{"product_id":"multimedia-semantics-isbn-9780470747001","title":"Multimedia Semantics","description":"\u003cb\u003eIn this book, the authors present the latest research results in the multimedia and semantic web communities, bridging the \"Semantic Gap\"\u003c\/b\u003e  \u003cp\u003eThis book explains, collects and reports on the latest research results that aim at narrowing the so-called multimedia \"Semantic Gap\": the large disparity between descriptions of multimedia content that can be computed automatically, and the richness and subjectivity of semantics in user queries and human interpretations of audiovisual media. Addressing the grand challenge posed by the \"Semantic Gap\" requires a multi-disciplinary approach (computer science, computer vision and signal processing, cognitive science, web science, etc.) and this is reflected in recent research in this area. In addition, the book targets an interdisciplinary community, and in particular the Multimedia and the Semantic Web communities. Finally, the authors provide both the fundamental knowledge and the latest state-of-the-art results from both communities with the goal of making the knowledge of one community available to the other.\u003c\/p\u003e \u003cp\u003e\u003ci\u003eKey Features:\u003c\/i\u003e\u003c\/p\u003e \u003cul\u003e \u003cli\u003ePresents state-of-the art research results in multimedia semantics: multimedia analysis, metadata standards and multimedia knowledge representation, semantic interaction with multimedia\u003c\/li\u003e \u003cli\u003eContains real industrial problems exemplified by user case scenarios\u003c\/li\u003e \u003cli\u003eOffers an insight into various standardisation bodies including W3C, IPTC and ISO MPEG\u003c\/li\u003e \u003cli\u003eContains contributions from academic and industrial communities from Europe, USA and Asia\u003c\/li\u003e \u003cli\u003eIncludes an accompanying website containing user cases, datasets, and software mentioned in the book, as well as links to the K-Space NoE and the SMaRT society web sites (\u003ca href=\"http:\/\/www.multimediasemantics.com\/\"\u003ehttp:\/\/www.multimediasemantics.com\/\u003c\/a\u003e)\u003c\/li\u003e \u003c\/ul\u003e \u003cp\u003eThis book will be a valuable reference for academic and industry researchers \/practitioners in multimedia, computational intelligence and computer science fields. Graduate students, project leaders, and consultants will also find this book of interest.\u003c\/p\u003e  \u003cb\u003eForeword xi\u003c\/b\u003e  \u003cp\u003e\u003cb\u003eList of Figures xiii\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eList of Tables xvii\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eList of Contributors xix\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003e1 Introduction 1\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eRaphaël Troncy, Benoit Huet and Simon Schenk\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003e2 Use Case Scenarios 7\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eWerner Bailer, Susanne Boll, Oscar Celma, Michael Hausenblas and Yves Raimond\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e2.1 Photo Use Case 8\u003c\/p\u003e \u003cp\u003e\u003ci\u003e2.1.1 Motivating Examples\u003c\/i\u003e 8\u003c\/p\u003e \u003cp\u003e\u003ci\u003e2.1.2 Semantic Description