Graph Based Multimedia Analysis
Auteurs : S Chowdhury Ananda, Sahu Abhimanyu
Graph Based Multimedia Analysis applies graph theory to the problems of analyzing an over-abundance of video data. Video data can be diverse: exocentric (captured by standard camera) or egocentric (captured by a wearable device like Google glass); of various durations; from multiple sources. Efficient extraction of important/useful information from such a large class of diverse inputs can be overwhelming. The book, with its rich repertoire of theoretically elegant solutions, empowers the audience to achieve tasks like obtaining concise yet useful summary and precisely recognizing single as well as multiple actions in a computationally efficient manner.
2. Theoretical Foundations
3. Exocentric Video Summarization
4. Multi-view Exocentric Video Summarization
5. Egocentric Video Summarization
6. Egocentric Video Co-summarization
7. Action Recognition in Egocentric Video
Dr. Ananda S. Chowdhury is a Professor and former Head in the Department of Electronics and Telecommunication Engineering at Jadavpur University, Kolkata, India, where he leads the Imaging, Vision and Pattern Recognition group. He received his Ph.D. degree in Computer Science from The University of Georgia, Athens, GA, USA and was a Postdoctoral Fellow at National Institutes of Health, Bethesda, MD, USA. He is a Senior Member of IEEE, and a Member of the International Association for Pattern Recognition Technical Committee (IAPR TC) on Graph based Representations. He has held invited academic visits to universities in France, Germany, Norway, Italy, The Netherlands, Singapore and Brazil. Dr. Chowdhury currently serves on the editorial boards of IEEE Transactions on Image Processing and Pattern Recognition Letters. His Erdös Number is two.
Dr. Abhimanyu Sahu is an Assistant Professor in the Department of Computer Science & Engineering at Motilal Nehru National Institute of Technology Allahabad, Prayagraj, India. He is a life member of ISTE. His current research interests include computer vision, multimedia analysis, and pattern recognition problems. Specifically, he is also interested in exploring different machine learning techniques (self-supervised/unsupervised learning, deep Learning) to solve several challenging problems in multimedia analysis such as summarization and action/object/activity recognition particularly in first-person (Egocentric) videos. He also worked on theoretical aspects of Graph-based modelings of the above fields.
- Addresses a number of challenging state-of-the-art problems in multimedia analysis like summarization, co-summarization, recognition
- Handles a wide class of video with different genres, durations, and numbers
- Applies a class of theoretically rich algorithms from the discipline of graph theory, in conjunction with deep learning and game theory
- Includes thorough complexity-analyses of the proposed solutions and an appendix containing implementable source codes
Date de parution : 09-2024
Ouvrage de 370 p.