Human Centric Visual Analysis with Deep Learning

This book introduces the applications of deep learning in various human centric visual analysis tasks, including classical ones, like face detection and alignment and newly arising tasks, like fashion clothing parsing. Starting from an overview of current research in human centric visual analysis, the book then presents a tutorial on the basic concepts and techniques of deep learning. In addition, it systematically investigates the main human-centric analysis tasks at different levels, ranging from detection and segmentation to parsing and higher-level understanding. Lastly, it presents state-of-the-art solutions based on deep learning for every task, and provides extensive references and discussions. Specifically, this book addresses four important research topics: 1) localizing people in images, such as face and pedestrian detection; 2) parsing people in details, such as human pose and clothing parsing, 3) identifying and verifying people, such as face and human identification, and 4) high-level human-centric tasks, such as person attributes and human activity understanding. It serves as a reference text for academic professors / students and industrial engineers working in the field of vision surveillance, biometrics, and human-computer interaction, where human centric visual analysis is indispensable in providing a better understanding of analysing human identity, pose, attributes, and behaviours.