of Photos Today\u003c\/i\u003e 9\u003c\/p\u003e \u003cp\u003e\u003ci\u003e2.1.3 Services We Need for Photo Collections\u003c\/i\u003e 10\u003c\/p\u003e \u003cp\u003e2.2 Music Use Case 10\u003c\/p\u003e \u003cp\u003e\u003ci\u003e2.2.1 Semantic Description of Music Assets\u003c\/i\u003e 11\u003c\/p\u003e \u003cp\u003e\u003ci\u003e2.2.2 Music Recommendation and Discovery\u003c\/i\u003e 12\u003c\/p\u003e \u003cp\u003e\u003ci\u003e2.2.3 Management of Personal Music Collections\u003c\/i\u003e 13\u003c\/p\u003e \u003cp\u003e2.3 Annotation in Professional Media Production and Archiving 14\u003c\/p\u003e \u003cp\u003e\u003ci\u003e2.3.1 Motivating Examples\u003c\/i\u003e 15\u003c\/p\u003e \u003cp\u003e\u003ci\u003e2.3.2 Requirements for Content Annotation\u003c\/i\u003e 17\u003c\/p\u003e \u003cp\u003e2.4 Discussion 18\u003c\/p\u003e \u003cp\u003eAcknowledgements 19\u003c\/p\u003e \u003cp\u003e\u003cb\u003e3 Canonical Processes of Semantically Annotated Media Production 21\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eLynda Hardman, Z¡êljko Obrenovic´ and Frank Nack\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e3.1 Canonical Processes 22\u003c\/p\u003e \u003cp\u003e\u003ci\u003e3.1.1 Premeditate\u003c\/i\u003e 23\u003c\/p\u003e \u003cp\u003e\u003ci\u003e3.1.2 Create Media Asset\u003c\/i\u003e 23\u003c\/p\u003e \u003cp\u003e\u003ci\u003e3.1.3 Annotate\u003c\/i\u003e 23\u003c\/p\u003e \u003cp\u003e\u003ci\u003e3.1.4 Package\u003c\/i\u003e 24\u003c\/p\u003e \u003cp\u003e\u003ci\u003e3.1.5 Query\u003c\/i\u003e 24\u003c\/p\u003e \u003cp\u003e\u003ci\u003e3.1.6 Construct Message\u003c\/i\u003e 25\u003c\/p\u003e \u003cp\u003e\u003ci\u003e3.1.7 Organize\u003c\/i\u003e 25\u003c\/p\u003e \u003cp\u003e\u003ci\u003e3.1.8 Publish\u003c\/i\u003e 26\u003c\/p\u003e \u003cp\u003e\u003ci\u003e3.1.9 Distribute\u003c\/i\u003e 26\u003c\/p\u003e \u003cp\u003e3.2 Example Systems 27\u003c\/p\u003e \u003cp\u003e\u003ci\u003e3.2.1 CeWe Color Photo Book\u003c\/i\u003e 27\u003c\/p\u003e \u003cp\u003e\u003ci\u003e3.2.2 SenseCam\u003c\/i\u003e 29\u003c\/p\u003e \u003cp\u003e3.3 Conclusion and Future Work 33\u003c\/p\u003e \u003cp\u003e\u003cb\u003e4 Feature Extraction for Multimedia Analysis 35\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eRachid Benmokhtar, Benoit Huet, Gaël Richard and Slim Essid\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e4.1 Low-Level Feature Extraction 36\u003c\/p\u003e \u003cp\u003e\u003ci\u003e4.1.1 What Are Relevant Low-Level Features?\u003c\/i\u003e 36\u003c\/p\u003e \u003cp\u003e\u003ci\u003e4.1.2 Visual Descriptors\u003c\/i\u003e 36\u003c\/p\u003e \u003cp\u003e\u003ci\u003e4.1.3 Audio Descriptors\u003c\/i\u003e 45\u003c\/p\u003e \u003cp\u003e4.2 Feature Fusion and Multi-modality 54\u003c\/p\u003e \u003cp\u003e\u003ci\u003e4.2.1 Feature Normalization\u003c\/i\u003e 54\u003c\/p\u003e \u003cp\u003e\u003ci\u003e4.2.2 Homogeneous Fusion\u003c\/i\u003e 55\u003c\/p\u003e \u003cp\u003e\u003ci\u003e4.2.3 Cross-modal Fusion\u003c\/i\u003e 56\u003c\/p\u003e \u003cp\u003e4.3 Conclusion 58\u003c\/p\u003e \u003cp\u003e\u003cb\u003e5 Machine Learning Techniques for Multimedia Analysis 59\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eSlim Essid, Marine Campedel, Gaël Richard, Tomas Piatrik, Rachid Benmokhtar and Benoit