Название: Human Centric Visual Analysis with Deep Learning Автор: Liang Lin, Dongyu Zhang
Издательство: Springer
Год: 2020
Страниц: 160
Язык: английский
Формат: pdf (true)
Размер: 10.1 MB
This book introduces the applications of Deep Learning (DL) in various human centric visual analysis tasks, including classical ones like face detection and alignment and some newly rising tasks like fashion clothing parsing. Starting from an overview of current research in human centric visual analysis, the book then presents a tutorial of basic concepts and techniques of Deep Learning. In addition, the book systematically investigates the main human centric analysis tasks of different levels, ranging from detection and segmentation to parsing and higher-level understanding. At last, it presents the state-of-the-art solutions based on Deep Learning for every task, as well as providing sufficient references and extensive discussions.
Specifically, this book addresses four important research topics, including 1) localizing persons in images, such as face and pedestrian detection; 2) parsing persons in details, such as human pose and clothing parsing, 3) identifying and verifying persons, such as face and human identification, and 4) high-level human centric tasks, such as person attributes and human activity understanding.
In this book, we will provide an in-depth summary of recent progress in human-centric visual analysis based on deep learning methods. The book is organized into five parts. In the first part, Chap. 1 first provides the background of deep learning methods including a short review of the development of artificial neural networks and the backpropagation method to give the reader a better understanding of certain deep learning concepts. We also introduce a new technique for the training of deep neural networks. Subsequently, in Chap. 2, we provide an overview of the tasks and the current progress of human-centric visual analysis...
This book can serve as reading material and reference text for academic professors/students or industrial engineers working in the field of vision surveillance, biometrics, and human-computer interaction, where human centric visual analysis are indispensable in analysing human identity, pose, attributes, and behaviours for further understanding.
Скачать Human Centric Visual Analysis with Deep Learning