Muutke küpsiste eelistusi

E-raamat: Multimedia Semantics: Metadata, Analysis and Interaction

Edited by (University Of Koblenz-Landau), Edited by (Institut EURECOM), Edited by (Department 2229, route des Crêtes, 06560)
  • Formaat: PDF+DRM
  • Ilmumisaeg: 13-Jul-2011
  • Kirjastus: Wiley-Blackwell
  • Keel: eng
  • ISBN-13: 9781119970224
Teised raamatud teemal:
  • Formaat - PDF+DRM
  • Hind: 111,09 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
  • Raamatukogudele
  • Formaat: PDF+DRM
  • Ilmumisaeg: 13-Jul-2011
  • Kirjastus: Wiley-Blackwell
  • Keel: eng
  • ISBN-13: 9781119970224
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

In this book, the authors present the latest research results in the multimedia and semantic web communities, bridging the "Semantic Gap"

This 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.

Key Features:

  • Presents state-of-the art research results in multimedia semantics: multimedia analysis, metadata standards and multimedia knowledge representation, semantic interaction with multimedia
  • Contains real industrial problems exemplified by user case scenarios
  • Offers an insight into various standardisation bodies including W3C, IPTC and ISO MPEG
  • Contains contributions from academic and industrial communities from Europe, USA and Asia
  • 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 (http://www.multimediasemantics.com/)

This 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.