Huet\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e5.1 Feature Selection 61\u003c\/p\u003e \u003cp\u003e\u003ci\u003e5.1.1 Selection Criteria\u003c\/i\u003e 61\u003c\/p\u003e \u003cp\u003e\u003ci\u003e5.1.2 Subset Search\u003c\/i\u003e 62\u003c\/p\u003e \u003cp\u003e\u003ci\u003e5.1.3 Feature Ranking\u003c\/i\u003e 63\u003c\/p\u003e \u003cp\u003e\u003ci\u003e5.1.4 A Supervised Algorithm Example\u003c\/i\u003e 63\u003c\/p\u003e \u003cp\u003e5.2 Classification 65\u003c\/p\u003e \u003cp\u003e\u003ci\u003e5.2.1 Historical Classification Algorithms\u003c\/i\u003e 65\u003c\/p\u003e \u003cp\u003e\u003ci\u003e5.2.2 Kernel Methods\u003c\/i\u003e 67\u003c\/p\u003e \u003cp\u003e\u003ci\u003e5.2.3 Classifying Sequences\u003c\/i\u003e 71\u003c\/p\u003e \u003cp\u003e\u003ci\u003e5.2.4 Biologically Inspired Machine Learning Techniques\u003c\/i\u003e 73\u003c\/p\u003e \u003cp\u003e5.3 Classifier Fusion 75\u003c\/p\u003e \u003cp\u003e\u003ci\u003e5.3.1 Introduction\u003c\/i\u003e 75\u003c\/p\u003e \u003cp\u003e\u003ci\u003e5.3.2 Non-trainable Combiners\u003c\/i\u003e 75\u003c\/p\u003e \u003cp\u003e\u003ci\u003e5.3.3 Trainable Combiners\u003c\/i\u003e 76\u003c\/p\u003e \u003cp\u003e\u003ci\u003e5.3.4 Combination of Weak Classifiers\u003c\/i\u003e 77\u003c\/p\u003e \u003cp\u003e\u003ci\u003e5.3.5 Evidence Theory\u003c\/i\u003e 78\u003c\/p\u003e \u003cp\u003e\u003ci\u003e5.3.6 Consensual Clustering\u003c\/i\u003e 78\u003c\/p\u003e \u003cp\u003e\u003ci\u003e5.3.7 Classifier Fusion Properties\u003c\/i\u003e 80\u003c\/p\u003e \u003cp\u003e5.4 Conclusion 80\u003c\/p\u003e \u003cp\u003e\u003cb\u003e6 Semantic Web Basics 81\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eEyal Oren and Simon Schenk\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e6.1 The Semantic Web 82\u003c\/p\u003e \u003cp\u003e6.2 RDF 83\u003c\/p\u003e \u003cp\u003e\u003ci\u003e6.2.1 RDF Graphs\u003c\/i\u003e 86\u003c\/p\u003e \u003cp\u003e\u003ci\u003e6.2.2 Named Graphs\u003c\/i\u003e 87\u003c\/p\u003e \u003cp\u003e\u003ci\u003e6.2.3 RDF Semantics\u003c\/i\u003e 88\u003c\/p\u003e \u003cp\u003e6.3 RDF Schema 90\u003c\/p\u003e \u003cp\u003e6.4 Data Models 93\u003c\/p\u003e \u003cp\u003e6.5 Linked Data Principles 94\u003c\/p\u003e \u003cp\u003e\u003ci\u003e6.5.1 Dereferencing Using Basic Web Look-up\u003c\/i\u003e 95\u003c\/p\u003e \u003cp\u003e\u003ci\u003e6.5.2 Dereferencing Using HTTP 303 Redirects\u003c\/i\u003e 95\u003c\/p\u003e \u003cp\u003e6.6 Development Practicalities 96\u003c\/p\u003e \u003cp\u003e\u003ci\u003e6.6.1 Data Stores\u003c\/i\u003e 97\u003c\/p\u003e \u003cp\u003e\u003ci\u003e6.6.2 Toolkits\u003c\/i\u003e 97\u003c\/p\u003e \u003cp\u003e\u003cb\u003e7 Semantic Web Languages 99\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eAntoine Isaac, Simon Schenk and Ansgar Scherp\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e7.1 The Need for Ontologies on the Semantic Web 100\u003c\/p\u003e \u003cp\u003e7.2 Representing Ontological Knowledge Using OWL 100\u003c\/p\u003e \u003cp\u003e\u003ci\u003e7.2.1 OWL Constructs and OWL Syntax\u003c\/i\u003e 100\u003c\/p\u003e \u003cp\u003e\u003ci\u003e7.2.2 The Formal Semantics of OWL and its Different Layers\u003c\/i\u003e 102\u003c\/p\u003e \u003cp\u003e\u003ci\u003e7.2.3 Reasoning Tasks\u003c\/i\u003e 106\u003c\/p\u003e \u003cp\u003e\u003ci\u003e7.2.4 OWL Flavors\u003c\/i\u003e 