Dacheng Tao – författare

Tensor signal processing is an emerging field with important applications to computer vision and image processing.

This book presents the state of the art in this new branch of signal processing, offering a great deal of research and discussions by leading experts in the area. The wide-ranging volume offers an overview into cutting-edge research into the newest tensor processing techniques and their application to different domains related to computer vision and image processing.

This comprehensive text will prove to be an invaluable reference and resource for researchers, practitioners and advanced students working in the area of computer vision and image processing.

This book has brought 24 groups of experts and active researchers around the world together in  image processing and analysis, video processing and analysis, and communications related processing, to present their newest research results, exchange latest experiences and insights, and explore future directions in these important and rapidly evolving areas. It aims at increasing the synergy between academic and industry professionals working in the related field. It focuses on the state-of-the-art research in various essential areas related to emerging technologies, standards and applications on analysis, processing, computing, and communication of multimedia information.

The target audience of this book is researchers and engineers as well as graduate students working in various disciplines linked to multimedia analysis, processing and communications, e.g., computer vision, pattern recognition, information technology, image processing, and artificial intelligence. The book is also meant to a broader audience including practicing professionals working in image/video applications such as image processing, video surveillance, multimedia indexing and retrieval, and so on. We hope that the researchers, engineers, students and other professionals who read this book would find it informative, useful and inspirational toward their own work in one way or another.  

Deep learning has significantly reshaped a variety of technologies, such as image processing, natural language processing, and audio processing. The excellent generalizability of deep learning is like a “cloud” to conventional complexity-based learning theory: the over-parameterization of deep learning makes almost all existing tools vacuous. This irreconciliation considerably undermines the confidence of deploying deep learning to security-critical areas, including autonomous vehicles and medical diagnosis, where small algorithmic mistakes can lead to fatal disasters. This book seeks to explaining the excellent generalizability, including generalization analysis via the size-independent complexity measures, the role of optimization in understanding the generalizability, and the relationship between generalizability and ethical/security issues. 

The efforts to understand the excellent generalizability are following two major paths: (1) developing size-independent complexity measures, which can evaluate the “effective” hypothesis complexity that can be learned, instead of the whole hypothesis space; and (2) modelling the learned hypothesis through stochastic gradient methods, the dominant optimizers in deep learning, via stochastic differential functions and the geometry of the associated loss functions. Related works discover that over-parameterization surprisingly bring many good properties to the loss functions. Rising concerns of deep learning are seen on the ethical and security issues, including privacy preservation and adversarial robustness. Related works also reveal an interplay between them and generalizability: a good generalizability usually means a good privacy-preserving ability; and more robust algorithms might have a worse generalizability.

 We expect readers can have a big picture of the current knowledge in deep learning theory, understand how the deep learning theory can guide new algorithm designing, and identify future research directions. Readers need knowledge of calculus, linear algebra, probability, statistics, and statistical learning theory.