Fusion in Computer Vision

1. Front Matter

   Pages i-xiv

   PDF

2. A Selective Weighted Late Fusion for Visual Concept Recognition

   • Ningning Liu, Emmanuel Dellandréa, Bruno Tellez, Liming Chen

   Pages 1-28

3. Bag-of-Words Image Representation: Key Ideas and Further Insight

   • Marc T. Law, Nicolas Thome, Matthieu Cord

   Pages 29-52

4. Hierarchical Late Fusion for Concept Detection in Videos

   • Sabin Tiberius Strat, Alexandre Benoit, Patrick Lambert, Hervé Bredin, Georges Quénot

   Pages 53-77

5. Fusion of Multiple Visual Cues for Object Recognition in Videos

   • Iván González-Díaz, Jenny Benois-Pineau, Vincent Buso, Hugo Boujut

   Pages 79-107

6. Evaluating Multimedia Features and Fusion for Example-Based Event Detection

   • Gregory K. Myers, Cees G. M. Snoek, Ramakant Nevatia, Ramesh Nallapati, Julien van Hout, Stephanie Pancoast et al.

   Pages 109-133

7. Rotation-Based Ensemble Classifiers for High-Dimensional Data

   • Junshi Xia, Jocelyn Chanussot, Peijun Du, Xiyan He

   Pages 135-160

8. Multimodal Fusion in Surveillance Applications

   • Virginia Fernandez Arguedas, Qianni Zhang, Ebroul Izquierdo

   Pages 161-184

9. Multimodal Violence Detection in Hollywood Movies: State-of-the-Art and Benchmarking

   • Claire-Hélène Demarty, Cédric Penet, Bogdan Ionescu, Guillaume Gravier, Mohammad Soleymani

   Pages 185-208

10. Fusion Techniques in Biomedical Information Retrieval

    • Alba García Seco de Herrera, Henning Müller

    Pages 209-228

11. Using Crowdsourcing to Capture Complexity in Human Interpretations of Multimedia Content

    • Martha Larson, Mark Melenhorst, María Menéndez, Peng Xu

    Pages 229-269

12. Back Matter

    Pages 271-272

    PDF

This book presents a thorough overview of fusion in computer vision, from an interdisciplinary and multi-application viewpoint, describing successful approaches, evaluated in the context of international benchmarks that model realistic use cases. Features: examines late fusion approaches for concept recognition in images and videos; describes the interpretation of visual content by incorporating models of the human visual system with content understanding methods; investigates the fusion of multi-modal features of different semantic levels, as well as results of semantic concept detections, for example-based event recognition in video; proposes rotation-based ensemble classifiers for high-dimensional data, which encourage both individual accuracy and diversity within the ensemble; reviews application-focused strategies of fusion in video surveillance, biomedical information retrieval, and content detection in movies; discusses the modeling of mechanisms of human interpretation of complex visual content.

• Bagging and Boosting Methods
• Contextual Fusion
• Data Dimensionality Reduction
• Early Fusion
• Feature Fusion
• Hierarchical and Community-Based Fusion
• Kernel Fusion
• Late Fusion
• Legal, Ethical and Social Concepts of Fusion
• Metric Spaces
• Multimodal Fusion
• Normalization for Fusion
• Social Media Fusion and Mining

• University Politehnica of Bucharest, Romania

  Bogdan Ionescu

• University of Bordeaux, Talence, France

  Jenny Benois-Pineau

• Queen Mary University of London, London, United Kingdom

  Tomas Piatrik

• Lab. of Informatics of Grenoble, France

  Georges Quénot

Dr. Bogdan Ionescu is a lecturer and Coordinator of the Video Processing Group at the Image Processing and Analysis Laboratory, University Politehnica of Bucharest, Romania. Dr. Jenny Benois-Pineau is a full professor and Chair of the Video Analysis and Indexing research group at the University of Bordeaux, France. Dr. Tomas Piatrik is a senior researcher in the Multimedia and Vision Research Group at Queen Mary University of London, UK. Dr. Georges Quénot is a senior researcher at CNRS and leader of the Multimedia Information Modeling and Retrieval group at the Grenoble Informatics Laboratory, France.

Policies and ethics