107\u003c\/p\u003e \u003cp\u003e\u003ci\u003e7.2.5 Beyond OWL\u003c\/i\u003e 107\u003c\/p\u003e \u003cp\u003e7.3 A Language to Represent Simple Conceptual Vocabularies: SKOS 108\u003c\/p\u003e \u003cp\u003e\u003ci\u003e7.3.1 Ontologies versus Knowledge Organization Systems\u003c\/i\u003e 108\u003c\/p\u003e \u003cp\u003e\u003ci\u003e7.3.2 Representing Concept Schemes Using SKOS\u003c\/i\u003e 109\u003c\/p\u003e \u003cp\u003e\u003ci\u003e7.3.3 Characterizing Concepts beyond SKOS\u003c\/i\u003e 111\u003c\/p\u003e \u003cp\u003e\u003ci\u003e7.3.4 Using SKOS Concept Schemes on the Semantic Web\u003c\/i\u003e 112\u003c\/p\u003e \u003cp\u003e7.4 Querying on the Semantic Web 113\u003c\/p\u003e \u003cp\u003e\u003ci\u003e7.4.1 Syntax\u003c\/i\u003e 113\u003c\/p\u003e \u003cp\u003e\u003ci\u003e7.4.2 Semantics\u003c\/i\u003e 118\u003c\/p\u003e \u003cp\u003e\u003ci\u003e7.4.3 Default Negation in SPARQL\u003c\/i\u003e 123\u003c\/p\u003e \u003cp\u003e\u003ci\u003e7.4.4 Well-Formed Queries\u003c\/i\u003e 124\u003c\/p\u003e \u003cp\u003e\u003ci\u003e7.4.5 Querying for Multimedia Metadata\u003c\/i\u003e 124\u003c\/p\u003e \u003cp\u003e\u003ci\u003e7.4.6 Partitioning Datasets\u003c\/i\u003e 126\u003c\/p\u003e \u003cp\u003e\u003ci\u003e7.4.7 Related Work\u003c\/i\u003e 127\u003c\/p\u003e \u003cp\u003e\u003cb\u003e8 Multimedia Metadata Standards 129\u003cbr\u003e \u003c\/b\u003e\u003ci\u003ePeter Schallauer, Werner Bailer, Raphaël Troncy and Florian Kaiser\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e8.1 Selected Standards 130\u003c\/p\u003e \u003cp\u003e\u003ci\u003e8.1.1 MPEG-7\u003c\/i\u003e 130\u003c\/p\u003e \u003cp\u003e\u003ci\u003e8.1.2 EBU P_Meta\u003c\/i\u003e 132\u003c\/p\u003e \u003cp\u003e\u003ci\u003e8.1.3 SMPTE Metadata Standards\u003c\/i\u003e 133\u003c\/p\u003e \u003cp\u003e\u003ci\u003e8.1.4 Dublin Core\u003c\/i\u003e 133\u003c\/p\u003e \u003cp\u003e\u003ci\u003e8.1.5 TV-Anytime\u003c\/i\u003e 134\u003c\/p\u003e \u003cp\u003e\u003ci\u003e8.1.6 METS and VRA\u003c\/i\u003e 134\u003c\/p\u003e \u003cp\u003e\u003ci\u003e8.1.7 MPEG-21\u003c\/i\u003e 135\u003c\/p\u003e \u003cp\u003e\u003ci\u003e8.1.8 XMP, IPTC in XMP\u003c\/i\u003e 135\u003c\/p\u003e \u003cp\u003e\u003ci\u003e8.1.9 EXIF\u003c\/i\u003e 136\u003c\/p\u003e \u003cp\u003e\u003ci\u003e8.1.10 DIG35\u003c\/i\u003e 137\u003c\/p\u003e \u003cp\u003e\u003ci\u003e8.1.11 ID3\/MP3\u003c\/i\u003e 137\u003c\/p\u003e \u003cp\u003e\u003ci\u003e8.1.12 NewsML G2 and rNews\u003c\/i\u003e 138\u003c\/p\u003e \u003cp\u003e\u003ci\u003e8.1.13 W3C Ontology for Media Resources\u003c\/i\u003e 138\u003c\/p\u003e \u003cp\u003e\u003ci\u003e8.1.14 EBUCore\u003c\/i\u003e 139\u003c\/p\u003e \u003cp\u003e8.2 Comparison 140\u003c\/p\u003e \u003cp\u003e8.3 Conclusion 143\u003c\/p\u003e \u003cp\u003e\u003cb\u003e9 The Core Ontology for Multimedia 145\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eThomas Franz, Raphaël Troncy and Miroslav Vacura\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e9.1 Introduction 145\u003c\/p\u003e \u003cp\u003e9.2 A Multimedia Presentation for Granddad 146\u003c\/p\u003e \u003cp\u003e9.3 Related Work 149\u003c\/p\u003e \u003cp\u003e9.4 Requirements for Designing a Multimedia Ontology 150\u003c\/p\u003e \u003cp\u003e9.5 A Formal Representation for MPEG-7 150\u003c\/p\u003e \u003cp\u003e\u003ci\u003e9.5.1 