Linked e-resources
Details
Table of Contents
Intro; Preface; Part I Problem Statement; Part II Technologies; Part III Applications; Part IV Concluding Remarks; Contents; Contributors; Part I Problem Statement; 1 Video Verification: Motivation and Requirements; 1.1 Introduction; 1.1.1 Who Verifies Video, Which Groups Are We Dealing With and Why Is This Important?; 1.1.2 The Value of Video Analysis; 1.1.3 Tools/Platforms `Made for Video Verification'; 1.1.4 A New Challenge: `Deep Fakes'; 1.1.5 Typology of Fake Videos; References; Part II Technologies; 2 Real-Time Story Detection and Video Retrieval from Social Media Streams
2.1 Introduction2.2 News Story Detection: Related Work/State of the Art; 2.3 InVID Approach to News Story Detection; 2.3.1 Content Annotation; 2.3.2 Clustering; 2.3.3 Ranking; 2.3.4 Labeling; 2.4 Story Detection: Implementation and Evaluation; 2.5 Video Retrieval from Social Media Streams; 2.5.1 Video Information Retrieval: Related Work/State of the Art; 2.5.2 Video API Querying; 2.5.3 Relevance Filtering and Ranking; 2.6 Social Video Retrieval: Implementation and Evaluation; 2.7 Conclusions; References; 3 Video Fragmentation and Reverse Search on the Web; 3.1 Introduction; 3.2 Related Work
3.2.1 Video Fragmentation3.2.2 Reverse Video Search on the Web; 3.3 State-of-the-Art Techniques and Tools; 3.3.1 Video Fragmentation; 3.3.2 Reverse Video Search on the Web; 3.4 Performance Evaluation and Benchmarking; 3.4.1 Video Fragmentation; 3.4.2 Reverse Video Search on the Web; 3.5 Conclusions and Future Work; References; 4 Finding Near-Duplicate Videos in Large-Scale Collections; 4.1 Introduction; 4.2 Literature Review; 4.2.1 Definition and Related Research Problems; 4.2.2 NDVR Approaches; 4.2.3 Benchmark Datasets; 4.3 NDVR Approaches in InVID; 4.3.1 Bag-of-Words Approach
4.3.2 Deep Metric Learning Approach4.4 Evaluation; 4.4.1 Experimental Setup; 4.4.2 Experimental Results; 4.5 Conclusions and Future Work; References; 5 Finding Semantically Related Videos in Closed Collections; 5.1 Problem Definition and Challenge; 5.2 Semantic Video Annotation; 5.2.1 Related Work; 5.2.2 Methodology; 5.2.3 Results; 5.3 Logo Detection; 5.3.1 Related Work; 5.3.2 Methodology; 5.3.3 Results; 5.4 Conclusions and Future Work; References; 6 Detecting Manipulations in Video; 6.1 Introduction; 6.2 Background; 6.3 Related Work; 6.3.1 Image Forensics; 6.3.2 Video Forensics
6.3.3 Detection of Double/Multiple Quantization6.3.4 Inter-frame Forgery Detection; 6.3.5 Video Deep Fakes and Their Detection; 6.4 Methodology; 6.4.1 Video Tampering Localization; 6.4.2 Tampering Detection; 6.5 Results; 6.5.1 Datasets and Experimental Setup; 6.5.2 Experiments and Results; 6.6 Conclusions and Future Work; References; 7 Verification of Web Videos Through Analysis of Their Online Context; 7.1 Introduction; 7.2 Related Work; 7.2.1 Journalistic Practices; 7.2.2 Machine Learning Approaches; 7.2.3 Verification Support; 7.3 Fake Video Corpus; 7.3.1 Dataset Collection and Overview; 7.3.2 Dataset Analysis
2.1 Introduction2.2 News Story Detection: Related Work/State of the Art; 2.3 InVID Approach to News Story Detection; 2.3.1 Content Annotation; 2.3.2 Clustering; 2.3.3 Ranking; 2.3.4 Labeling; 2.4 Story Detection: Implementation and Evaluation; 2.5 Video Retrieval from Social Media Streams; 2.5.1 Video Information Retrieval: Related Work/State of the Art; 2.5.2 Video API Querying; 2.5.3 Relevance Filtering and Ranking; 2.6 Social Video Retrieval: Implementation and Evaluation; 2.7 Conclusions; References; 3 Video Fragmentation and Reverse Search on the Web; 3.1 Introduction; 3.2 Related Work
3.2.1 Video Fragmentation3.2.2 Reverse Video Search on the Web; 3.3 State-of-the-Art Techniques and Tools; 3.3.1 Video Fragmentation; 3.3.2 Reverse Video Search on the Web; 3.4 Performance Evaluation and Benchmarking; 3.4.1 Video Fragmentation; 3.4.2 Reverse Video Search on the Web; 3.5 Conclusions and Future Work; References; 4 Finding Near-Duplicate Videos in Large-Scale Collections; 4.1 Introduction; 4.2 Literature Review; 4.2.1 Definition and Related Research Problems; 4.2.2 NDVR Approaches; 4.2.3 Benchmark Datasets; 4.3 NDVR Approaches in InVID; 4.3.1 Bag-of-Words Approach
4.3.2 Deep Metric Learning Approach4.4 Evaluation; 4.4.1 Experimental Setup; 4.4.2 Experimental Results; 4.5 Conclusions and Future Work; References; 5 Finding Semantically Related Videos in Closed Collections; 5.1 Problem Definition and Challenge; 5.2 Semantic Video Annotation; 5.2.1 Related Work; 5.2.2 Methodology; 5.2.3 Results; 5.3 Logo Detection; 5.3.1 Related Work; 5.3.2 Methodology; 5.3.3 Results; 5.4 Conclusions and Future Work; References; 6 Detecting Manipulations in Video; 6.1 Introduction; 6.2 Background; 6.3 Related Work; 6.3.1 Image Forensics; 6.3.2 Video Forensics
6.3.3 Detection of Double/Multiple Quantization6.3.4 Inter-frame Forgery Detection; 6.3.5 Video Deep Fakes and Their Detection; 6.4 Methodology; 6.4.1 Video Tampering Localization; 6.4.2 Tampering Detection; 6.5 Results; 6.5.1 Datasets and Experimental Setup; 6.5.2 Experiments and Results; 6.6 Conclusions and Future Work; References; 7 Verification of Web Videos Through Analysis of Their Online Context; 7.1 Introduction; 7.2 Related Work; 7.2.1 Journalistic Practices; 7.2.2 Machine Learning Approaches; 7.2.3 Verification Support; 7.3 Fake Video Corpus; 7.3.1 Dataset Collection and Overview; 7.3.2 Dataset Analysis