Название: Graph Based Multimedia Analysis
Автор: Ananda S. Chowdhury, Abhimanyu Sahu
Издательство: Morgan Kaufmann/Elsevier
Год: 2024
Страниц: 370
Язык: английский
Формат: epub
Размер: 72.1 MB
Graph Based Multimedia Analysis applies concepts from graph theory to the problems of analyzing overabundant video data. Video data can be quite diverse: exocentric (captured by a standard camera) or egocentric (captured by a wearable device like Google Glass); of various durations (ranging from a few seconds to several hours); and could be from a single source or multiple sources. Efficient extraction of important information from such a large class of diverse video data can be overwhelming. The book, with its rich repertoire of theoretically elegant solutions, from graph theory in conjunction with deep learning, constrained optimization, and game theory, empowers the audience to achieve tasks like obtaining concise yet useful summaries and precisely recognizing single as well as multiple actions in a computationally efficient manner. The book provides a unique treatise on topics like egocentric video analysis and scalable video processing. This book provides a comprehensive and methodical approach to these challenges, underpinned by the rigorous and elegant framework of graph theory. It deftly bridges the gap between the somewhat disparate domains of video processing and graph theory, demonstrating how graph-based methodologies can effectively address critical problems in video summarization, cosummarization, and action recognition. The salient feature of this work is its extensive utilization of graph theoretical concepts. The book covers an impressive array of graph-based methods, including Delaunay graphs, Optimal Path-Forests, Bipartite Graph Matching, Graph Centrality measures, Graph Connectedness, Spectral Measures of Graph Similarity, Minimum Spanning Tree, and Random Walks. The integration of game-theoretic models, constrained optimization techniques, and advanced Deep Learning methods such as Convolutional Neural Networks and Transfer Learning, further enriches the suite of methods presented.
