Video Mining

1. Front Matter

   Pages i-ix

   PDF

2. Efficient Video Browsing

   • Arnon Amir, Savitha Srinivasan, Dulce Ponceleon

   Pages 1-30

3. Beyond Key-Frames: The Physical Setting as a Video Mining Primitive

   • Aya Aner-Wolf, John R. Kender

   Pages 31-60

4. Temporal Video Boundaries

   • Nevenka Dimitrova, Lalitha Agnihotri, Radu Jasinschi

   Pages 61-90

5. Video Summarization Using Mpeg-7 Motion Activity and Audio Descriptors

   • Ajay Divakaran, Kadir A. Peker, Regunathan Radhakrishnan, Ziyou Xiong, Romain Cabasson

   Pages 91-121

6. Movie Content Analysis, Indexing and Skimming Via Multimodal Information

   • Ying Li, Shrikanth Narayanan, C.-C. Jay Kuo

   Pages 123-154

7. Video OCR: A Survey And Practitioner’s Guide

   • Rainer Lienhart

   Pages 155-183

8. Video Categorization Using Semantics and Semiotics

   • Zeeshan Rasheed, Mubarak Shah

   Pages 185-217

9. Understanding the Semantics of Media

   • Malcolm Slaney, Dulce Ponceleon, James Kaufman

   Pages 219-252

10. Statistical Techniques for Video Analysis and Searching

    • John R. Smith, Ching-Yung Lin, Milind Naphade, Apostol Paul Natsev, Belle Tseng

    Pages 253-277

11. Unsupervised Mining of Statistical Temporal Structures in Video

    • Lexing Xie, Shih-Fu Chang, Ajay Divakaran, Huifang Sun

    Pages 279-307

12. Pseudo-Relevance Feedback for Multimedia Retrieval

    • Rong Yan, Alexander G. Hauptmann, Rong Jin

    Pages 309-338

13. Back Matter

    Pages 339-340

    PDF

Traditionally, scientific fields have defined boundaries, and scientists work on research problems within those boundaries. However, from time to time those boundaries get shifted or blurred to evolve new fields. For instance, the original goal of computer vision was to understand a single image of a scene, by identifying objects, their structure, and spatial arrangements. This has been referred to as image understanding. Recently, computer vision has gradually been making the transition away from understanding single images to analyzing image sequences, or video Video understanding deals with understanding of video understanding. sequences, e.g., recognition of gestures, activities, facial expressions, etc. The main shift in the classic paradigm has been from the recognition of static objects in the scene to motion-based recognition of actions and events. Video understanding has overlapping research problems with other fields, therefore blurring the fixed boundaries. Computer graphics, image processing, and video databases have obvi­ ous overlap with computer vision. The main goal of computer graphics is to generate and animate realistic looking images, and videos. Re­ searchers in computer graphics are increasingly employing techniques from computer vision to generate the synthetic imagery. A good exam­ pIe of this is image-based rendering and modeling techniques, in which geometry, appearance, and lighting is derived from real images using computer vision techniques. Here the shift is from synthesis to analy­ sis followed by synthesis. Image processing has always overlapped with computer vision because they both inherently work directly with images.

• Audio
• Frames
• information
• multimedia
• optical character recognition (OCR)
• production
• video
• video mining
• video on demand

• University of Maryland, College Park, USA

  Azriel Rosenfeld, David Doermann, Daniel DeMenthon

Policies and ethics