Muutke küpsiste eelistusi

E-raamat: Multimedia Ontology: Representation and Applications [Taylor & Francis e-raamat]

, (Tata Consultancy Services Ltd, Gurgaon, India),
  • Formaat: 304 pages, 2 Tables, black and white; 108 Illustrations, black and white
  • Ilmumisaeg: 05-Mar-2020
  • Kirjastus: Chapman & Hall/CRC
  • ISBN-13: 9780429160899
Teised raamatud teemal:
  • Taylor & Francis e-raamat
  • Hind: 124,64 €*
  • * hind, mis tagab piiramatu üheaegsete kasutajate arvuga ligipääsu piiramatuks ajaks
  • Tavahind: 178,05 €
  • Säästad 30%
Multimedia Ontology: Representation and ApplicationsSuurem pilt
  • Formaat: 304 pages, 2 Tables, black and white; 108 Illustrations, black and white
  • Ilmumisaeg: 05-Mar-2020
  • Kirjastus: Chapman & Hall/CRC
  • ISBN-13: 9780429160899
Teised raamatud teemal:
Taylor & Francis e-raamatudRohkem infot Taylor & Francis e-raamatute kohta
Raamatu kodulehekülg: https://www.taylorfrancis.com/books/9780429160899

The result of more than 15 years of collective research, Multimedia Ontology: Representation and Applications provides a theoretical foundation for understanding the nature of media data and the principles involved in its interpretation. The book presents a unified approach to recent advances in multimedia and explains how a multimedia ontology can fill the semantic gap between concepts and the media world. It relays real-life examples of implementations in different domains to illustrate how this gap can be filled.

The book contains information that helps with building semantic, content-based search and retrieval engines and also with developing vertical application-specific search applications. It guides you in designing multimedia tools that aid in logical and conceptual organization of large amounts of multimedia data. As a practical demonstration, it showcases multimedia applications in cultural heritage preservation efforts and the creation of virtual museums.

The book describes the limitations of existing ontology techniques in semantic multimedia data processing, as well as some open problems in the representations and applications of multimedia ontology. As an antidote, it introduces new ontology representation and reasoning schemes that overcome these limitations. The long, compiled efforts reflected in Multimedia Ontology: Representation and Applications are a signpost for new achievements and developments in efficiency and accessibility in the field.

