| 摘要 | 第8-10页 |
| ABSTRACT | 第10-11页 |
| LIST OF ABBREVIATIONS | 第15-16页 |
| CHAPTER 1:INTRODUCTION | 第16-30页 |
| 1.1 ONTOLOGIES | 第17-19页 |
| 1.1.1 Types of Ontologies | 第17-18页 |
| 1.1.2 Roles of Ontologies | 第18-19页 |
| 1.2 ONTOLOGY UTILIZATION IN WEB-BASED APPLICATIONS | 第19-24页 |
| 1.2.1 Overview of Web Video Classification | 第20-24页 |
| 1.2.2 Overview of Disaster Management | 第24页 |
| 1.3 MOTIVATION | 第24-26页 |
| 1.4 MAIN CONTRIBUTIONS | 第26-27页 |
| 1.5 ORGANIZATION OF DISSERTATION | 第27-30页 |
| CHAPTER 2: BACKGROUND AND RELATED WORK | 第30-46页 |
| 2.1 WEB VIDEO CLASSIFICATION | 第30-38页 |
| 2.1.1 Textual Features based Web Video Classification | 第30-31页 |
| 2.1.2 Low-level Features based Web Video Classification | 第31-34页 |
| 2.1.3 Multi-Modality based Web Video Classification | 第34-38页 |
| 2.2 HIGH-LEVEL CONCEPT DETECTORS AND SEMANTIC RELATEDNESS MEASURES | 第38-44页 |
| 2.2.1 High-level Concept Detectors | 第38-40页 |
| 2.2.2 Semantic Relatedness Measures | 第40-42页 |
| 2.2.3 Concept Detector Selection through Semantic Relatedness Measures | 第42-44页 |
| 2.3 FORMAL ONTOLOGIES FOR EXTRACTING DISASTER RELATED INFORMATION FROM WEB | 第44-46页 |
| CHAPTER 3:WEB VIDEO CATEGORIZATION USING CATEGORY-PREDICTIVECLASSIFIERS AND CATEGORY-SPECIFIC CONCEPT CLASSIFIERS | 第46-80页 |
| 3.1 INTRODUCTION | 第46-51页 |
| 3.2 CATEGORY-SPECIFIC CONCEPT SELECTION FOR WEB VIDEO CLASSIFICATION | 第51-55页 |
| 3.2.1 FECS Learning | 第52-53页 |
| 3.2.2 FECS Construction | 第53-55页 |
| 3.3 BUILDING CNC AND CXC CLASSIFIERS | 第55-56页 |
| 3.3.1 CNC Classifiers | 第55-56页 |
| 3.3.2 CXC Classifiers | 第56页 |
| 3.4 INTEGRATING CNC CLASSIFIERS WITH CSC CLASSIFIERS | 第56-57页 |
| 3.5 COMBINING REFINED CNC CLASSIFIERS WITH CXC CLASSIFIERS | 第57-59页 |
| 3.6 THE ALGORITHM | 第59-60页 |
| 3.7 EXPERIMENTAL RESULTS | 第60-77页 |
| 3.7.1 Dataset and Performance Metrics | 第60-61页 |
| 3.7.2 Feature Extraction and Pre-Processing | 第61-63页 |
| 3.7.3 Classifier Selection and Parameters Adjustment | 第63页 |
| 3.7.4 Performance of CNC Classifiers | 第63-66页 |
| 3.7.5 Refining CNC Classifiers using CSC Classifiers | 第66-70页 |
| 3.7.6 Fusing Refined CNC Classifiers with CXC Classifiers | 第70-71页 |
| 3.7.7 Comparison with State-of-the-art Techniques | 第71-77页 |
| 3.8 SUMMARY | 第77-80页 |
| CHAPTER 4:WEB VIDEO CLASSIFICATION WITH VISUAL AND TEXTUAL SEMANTICTECHNIQUES | 第80-102页 |
| 4.1 INTRODUCTION | 第80-83页 |
| 4.2 RENDERING SEMANTIC SUPPORT FOR WEB VIDEO CLASSIFICATION | 第83-86页 |
| 4.2.1 Fetching Category Discriminative Terms through Open Directory Project and Large ScaleWeb Videos | 第83-85页 |
| 4.2.2 Semantic Relevance Computation | 第85-86页 |
| 4.3 WEB VIDEO CLASSIFICATION USING CONTENT FEATURES | 第86-90页 |
| 4.3.1 High-level Concept-based Category Classifiers | 第86-87页 |
| 4.3.2 VSR based Web Video Classification | 第87-89页 |
| 4.3.3 Content Fusion | 第89-90页 |
| 4.4 WEB VIDEO CLASSIFICATION USING CONTEXTUAL FEATURES | 第90-91页 |
| 4.4.1 VSM based Web Video Classification | 第90页 |
| 4.4.2 TSR based Web Video Classification | 第90-91页 |
| 4.4.3 Contextual Fusion | 第91页 |
| 4.5 INTEGRATING CONTENT AND CONTEXT FOR WEB VIDEO CLASSIFICATION | 第91-92页 |
| 4.6 THE ALGORITHM | 第92-93页 |
| 4.7 EXPERIMENTAL RESULTS | 第93-100页 |
| 4.7.1 Dataset and Evaluation Metrics | 第93-94页 |
| 4.7.2 Feature Extraction and Pre-Processing | 第94页 |
| 4.7.3 Analysis of Category Classifiers and VSR based Video Classification | 第94-97页 |
| 4.7.4 Analysis of VSM and TSR based Video Classification | 第97-99页 |
| 4.7.5 Analysis of Content and Context Fusion | 第99-100页 |
| 4.8 SUMMARY | 第100-102页 |
| CHAPTER 5:DESIGNING ONTOLOGY FOR CONCEPTUALIZATION AND EXTRACTION OFDISASTER INFORMATION FROM WEB | 第102-122页 |
| 5.1 INTRODUCTION | 第102-103页 |
| 5.2 PROPOSED ONTOLOGY | 第103-113页 |
| 5.2.1 Defining Domain and Scope of Ontology | 第103-104页 |
| 5.2.2 Reusing Existing Ontologies | 第104页 |
| 5.2.3 Enumerating Important Terms | 第104-105页 |
| 5.2.4 Defining Classes and Class Hierarchy | 第105-107页 |
| 5.2.5 Defining Properties | 第107-108页 |
| 5.2.6 Defining Property Restrictions | 第108-113页 |
| 5.3 ONTOLOGY EVALUATION | 第113-115页 |
| 5.3.1 Ontology based Semantic Web Crawling | 第113-115页 |
| 5.4 EXPERIMENTAL SETUP AND RESULTS | 第115-120页 |
| 5.4.1 Conventional Crawling, Ontology-driven Crawling, and their Comparison on RelevantDisaster Documents | 第115-117页 |
| 5.4.2 Conventional Crawling, Ontology-driven Crawling, and their Comparison on Semi-relevant Disaster Documents | 第117-118页 |
| 5.4.3 Conventional Crawling, Ontology-driven Crawling, and their Comparison on IrrelevantDisaster Documents | 第118-120页 |
| 5.5 SUMMARY | 第120-122页 |
| CHAPTER 6:CONCLUSION AND FUTURE WORK | 第122-126页 |
| 6.1 CONCLUSION | 第122-123页 |
| 6.2 FUTURE WORK | 第123-126页 |
| ACKNOWLEDGEMENTS | 第126-128页 |
| REFERENCES | 第128-140页 |
| LIST OF PUBLICATIONS | 第140页 |