Foreword xi
List of Figures
xiii
List of Tables
xvii
List of Contributors
xix
1 Introduction
1(6)
Raphael Troncy
Benoit Huet
Simon Schenk
2 Use Case Scenarios
7(14)
Werner Bailer
Susanne Boll
Oscar Celma
Michael Hausenblas
Yves Raimond
2.1 Photo Use Case
8(2)
2.1.1 Motivating Examples
8(1)
2.1.2 Semantic Description of Photos Today
9(1)
2.1.3 Services We Need for Photo Collections
10(1)
2.2 Music Use Case
10(4)
2.2.1 Semantic Description of Music Assets
11(1)
2.2.2 Music Recommendation and Discovery
12(1)
2.2.3 Management of Personal Music Collections
13(1)
2.3 Annotation in Professional Media Production and Archiving
14(4)
2.3.1 Motivating Examples
15(2)
2.3.2 Requirements for Content Annotation
17(1)
2.4 Discussion
18(3)
Acknowledgements
19(2)
3 Canonical Processes of Semantically Annotated Media Production
21(14)
Lynda Hardman
Zeljko Obrenovic
Frank Nack
3.1 Canonical Processes
22(5)
3.1.1 Premeditate
23(1)
3.1.2 Create Media Asset
23(1)
3.1.3 Annotate
23(1)
3.1.4 Package
24(1)
3.1.5 Query
24(1)
3.1.6 Construct Message
25(1)
3.1.7 Organize
25(1)
3.1.8 Publish
26(1)
3.1.9 Distribute
26(1)
3.2 Example Systems
27(6)
3.2.1 CeWe Color Photo Book
27(2)
3.2.2 SenseCam
29(4)
3.3 Conclusion and Future Work
33(2)
4 Feature Extraction for Multimedia Analysis
35(24)
Rachid Benmokhtar
Benoit Huet
Gael Richard
Slim Essid
4.1 Low-Level Feature Extraction
36(18)
4.1.1 What Are Relevant Low-Level Features?
36(1)
4.1.2 Visual Descriptors
36(9)
4.1.3 Audio Descriptors
45(9)
4.2 Feature Fusion and Multi-modality
54(4)
4.2.1 Feature Normalization
54(1)
4.2.2 Homogeneous Fusion
55(1)
4.2.3 Cross-modal Fusion
56(2)
4.3 Conclusion
58(1)
5 Machine Learning Techniques for Multimedia Analysis
59(22)
Slim Essid
Marine Campedel
Gael Richard
Tomas Piatrik
Rachid Benmokhtar
Benoit Huet
5.1 Feature Selection
61(4)
5.1.1 Selection Criteria
61(1)
5.1.2 Subset Search
62(1)
5.1.3 Feature Ranking
63(1)
5.1.4 A Supervised Algorithm Example
63(2)
5.2 Classification
65(10)
5.2.1 Historical Classification Algorithms
65(2)
5.2.2 Kernet Methods
67(4)
5.2.3 Classifying Sequences
71(2)
5.2.4 Biologically Inspired Machine Learning Techniques
73(2)
5.3 Classifier Fusion
75(5)
5.3.1 Introduction
75(1)
5.3.2 Non-trainable Combiners
75(1)
5.3.3 Trainable Combiners
76(1)
5.3.4 Combination of Weak Classifiers
77(1)
5.3.5 Evidence Theory
78(1)
5.3.6 Consensual Clustering
78(2)
5.3.7 Classifier Fusion Properties
80(1)
5.4 Conclusion
80(1)
6 Semantic Web Basics
81(18)
Eyal Oren
Simon Schenk
6.1 The Semantic Web
82(1)
6.2 RDF
83(7)
6.2.1 RDF Graphs
86(1)
6.2.2 Named Graphs
87(1)
6.2.3 RDF Semantics
88(2)
6.3 RDF Schema
90(3)
6.4 Data Models
93(1)
6.5 Linked Data Principles
94(2)
6.5.1 Dereferencing Using Basic Web Look-up
95(1)
6.5.2 Dereferencing Using Http 303 Redirects
95(1)
6.6 Development Practicalities
96(3)
6.6.1 Data Stores
97(1)
6.6.2 Toolkits
97(2)
7 Semantic Web Languages
99(30)
Antoine Isaac
Simon Schenk
Ansgar Scherp
7.1 The Need for Ontologies on the Semantic Web
100(1)
7.2 Representing Ontological Knowledge Using OWL
100(8)
7.2.1 OWL Constructs and OWL Syntax
100(2)
7.2.2 The Formal Semantics of OWL and its Different Layers
102(4)
7.2.3 Reasoning Tasks
106(1)
7.2.4 OWL Flavors
107(1)
7.2.5 Beyond OWL
107(1)
7.3 A Language to Represent Simple Conceptual Vocabularies: SKOS
108(5)
7.3.1 Ontologies versus Knowledge Organization Systems
108(1)
7.3.2 Representing Concept Schemes Using SKOS
109(2)
7.3.3 Characterizing Concepts beyond SKOS
111(1)
7.3.4 Using SKOS Concept Schemes on the Semantic Web
112(1)
7.4 Querying on the Semantic Web
113(16)
7.4.1 Syntax
113(5)
7.4.2 Semantics
118(5)
7.4.3 Default Negation in SPARQL
123(1)
7.4.4 Well-Formed Queries
124(1)
7.4.5 Querying for Multimedia Metadata
124(2)
7.4.6 Partitioning Datasets
126(1)
7.4.7 Related Work
127(2)
8 Multimedia Metadata Standards
129(16)
Peter Schallauer
Werner Bailer
Raphael Troncy
Florian Kaiser
8.1 Selected Standards
130(10)
8.1.1 MPEG-7
130(2)
8.1.2 EBU_Meta
132(1)
8.1.3 SMPTE Metadata Standards
133(1)
8.1.4 Dublin Core
133(1)
8.1.5 TV-Anytime
134(1)
8.1.6 METS and VRA
134(1)
8.1.7 MPEG-21
135(1)
8.1.8 XMP, IPTC in XMP
135(1)
8.1.9 EXIF
136(1)
8.1.10 DIG35
137(1)
8.1.11 ID3/MP3
137(1)
8.1.12 NewsML G2 and rNews
138(1)
8.1.13 W3C Ontology for Media Resources
138(1)
8.1.14 EBUCore
139(1)
8.2 Comparison
140(3)
8.3 Conclusion
143(2)
9 The Core Ontology for Multimedia
145(18)
Thomas Franz
Raphael Troncy
Miroslav Vacura
9.1 Introduction
145(1)
9.2 A Multimedia Presentation for Granddad
146(3)
9.3 Related Work
149(1)
9.4 Requirements for Designing a Multimedia Ontology
150(1)
9.5 A Formal Representation for MPEG-7
150(7)
9.5.1 DOLCE as Modeling Basis
151(1)
9.5.2 Multimedia Patterns
151(4)
9.5.3 Basic Patterns
155(2)
9.5.4 Comparison with Requirements
157(1)
9.6 Granddad's Presentation Explained by COMM
157(2)
9.7 Lessons Learned
159(1)
9.8 Conclusion
160(3)
10 Knowledge-Driven Segmentation and Classification
163(20)
Thanos Athanasiadis
Phivos Mylonas
Georgios Th. Papadopoulos
Vasileios Mezaris
Yannis Avrithis
Ioannis Kompatsiaris
Michael G. Strintzis
10.1 Related Work
164(1)
10.2 Semantic Image Segmentation
165(5)
10.2.1 Graph Representation of an Image
165(1)
10.2.2 Image Graph Initialization
165(2)
10.2.3 Semantic Region Growing
167(3)
10.3 Using Contextual Knowledge to Aid Visual Analysis
170(7)
10.3.1 Contextual Knowledge Formulation
170(3)
10.3.2 Contextual Relevance
173(4)
10.4 Spatial Context and Optimization
177(4)
10.4.1 Introduction
177(1)
10.4.2 Low-Level Visual Information Processing
177(1)
10.4.3 Initial Region-Concept Association
178(1)
10.4.4 Final Region-Concept Association
179(2)
10.5 Conclusions
181(2)
11 Reasoning for Multimedia Analysis
183(22)
Nikolaos Simou
Giorgos Stoilos
Carsten Saathoff
Jan Nemrava
Vojtech Svatek
Petr Berka
Vassilis Tzouvaras
11.1 Fuzzy DL Reasoning
184(8)
11.1.1 The Fuzzy DL f-SHIN
184(1)
11.1.2 The Tableaux Algorithm
185(2)
11.1.3 The FiRE Fuzzy Reasoning Engine
187(5)
11.2 Spatial Features for Image Region Labeling
192(4)
11.2.1 Fuzzy Constraint Satisfaction Problems
192(1)
11.2.2 Exploiting Spatial Features Using Fuzzy Constraint Reasoning
193(3)
11.3 Fuzzy Rule Based Reasoning Engine
196(5)
11.4 Reasoning over Resources Complementary to Audiovisual Streams
201(4)
12 Multi-Modal Analysis for Content Structuring and Event Detection
205(18)
Noel E. O'Connor
David A. Sadlier
Bart Lehane
Andrew Salway
Jan Nemrava
Paul Buitelaar
12.1 Moving Beyond Shots for Extracting Semantics
206(1)
12.2 A Multi-Modal Approach
207(1)
12.3 Case Studies
207(1)
12.4 Case Study 1: Field Sports
208(6)
12.4.1 Content Structuring
208(5)
12.4.2 Concept Detection Leveraging Complementary Text Sources
213(1)
12.5 Case Study 2: Fictional Content
214(7)
12.5.1 Content Structuring
215(4)
12.5.2 Concept Detection Leveraging Audio Description
219(2)
12.6 Conclusions and Future Work
221(2)
13 Multimedia Annotation Tools
223(18)
Carsten Saathoff
Krishna Chandramouli
Werner Bailer
Peter Schallauer
Raphael Troncy
13.1 State of the Art
224(1)
13.2 SVAT: Professional Video Annotation
225(4)
13.2.1 User Interface
225(3)
13.2.2 Semantic Annotation
228(1)
13.3 KAT: Semi-automatic, Semantic Annotation of Multimedia Content
229(10)
13.3.1 History
231(1)
13.3.2 Architecture
232(2)
13.3.3 Default Plugins
234(1)
13.3.4 Using COMM as an Underlying Model: Issues and Solutions
234(3)
13.3.5 Semi-automatic Annotation: An Example
237(2)
13.4 Conclusions
239(2)
14 Information Organization Issues in Multimedia Retrieval Using Low-Level Features
241(20)
Frank Hopfgartner
Reede Ren
Thierry Urruty
Joemon M. Jose
14.1 Efficient Multimedia Indexing Structures
242(7)
14.1.1 An Efficient Access Structure for Multimedia Data
243(2)
14.1.2 Experimental Results
245(4)
14.1.3 Conclusion
249(1)
14.2 Feature Term Based Index
249(10)
14.2.1 Feature Term
250(1)
14.2.2 Feature Term Distribution
251(1)
14.2.3 Feature Term Extraction
252(1)
14.2.4 Feature Dimension Selection
253(1)
14.2.5 Collection Representation and Retrieval System
254(2)
14.2.6 Experiment
256(2)
14.2.7 Conclusion
258(1)
14.3 Conclusion and Future Trends
259(2)
Acknowledgement
259(2)
15 The Role of Explicit Semantics in Search and Browsing
261(18)
Michiel Hildebrand
Jacco van Ossenbruggen
Lynda Hardman
15.1 Basic Search Terminology
261(1)
15.2 Analysis of Semantic Search
262(8)
15.2.1 Query Construction
263(2)
15.2.2 Search Algorithm
265(2)
15.2.3 Presentation of Results
267(2)
15.2.4 Survey Summary
269(1)
15.3 Use Case A: Keyword Search in ClioPatria
270(4)
15.3.1 Query Construction
270(1)
15.3.2 Search Algorithm
270(3)
15.3.3 Result Visualization and Organization
273(1)
15.4 Use Case B: Faceted Browsing in ClioPatria
274(3)
15.4.1 Query Construction
274(2)
15.4.2 Search Algorithm
276(1)
15.4.3 Result Visualization and Organization
276(1)
15.5 Conclusions
277(2)
16 Conclusion
279(2)
Raphael Troncy
Benoit Huet
Simon Schenk
References 281(20)
Author Index 301(2)
Subject Index 303
Dr. Raphaël Troncy, Centre for Mathematics and Computer Science, Netherlands Raphaël 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.





Dr. Benoit Huet, Institut EURECOM, France Benoit 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.

Simon Schenk, University of Koblenz-Landau, Germany Simon 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.