Foreword xiii
Preface xv
List of Figures
xvii
List of Tables
xxi
List of Acronyms
xxiii
Author Biographies xxvii
1 Introduction
1(6)
1.1 The Multimedia Wave
1(1)
1.2 Semantic Multimedia Web: Bridging the Semantic Gap
2(1)
1.3 Multimedia Web Ontology Language
3(1)
1.4 Organization of the Book
3(4)
2 Ontology and the Semantic Web
7(16)
2.1 Introduction
7(1)
2.2 Evolution of the Semantic Web
8(3)
2.3 Semantic Web Technologies
11(3)
2.4 What Is an Ontology?
14(1)
2.5 Formal Ontology Definition
15(2)
2.6 Ontology Representation
17(5)
2.6.1 RDF and RDF Schema
17(2)
2.6.2 Description Logics
19(1)
2.6.3 Web Ontology Language
20(2)
2.7 Conclusions
22(1)
3 Characterizing Multimedia Semantics
23(14)
3.1 Introduction
23(1)
3.2 A First Look at Multimedia Semantics
24(3)
3.2.1 What a Media Instance Denotes
24(1)
3.2.2 Interaction between the Objects and the Role of Context
25(1)
3.2.3 The Connotation of Media Forms
25(1)
3.2.4 The Semantics Lie in the Mind of the Beholder
26(1)
3.2.5 Multimedia as a Communication Channel
27(1)
3.3 Percepts, Concepts, Knowledge and Expressions
27(5)
3.3.1 Percepts and Concepts
27(2)
3.3.2 The Perceptual Knowledge
29(1)
3.3.3 Communication and Expressions
29(1)
3.3.4 Symbolism and Interpretation
30(2)
3.4 Representing Multimedia Semantics
32(2)
3.5 Semantic Web Technologies and Multimedia
34(1)
3.6 Conclusions
35(2)
4 Ontology Representations for Multimedia
37(24)
4.1 Introduction
37(1)
4.2 An Overview of MPEG-7 and MPEG-21
37(6)
4.3 MPEG-7 Ontologies
43(3)
4.4 Using MPEG-7 Ontology for Applications
46(6)
4.4.1 Museum Ontology
47(1)
4.4.2 Associating Domain Knowledge with MPEG-7 Ontology
48(1)
4.4.3 Ontological Framework for Application Support
49(1)
4.4.4 MPEG-7 and Semantic Interoperability
50(2)
4.5 Multimedia Concept Modeling
52(1)
4.6 Ontology Applications
53(6)
4.6.1 Use of Ontology for Accessing Paintings
54(1)
4.6.2 Ontology for Ambient Intelligence
55(2)
4.6.3 Ontology for Sensor-Web Applications
57(1)
4.6.4 Biomedical Applications
58(1)
4.6.5 Ontology for Phenomics
59(1)
4.7 Conclusions
59(2)
5 Multimedia Web Ontology Language
61(40)
5.1 Introduction
61(1)
5.2 Perceptual Modeling of Domains
62(2)
5.3 An Overview of the Multimedia Web Ontology Language .
64(3)
5.3.1 Knowledge Representation
64(2)
5.3.2 Reasoning
66(1)
5.4 MOWL: Concepts, Media Observables and Media Relations
67(2)
5.5 MOWL: Spatio-Temporal Constructs for Complex Events .
69(6)
5.5.1 Allen's Interval Algebra
70(1)
5.5.2 Concave Intervals
71(1)
5.5.3 Accommodating Viewpoints
72(2)
5.5.4 Discussions
74(1)
5.6 MOWL Language Constructs
75(9)
5.6.1 Concepts and Media Properties
75(1)
5.6.2 Media Property Propagation
76(2)
5.6.3 Uncertainty Specification
78(3)
5.6.4 Spatio-Temporal Relations
81(3)
5.7 The Observation Model
84(6)
5.7.1 Defining an Observation Model
84(2)
5.7.2 Semantics of MOWL Relations for Constructing OM
86(3)
5.7.3 Computing CPTs in the OM
89(1)
5.8 MOWL Inferencing Framework
90(7)
5.8.1 Constructing the Observation Model
91(1)
5.8.2 Concept Recognition Using the OM
91(6)
5.9 Reasoning Modes with Bayesian Network and MOWL
97(1)
5.10 Conclusions
98(3)
6 Modeling the Semantics of Multimedia Content
101(20)
6.1 Introduction
101(1)
6.2 Data-Driven Learning for Multimedia Semantics Extraction
102(2)
6.3 Media Features for Semantic Modeling
104(5)
6.3.1 Image-Based Features
104(3)
6.3.2 Audio Features
107(1)
6.3.3 Textual Features
108(1)
6.3.4 Video Features
108(1)
6.4 Semantic Classification of Multimedia Content
109(1)
6.5 Use of Ontology for Semantic Classification
110(9)
6.5.1 Architecture Classification
111(1)
6.5.2 Indian Architecture Domain
111(3)
6.5.3 Region Discriminators
114(1)
6.5.3.1 Semantic Features
114(1)
6.5.3.2 Learning Discriminative Region Using Random Forest
115(1)
6.5.4 Architecture Categorization Using a Multimedia Ontology
116(1)
6.5.5 Experiments: Indian Architecture Categorization
116(3)
6.6 Conclusions
119(2)
7 Learning Multimedia Ontology
121(28)
7.1 Introduction
121(1)
7.2 State of the Art in Ontology Learning
122(3)
7.3 Learning an Ontology from Multimedia Data
125(2)
7.4 Ontology-Based Management of Multimedia Resources . .
127(7)
7.4.1 Bayesian Network Learning
129(1)
7.4.2 Learning OM: A Bayesian Network
129(1)
7.4.3 Full Bayesian Network Learning
130(1)
7.4.3.1 FBN Structure Learning
131(1)
7.4.3.2 Learning CPT-Trees
132(1)
7.4.3.3 Learning Associations of Observables with Concepts
133(1)
7.5 Application of Multimedia Ontology Learning
134(13)
7.5.1 Learning the Structure
135(2)
7.5.1.1 Performance Measure
137(1)
7.5.1.2 Logic and Implementation
138(2)
7.5.2 Parametric Learning
140(2)
7.5.2.1 Concept Recognition Using MOWL
142(1)
7.5.2.2 Concept Recognition after Learning
143(2)
7.5.2.3 Semantic Annotation Generation
145(2)
7.6 Conclusions
147(2)
8 Applications Exploiting Multimedia Semantics
149(24)
8.1 Introduction
149(2)
8.2 Multimedia Retrieval and Classification
151(3)
8.2.1 HeritAge: Integrating Diverse Media Contents from Distributed Collections
151(1)
8.2.2 Document Image Classification
151(3)
8.3 Recommendation of Media-Rich Commodities
154(6)
8.3.1 Painting Recommendation
154(2)
8.3.2 Garment Recommendation
156(3)
8.3.3 Discussions
159(1)
8.4 Information Integration from Open Resources
160(11)
8.4.1 News Aggregation from Social Media
160(1)
8.4.2 Information Aggregation by Event Pattern Detection and Trend Analysis
161(1)
8.4.2.1 E-MOWL and Geo-ontology
162(1)
8.4.2.2 Video Context and Document Set
163(2)
8.4.2.3 Spatial and Temporal Trend Analysis
165(1)
8.4.3 News Aggregation from Sports and Political Videos
166(1)
8.4.3.1 Semantic Annotation of Video
167(2)
8.4.3.2 Sports and Political News Aggregation
169(1)
8.4.4 Discussions
169(2)
8.5 Conclusions
171(2)
9 Distributed Multimedia Applications
173(20)
9.1 Introduction
173(1)
9.2 Challenges for Web-Scale Multimedia Data Access
174(1)
9.3 Architectures for Distributed Multimedia Data Processing
174(2)
9.4 Peer-to-Peer Architecture
176(1)
9.5 Multiagent Architecture for Distributed Multimedia Systems
177(4)
9.5.1 Advantages of Agent-Based Architecture
178(1)
9.5.2 Agent Coordination and Ontology
179(1)
9.5.3 Ontology for Multimedia Data Integration
180(1)
9.6 Ontology Alignment
181(3)
9.6.1 Definitions
182(1)
9.6.2 Similarity Measures
183(1)
9.6.3 Similarity Measure with Media Features
183(1)
9.7 Knowledge-based Access to Massively Distributed Multimedia
184(6)
9.7.1 Observation Model, Minimalist Plan, and Observation Plan
185(1)
9.7.2 Formulating Minimalist Plan
186(1)
9.7.3 Formulating an Observation Plan
187(2)
9.7.4 An Illustrative Example
189(1)
9.8 Conclusion
190(3)
10 Application of Multimedia Ontology in Heritage Preservation
193(26)
10.1 Introduction
193(2)
10.2 Preserving the Intangible Heritage of Indian Classical Dance
195(9)
10.2.1 MOWL Language Constructs for Dance Ontology
196(1)
10.2.2 Multimedia Dance Ontology
197(3)
10.2.3 Concept Recognition and Semantic Annotation of Heritage Artifacts
200(1)
10.2.4 Browsing and Querying Video Content
201(3)
10.3 Intellectual Journey: Space-Time Traversal Using an Ontology
204(8)
10.3.1 Ontology-based Interlinking of Digital Heritage Artifacts
205(1)
10.3.2 Ontology-based Framework for Space-Time Exploration
206(2)
10.3.3 Intellectual Exploration of the Theme of Girija Kalyana
208(3)
10.3.4 Experiential Exploration Interface
211(1)
10.4 Cross-Modal Query and Retrieval
212(5)
10.4.1 Multimedia Ontology of Mural Paintings Domain . .
213(1)
10.4.2 Ontology-based Cross-Modal Retrieval and Semantic Access
214(1)
10.4.2.1 LDA-based Image and Text Modeling
215(1)
10.4.2.2 Semantic Matching
215(1)
10.4.2.3 Cross-Modal Retrieval
216(1)
10.5 Conclusion
217(2)
11 Open Problems and Future Directions
219(6)
11.1 Knowledge and Human Society
219(1)
11.2 Knowledge Organization and Formal Representation
219(2)
11.3 The Perceptual World and MOWL
221(1)
11.4 The Big Debate: Data-Driven vs. Knowledge-Driven Approaches
222(1)
11.5 Looking Forward: Convergence between Knowledge-Based and Data-Driven Approaches
223(2)
A MOWL Schema in Notation3 225(6)
B MOWL Syntax Structural Specification 231(4)
C Examples of WSDL Specification for Media Pattern Detectors 235(2)
Bibliography 237(24)
Index 261
Santanu Chaudhury did his BTech (1984) in Electronics and Electrical Communication Engineering and PhD (1989) in Computer Science and Engineering from Indian Institute of Technology (IIT), Kharagpur, India. Currently, he is a professor in the Department of Electrical Engineering at IIT Delhi. He was also Dean, Undergraduate Studies at IIT Delhi. He was awarded INSA medal for young scientists in 1993. He is a fellow of Indian National Academy of Engineering and National Academy of Sciences, India. He is also a fellow of the International Association of Pattern Recognition. His research interests are in the areas of Computer Vision, Artificial Intelligence and Multimedia Systems. He has published more than 150 papers in international journals and conference proceedings. He has been on the programme committee of a number of international conferences, including ICCV, ACCV, ICPR, ICVGIP, and PReMI.

