Linked e-resources
Details
Table of Contents
Preface; Acknowledgements; Contents; 1 Introduction; 1.1 Overview; 1.2 Discovering Spatial Co-occurrence Patterns; 1.3 Discovering Feature Co-occurrence Patterns; 1.4 Outline of the Book; References; 2 Context-Aware Discovery of Visual Co-occurrence Patterns; 2.1 Introduction; 2.2 Multi-context-aware Clustering; 2.2.1 Regularized k-means Formulation with Multiple Contexts; 2.2.2 Self-learning Optimization; 2.3 Experiments; 2.3.1 Spatial Visual Pattern Discovery; 2.3.2 Image Region Clustering Using Multiple Contexts; 2.4 Summary of this Chapter; References
3 Hierarchical Sparse Coding for Visual Co-occurrence Discovery3.1 Introduction; 3.2 Spatial Context-Aware Multi-feature Sparse Coding; 3.2.1 Learning Spatial Context-Aware Visual Phrases; 3.2.2 Learning Multi-feature Fused Visual Phrases; 3.3 Experiments; 3.3.1 Spatial Visual Pattern Discovery; 3.3.2 Scene Clustering; 3.3.3 Scene Categorization; 3.4 Summary of this Chapter; References; 4 Feature Co-occurrence for Visual Labeling; 4.1 Introduction; 4.2 Multi-feature Collaboration for Transductive Learning; 4.2.1 Spectral Embedding of Multi-feature Data
4.2.2 Embedding Co-occurrence for Data Representation4.2.3 Transductive Learning with Feature Co-occurrence Patterns; 4.2.4 Collaboration Between Pattern Discovery and Label Propagation; 4.3 Experiments; 4.3.1 Experimental Setting; 4.3.2 Label Propagation on Synthetic Data; 4.3.3 Digit Recognition; 4.3.4 Object Recognition; 4.3.5 Body Motion Recognition; 4.3.6 Scene Recognition; 4.4 Summary of this Chapter; References; 5 Visual Clustering with Minimax Feature Fusion; 5.1 Introduction; 5.2 Minimax Optimization for Multi-feature Spectral Clustering
5.2.1 Spectral Embedding for Regularized Data-Cluster Similarity Matrix5.2.2 Minimax Fusion; 5.2.3 Minimax Optimization; 5.3 Experiments; 5.3.1 Datasets and Experimental Setting; 5.3.2 Baseline Algorithms; 5.3.3 Evaluation Metrics; 5.3.4 Experimental Results; 5.3.5 Convergence Analysis; 5.3.6 Sensitivity of Parameters; 5.4 Summary of this Chapter; References; 6 Conclusion; References
3 Hierarchical Sparse Coding for Visual Co-occurrence Discovery3.1 Introduction; 3.2 Spatial Context-Aware Multi-feature Sparse Coding; 3.2.1 Learning Spatial Context-Aware Visual Phrases; 3.2.2 Learning Multi-feature Fused Visual Phrases; 3.3 Experiments; 3.3.1 Spatial Visual Pattern Discovery; 3.3.2 Scene Clustering; 3.3.3 Scene Categorization; 3.4 Summary of this Chapter; References; 4 Feature Co-occurrence for Visual Labeling; 4.1 Introduction; 4.2 Multi-feature Collaboration for Transductive Learning; 4.2.1 Spectral Embedding of Multi-feature Data
4.2.2 Embedding Co-occurrence for Data Representation4.2.3 Transductive Learning with Feature Co-occurrence Patterns; 4.2.4 Collaboration Between Pattern Discovery and Label Propagation; 4.3 Experiments; 4.3.1 Experimental Setting; 4.3.2 Label Propagation on Synthetic Data; 4.3.3 Digit Recognition; 4.3.4 Object Recognition; 4.3.5 Body Motion Recognition; 4.3.6 Scene Recognition; 4.4 Summary of this Chapter; References; 5 Visual Clustering with Minimax Feature Fusion; 5.1 Introduction; 5.2 Minimax Optimization for Multi-feature Spectral Clustering
5.2.1 Spectral Embedding for Regularized Data-Cluster Similarity Matrix5.2.2 Minimax Fusion; 5.2.3 Minimax Optimization; 5.3 Experiments; 5.3.1 Datasets and Experimental Setting; 5.3.2 Baseline Algorithms; 5.3.3 Evaluation Metrics; 5.3.4 Experimental Results; 5.3.5 Convergence Analysis; 5.3.6 Sensitivity of Parameters; 5.4 Summary of this Chapter; References; 6 Conclusion; References