DOLCE as Modeling Basis\u003c\/i\u003e 151\u003c\/p\u003e \u003cp\u003e\u003ci\u003e9.5.2 Multimedia Patterns\u003c\/i\u003e 151\u003c\/p\u003e \u003cp\u003e\u003ci\u003e9.5.3 Basic Patterns\u003c\/i\u003e 155\u003c\/p\u003e \u003cp\u003e\u003ci\u003e9.5.4 Comparison with Requirements\u003c\/i\u003e 157\u003c\/p\u003e \u003cp\u003e9.6 Granddad’s Presentation Explained by COMM 157\u003c\/p\u003e \u003cp\u003e9.7 Lessons Learned 159\u003c\/p\u003e \u003cp\u003e9.8 Conclusion 160\u003c\/p\u003e \u003cp\u003e\u003cb\u003e10 Knowledge-Driven Segmentation and Classification 163\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eThanos Athanasiadis, Phivos Mylonas, Georgios Th. Papadopoulos, Vasileios Mezaris, Yannis Avrithis, Ioannis Kompatsiaris and Michael G. Strintzis\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e10.1 Related Work 164\u003c\/p\u003e \u003cp\u003e10.2 Semantic Image Segmentation 165\u003c\/p\u003e \u003cp\u003e\u003ci\u003e10.2.1 Graph Representation of an Image\u003c\/i\u003e 165\u003c\/p\u003e \u003cp\u003e\u003ci\u003e10.2.2 Image Graph Initialization\u003c\/i\u003e 165\u003c\/p\u003e \u003cp\u003e\u003ci\u003e10.2.3 Semantic Region Growing\u003c\/i\u003e 167\u003c\/p\u003e \u003cp\u003e10.3 Using Contextual Knowledge to Aid Visual Analysis 170\u003c\/p\u003e \u003cp\u003e\u003ci\u003e10.3.1 Contextual Knowledge Formulation\u003c\/i\u003e 170\u003c\/p\u003e \u003cp\u003e\u003ci\u003e10.3.2 Contextual Relevance\u003c\/i\u003e 173\u003c\/p\u003e \u003cp\u003e10.4 Spatial Context and Optimization 177\u003c\/p\u003e \u003cp\u003e\u003ci\u003e10.4.1 Introduction\u003c\/i\u003e 177\u003c\/p\u003e \u003cp\u003e\u003ci\u003e10.4.2 Low-Level Visual Information Processing\u003c\/i\u003e 177\u003c\/p\u003e \u003cp\u003e\u003ci\u003e10.4.3 Initial Region-Concept Association\u003c\/i\u003e 178\u003c\/p\u003e \u003cp\u003e\u003ci\u003e10.4.4 Final Region-Concept Association\u003c\/i\u003e 179\u003c\/p\u003e \u003cp\u003e10.5 Conclusions 181\u003c\/p\u003e \u003cp\u003e\u003cb\u003e11 Reasoning for Multimedia Analysis 183\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eNikolaos Simou, Giorgos Stoilos, Carsten Saathoff, Jan Nemrava, Vojt¡ech Sv´atek, Petr Berka and Vassilis Tzouvaras\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e11.1 Fuzzy DL Reasoning 184\u003c\/p\u003e \u003cp\u003e\u003ci\u003e11.1.1 The Fuzzy DL f-SHIN\u003c\/i\u003e 184\u003c\/p\u003e \u003cp\u003e\u003ci\u003e11.1.2 The Tableaux Algorithm\u003c\/i\u003e 185\u003c\/p\u003e \u003cp\u003e\u003ci\u003e11.1.3 The FiRE Fuzzy Reasoning Engine\u003c\/i\u003e 187\u003c\/p\u003e \u003cp\u003e11.2 Spatial Features for Image Region Labeling 192\u003c\/p\u003e \u003cp\u003e\u003ci\u003e11.2.1 Fuzzy Constraint Satisfaction Problems\u003c\/i\u003e 192\u003c\/p\u003e \u003cp\u003e\u003ci\u003e11.2.2 Exploiting Spatial Features Using Fuzzy\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e\u003ci\u003eConstraint Reasoning\u003c\/i\u003e 193\u003c\/p\u003e \u003cp\u003e11.3 Fuzzy Rule Based Reasoning Engine 196\u003c\/p\u003e \u003cp\u003e11.4 Reasoning over Resources Complementary to Audiovisual Streams 201\u003c\/p\u003e \u003cp\u003e\u003cb\u003e12 Multi-Modal Analysis for Content Structuring and Event Detection 205\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eNoel