Anupama Mallik did her BSc (1986) in Physics and Masters in Computer Applications (1989) from Delhi University, and PhD (2012) in Electrical Engineering from the Indian Institute of Technology (IIT), Delhi. Her PhD thesis dealt with ontology based exploration of multimedia contents. She is associated with Multimedia research group of the Electrical Engineering Department, IIT Delhi and has worked as a Research Scientist in projects sponsored by the Department of Science and Technology, Government of India. Her current research interests include Semantic web based applications, multimedia ontology, ontology applications in Internet of Things, and in cultural heritage preservation. She is a visiting faculty at the Indraprastha Institute of Information Technology, Delhi (IIIT-D). She is a member of the ACM.

Hiranmay Ghosh is a principal scientist with TCS Innovation Labs Delhi and leads its multimedia research track. He received his PhD from IIT, Delhi and his BTech and BSc degrees from the University of Calcutta. His current research interests include multimedia systems, knowledge representation and reasoning, semantic web, intelligent agents, cognitive models and robotics. He is an adjunct faculty member of the Electrical Engineering Department of IIT, Delhi and is associated with its multimedia research group. He is a member of the academic advisory committee of IIT, Ropar. He is a senior member of the Institute of Electrical and Electronics Engineers (IEEE), and a member of ACM and IUPRAI.
Püsilink: https://www.kriso.ee/db/9780429160899_pe.html
Märksõnad: