Loading…
Understanding-oriented multimedia content analysis
This book offers a systematic introduction to an understanding-oriented approach to multimedia content analysis. It integrates the visual understanding and learning models into a unified framework, within which the visual understanding guides the model learning while the learned models improve the v...
Saved in:
| Main Author: | |
|---|---|
| Corporate Author: | |
| Format: | eBook |
| Language: | English |
| Published: |
Singapore :
Springer,
2017.
Singapore : 2017. |
| Series: | Springer theses.
|
| Physical Description: |
1 online resource. |
| Subjects: | |
| Online Access: | SpringerLink - Click here for access |
Contents:
- Supervisor's Foreword; Preface; Parts of this book have been published in the following articles:Zechao Li, Jing Liu, Jinhui Tang, Hanqing Lu. Robust Structured Subspace Learning for Data Representation. IEEE Trans. on Pattern Analysis and Machine Intelligence 37(10): 2085-2098, 2015. Zechao Li, Jinhui Tang. Unsupervised Feature Selection via Nonnegative Spectral Analysis and Redundancy Control. IEEE Trans. on Image Processing 24(12): 5343-5355, 2015. Zechao Li, Jing Liu, Yi Yang, Xiaofang Zhou, Hanqing Lu. Clustering-Guided Spa; Acknowledgements; Contents; Notations; 1 Introduction.
- 1.1 Multimedia Analysis and Understanding1.2 Challenges and Progresses; 1.3 Understanding-Oriented Multimedia Content Analysis; 1.4 Organization of This Book; References; 2 Understanding-Oriented Unsupervised Feature Selection; 2.1 Introduction; 2.2 Related Work; 2.3 Clustering-Guided Sparse Structural Learning#x83;; 2.3.1 Nonnegative Spectral Clustering; 2.3.2 Sparse Structural Analysis; 2.3.3 Optimization; 2.3.4 Convergence Analysis; 2.3.5 Discussions; 2.3.6 Experiments; 2.4 Nonnegative Spectral Analysis and Redundancy Control for Unsupervised Feature Selection; 2.4.1 The Objective Function.
- 2.4.2 Optimization2.4.3 Experiments; 2.5 Discussions; References; 3 Understanding-Oriented Feature Learning; 3.1 Introduction; 3.2 Related Work; 3.2.1 Feature Selection; 3.2.2 Subspace Learning; 3.3 The Proposed RSSL Framework; 3.3.1 Formulation; 3.3.2 Optimization; 3.3.3 Computational Complexity Analysis; 3.3.4 Image Understanding Tasks; 3.4 Performance Evaluation; 3.4.1 Image Tagging; 3.4.2 Clustering; 3.4.3 Classification; 3.4.4 Discussion; 3.5 Discussions; References; 4 Personalized Tag Recommendation; 4.1 Introduction; 4.2 Related Work; 4.3 Personalized Geo-Specific Tag Recommendation.
- 4.3.1 Overview of Our Solution4.3.2 Discovering Intermediate Space and Unified Space; 4.3.3 Optimization; 4.3.4 Tag Representation in Unified Space; 4.3.5 Tag Recommendation; 4.4 Performance Evaluation; 4.4.1 Dataset; 4.4.2 Evaluation Measures; 4.4.3 Parameter Setting; 4.4.4 Compared Methods; 4.4.5 Parameter Sensitivity Analysis; 4.4.6 Experimental Analysis; 4.5 Discussions; References; 5 Understanding-Oriented Multimedia News Retrieval; 5.1 Introduction; 5.2 Related Work; 5.3 Person-Centered Multimedia News Retrieval; 5.3.1 Overview of the Proposed MMPNR System.
- 5.3.2 Correlation Initialization5.3.3 Correlation Reconstruction; 5.3.4 Ranking and Visualization; 5.4 Multimedia News Contextualization; 5.4.1 Overview of GeoVisNews; 5.4.2 News Document Geo-Localization; 5.4.3 Image Enrichment; 5.4.4 Result Ranking and Visualization; 5.5 Discussions; References; 6 Understanding-Oriented Multimedia News Summarization; 6.1 Introduction; 6.2 Previous Work; 6.3 Multimedia News Summarization; 6.3.1 Hierarchical Topic Structure; 6.3.2 Multimedia Topic Representation; 6.3.3 User Interface Overview; 6.4 Performance Evaluation.