E. O’Connor, David A. Sadlier, Bart Lehane, Andrew Salway, Jan Nemrava and Paul Buitelaar\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e12.1 Moving Beyond Shots for Extracting Semantics 206\u003c\/p\u003e \u003cp\u003e12.2 A Multi-Modal Approach 207\u003c\/p\u003e \u003cp\u003e12.3 Case Studies 207\u003c\/p\u003e \u003cp\u003e12.4 Case Study 1: Field Sports 208\u003c\/p\u003e \u003cp\u003e\u003ci\u003e12.4.1 Content Structuring\u003c\/i\u003e 208\u003c\/p\u003e \u003cp\u003e\u003ci\u003e12.4.2 Concept Detection Leveraging Complementary Text Sources\u003c\/i\u003e 213\u003c\/p\u003e \u003cp\u003e12.5 Case Study 2: Fictional Content 214\u003c\/p\u003e \u003cp\u003e\u003ci\u003e12.5.1 Content Structuring\u003c\/i\u003e 215\u003c\/p\u003e \u003cp\u003e\u003ci\u003e12.5.2 Concept Detection Leveraging Audio Description\u003c\/i\u003e 219\u003c\/p\u003e \u003cp\u003e12.6 Conclusions and Future Work 221\u003c\/p\u003e \u003cp\u003e\u003cb\u003e13 Multimedia Annotation Tools 223\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eCarsten Saathoff, Krishna Chandramouli, Werner Bailer, Peter Schallauer and Raphaël Troncy\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e13.1 State of the Art 224\u003c\/p\u003e \u003cp\u003e13.2 SVAT: Professional Video Annotation 225\u003c\/p\u003e \u003cp\u003e\u003ci\u003e13.2.1 User Interface\u003c\/i\u003e 225\u003c\/p\u003e \u003cp\u003e\u003ci\u003e13.2.2 Semantic Annotation\u003c\/i\u003e 228\u003c\/p\u003e \u003cp\u003e13.3 KAT: Semi-automatic, Semantic Annotation of Multimedia Content 229\u003c\/p\u003e \u003cp\u003e\u003ci\u003e13.3.1 History\u003c\/i\u003e 231\u003c\/p\u003e \u003cp\u003e\u003ci\u003e13.3.2 Architecture\u003c\/i\u003e 232\u003c\/p\u003e \u003cp\u003e\u003ci\u003e13.3.3 Default Plugins\u003c\/i\u003e 234\u003c\/p\u003e \u003cp\u003e\u003ci\u003e13.3.4 Using COMM as an Underlying Model: Issues and Solutions\u003c\/i\u003e 234\u003c\/p\u003e \u003cp\u003e\u003ci\u003e13.3.5 Semi-automatic Annotation: An Example\u003c\/i\u003e 237\u003c\/p\u003e \u003cp\u003e13.4 Conclusions 239\u003c\/p\u003e \u003cp\u003e\u003cb\u003e14 Information Organization Issues in Multimedia Retrieval Using Low-Level Features 241\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eFrank Hopfgartner, Reede Ren, Thierry Urruty and Joemon M. Jose\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e14.1 Efficient Multimedia Indexing Structures 242\u003c\/p\u003e \u003cp\u003e\u003ci\u003e14.1.1 An Efficient Access Structure for Multimedia Data\u003c\/i\u003e 243\u003c\/p\u003e \u003cp\u003e\u003ci\u003e14.1.2 Experimental Results\u003c\/i\u003e 245\u003c\/p\u003e \u003cp\u003e\u003ci\u003e14.1.3 Conclusion\u003c\/i\u003e 249\u003c\/p\u003e \u003cp\u003e14.2 Feature Term Based Index 249\u003c\/p\u003e \u003cp\u003e\u003ci\u003e14.2.1 Feature Terms\u003c\/i\u003e 250\u003c\/p\u003e \u003cp\u003e\u003ci\u003e14.2.2 Feature Term Distribution\u003c\/i\u003e 251\u003c\/p\u003e \u003cp\u003e\u003ci\u003e14.2.3 Feature Term Extraction\u003c\/i\u003e 252\u003c\/p\u003e \u003cp\u003e\u003ci\u003e14.2.4 Feature Dimension Selection\u003c\/i\u003e 253\u003c\/p\u003e \u003cp\u003e\u003ci\u003e14.2.5 Collection Representation and Retrieval System\u003c\/i\u003e 254\u003c\/p\u003e \u003cp\u003e\u003ci\u003e14.2.6 Experiment\u003c\/i\u003e 256\u003c\/p\u003e \u003cp\u003e\u003ci\u003e14.2.7 Conclusion\u003c\/i\u003e 258\u003c\/p\u003e \u003cp\u003e14.3 Conclusion and Future Trends 259\u003c\/p\u003e \u003cp\u003eAcknowledgement 259\u003c\/p\u003e \u003cp\u003e\u003cb\u003e15 The Role of Explicit Semantics in Search and Browsing 261\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eMichiel Hildebrand, Jacco van Ossenbruggen and Lynda Hardman\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e15.1 Basic Search Terminology 261\u003c\/p\u003e \u003cp\u003e15.2 Analysis of Semantic Search 262\u003c\/p\u003e \u003cp\u003e\u003ci\u003e15.2.1 Query Construction\u003c\/i\u003e 263\u003c\/p\u003e \u003cp\u003e\u003ci\u003e15.2.2 Search Algorithm\u003c\/i\u003e 265\u003c\/p\u003e \u003cp\u003e\u003ci\u003e15.2.3 Presentation of Results\u003c\/i\u003e 267\u003c\/p\u003e \u003cp\u003e\u003ci\u003e15.2.4 Survey Summary\u003c\/i\u003e 269\u003c\/p\u003e \u003cp\u003e15.3 Use Case A: Keyword Search in ClioPatria 270\u003c\/p\u003e \u003cp\u003e\u003ci\u003e15.3.1 Query Construction\u003c\/i\u003e 270\u003c\/p\u003e \u003cp\u003e\u003ci\u003e15.3.2 Search Algorithm\u003c\/i\u003e 270\u003c\/p\u003e \u003cp\u003e\u003ci\u003e15.3.3 Result Visualization and Organization\u003c\/i\u003e 273\u003c\/p\u003e \u003cp\u003e15.4 Use Case B: Faceted Browsing in ClioPatria 274\u003c\/p\u003e \u003cp\u003e\u003ci\u003e15.4.1 Query Construction\u003c\/i\u003e 274\u003c\/p\u003e \u003cp\u003e\u003ci\u003e15.4.2 Search Algorithm\u003c\/i\u003e 276\u003c\/p\u003e \u003cp\u003e\u003ci\u003e15.4.3 Result Visualization and Organization\u003c\/i\u003e 276\u003c\/p\u003e \u003cp\u003e15.5 Conclusions 277\u003c\/p\u003e \u003cp\u003e\u003cb\u003e16 Conclusion 279\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eRaphaël Troncy, Benoit Huet and Simon Schenk\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eReferences 281\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eAuthor Index 301\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eSubject Index 303\u003c\/b\u003e\u003c\/p\u003e  \u003cp\u003e\u003cstrong\u003eDr. Raphaël Troncy, Centre for Mathematics and Computer Science, Netherlands\u003c\/strong\u003e\u003cbr\u003eRaphaël Troncy obtained his Master's thesis with honours in computer science at the University Joseph Fourier of Grenoble, France. He received his PhD with honours in 2004. His research interests include Semantic Web and Multimedia Technologies, Knowledge Representation, Ontology Modeling and Alignment. Raphaël Troncy is an expert in audio visual metadata and in combining existing metadata standards (such as MPEG-7) with current Semantic Web technologies.\u003c\/p\u003e\u003cp\u003e\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eDr. Benoit Huet, Institut EURECOM, France\u003c\/strong\u003e\u003cbr\u003eBenoit Huet received his BSc degree in computer science and engineering from the Ecole Superieure de Technologie Electrique (Groupe ESIEE, France) in 1992. In 1993, he was awarded the MSc degree in Artificial Intelligence from the University of Westminster (UK) with distinction. He received his PhD degree in Computer Science from the University of York (UK). His research interests include computer vision, content-based retrieval, multimedia data mining and indexing (still and\/or moving images) and pattern recognition. \u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eSimon Schenk, University of Koblenz-Landau, Germany\u003c\/strong\u003e\u003cbr\u003eSimon Schenk is a research and teaching assistant at the Information Systems and Semantic Web Group of University of Koblenz-Landau.Simon is working towards his PhD degree under the supervision of Professor Dr. Steffen Staab. Previously, he has worked as a consultant for Capgemini. Schenk studied at NORDAKADEMIE University of Applied Sciences, Germany and Karlstads Universitet, Sweden and received his diploma in Computer Science and Business Management from NORDAKADEMIE in 2004.   \u003cb\u003eIn this book, the authors present the latest research results in the multimedia and semantic web communities, bridging the \"Semantic Gap\"\u003c\/b\u003e  \u003c\/p\u003e\u003cp\u003eThis book explains, collects and reports on the latest research results that aim at narrowing the so-called multimedia \"Semantic Gap\": the large disparity between descriptions of multimedia content that can be computed automatically, and the richness and subjectivity of semantics in user queries and human interpretations of audiovisual media. Addressing the grand challenge posed by the \"Semantic Gap\" requires a multi-disciplinary approach (computer science, computer vision and signal processing, cognitive science, web science, etc.) and this is reflected in recent research in this area. In addition, the book targets an interdisciplinary community, and in particular the Multimedia and the Semantic Web communities. Finally, the authors provide both the fundamental knowledge and the latest state-of-the-art results from both communities with the goal of making the knowledge of one community available to the other.\u003c\/p\u003e \u003cp\u003e\u003ci\u003eKey Features:\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e• Presents state-of-the art research results in multimedia semantics: multimedia analysis, metadata standards and multimedia knowledge representation, semantic interaction with multimedia\u003cbr\u003e • Contains real industrial problems exemplified by user case scenarios\u003cbr\u003e • Offers an insight into various standardisation bodies including W3C, IPTC and ISO MPEG\u003cbr\u003e • Contains contributions from academic and industrial communities from Europe, USA and Asia\u003cbr\u003e • Includes an accompanying website containing user cases, datasets, and software mentioned in the book, as well as links to the K-Space NoE and the SMaRT society web sites (\u003ca href=\"http:\/\/www.multimediasemantics.com\/\"\u003ehttp:\/\/www.multimediasemantics.com\/\u003c\/a\u003e)\u003c\/p\u003e \u003cp\u003eThis book will be a valuable reference for academic and industry researchers \/practitioners in multimedia, computational intelligence and computer science fields. Graduate students, project leaders, and consultants will also find this book of interest.\u003c\/p\u003e","brand":"Wiley-Blackwell","offers":[{"title":"Default Title","offer_id":47989661368549,"sku":"NP9780470747001","price":119.95,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1842\/7735\/files\/9780470747001.jpg?v=1761785003","url":"https:\/\/k12savings.com\/es\/products\/multimedia-semantics-isbn-9780470747001","provider":"K12savings","version":"1.0","type":"link"}