an Audiovisual Document; 5.1 Introduction; 5.2 Shot Segmentation; 5.3 Evaluation of Shot-Segmentation Algorithms; 5.4 Formal Description of the Video Editing Work; 5.5 Macrosegmentation; 5.6 Conclusion; 5.7 Acknowledgement; References; 6 Object-Based Video Indexing; 6.1 Introduction; 6.2 MPEG-7 as a Normalized Framework for Object-Based Indexing of Video Content 327 $a6.3 Spatio-Temporal Segmentation of Video for Object Extraction6.4 Rough Indexing Paradigm for Object-Based Indexing of Compressed Content; 6.5 Conclusion; References; 7 Automatic Extraction and Analysis of Visual Objects Information; 7.1 Introduction; 7.2 Overview of the Proposed Model; 7.3 Region-Based Representation of Images: The Binary Partition Tree; 7.4 Perceptual Modelling of a Semantic Class; 7.5 Structural Modelling of a Semantic Class; 7.6 Conclusions; Acknowledgements; References; 8 Mining the Semantics of Visual Concepts and Context; 8.1 Introduction 327 $a8.2 Modelling Concepts: Support Vector Machines for Multiject Models8.3 Modelling Context: A Graphical Multinet Model for Learning and Enforcing Context; 8.4 Experimental Set-up and Results; 8.5 Concluding Remarks; Acknowledgement; References; 9 Machine Learning in Multimedia; 9.1 Introduction; 9.2 Graphical Models and Multimedia Understanding; 9.3 Learning Classifiers with Labelled and Unlabelled Data; 9.4 Examples of Graphical Models for Multimedia Understanding and Computer Vision; 9.5 Conclusions; References; Part Three: Multimedia Content Management Systems and the Semantic Web 327 $a10 Semantic Web Applications 330 $aThe emerging idea of the semantic web is based on the maximum automation of the complete knowledge lifecycle processes: knowledge representation, acquisition, adaptation, reasoning, sharing and use. Text-based based browsers involve a costly information-retrieval process: descriptions are inherently subjective and usage is often confined to the specific application domain for which the descriptions were created. Automatic extracted audiovisual features are, in general, more objective, domain-independent and can be native to the audiovisual content. This book seeks to draw together in one c 606 $aMultimedia systems 606 $aSemantic Web 606 $aInformation storage and retrieval systems 615 0$aMultimedia systems. 615 0$aSemantic Web. 615 0$aInformation storage and retrieval systems. 676 $a006.7 700 $aStamou$b Giorgos$01760078 701 $aKollias$b Stefanos$01756189 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9910877728103321 996 $aMultimedia content and the semantic Web$94198859 997 $aUNINA