Advertisement

Human Centric Visual Analysis with Deep Learning

  • Liang Lin
  • Dongyu Zhang
  • Ping Luo
  • Wangmeng Zuo
Book

Table of contents

  1. Front Matter
    Pages i-xii
  2. Motivation and Overview

    1. Front Matter
      Pages 1-1
    2. Liang Lin, Dongyu Zhang, Ping Luo, Wangmeng Zuo
      Pages 3-13
    3. Liang Lin, Dongyu Zhang, Ping Luo, Wangmeng Zuo
      Pages 15-25
  3. Localizing Persons in Images

    1. Front Matter
      Pages 27-28
    2. Liang Lin, Dongyu Zhang, Ping Luo, Wangmeng Zuo
      Pages 29-45
    3. Liang Lin, Dongyu Zhang, Ping Luo, Wangmeng Zuo
      Pages 47-54
  4. Parsing Person in Detail

    1. Front Matter
      Pages 55-57
    2. Liang Lin, Dongyu Zhang, Ping Luo, Wangmeng Zuo
      Pages 59-68
    3. Liang Lin, Dongyu Zhang, Ping Luo, Wangmeng Zuo
      Pages 69-83
    4. Liang Lin, Dongyu Zhang, Ping Luo, Wangmeng Zuo
      Pages 85-93
  5. Identifying and Verifying Persons

    1. Front Matter
      Pages 95-98
    2. Liang Lin, Dongyu Zhang, Ping Luo, Wangmeng Zuo
      Pages 99-114
    3. Liang Lin, Dongyu Zhang, Ping Luo, Wangmeng Zuo
      Pages 115-130
  6. Higher Level Tasks

    1. Front Matter
      Pages 131-133
    2. Liang Lin, Dongyu Zhang, Ping Luo, Wangmeng Zuo
      Pages 135-156

About this book

Introduction

This book introduces the applications of deep learning 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.

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.

Keywords

Deep Learning Visual Analysis Human Centric Computing Object Recognition and Detection Computer Vision

Authors and affiliations

  • Liang Lin
    • 1
  • Dongyu Zhang
    • 2
  • Ping Luo
    • 3
  • Wangmeng Zuo
    • 4
  1. 1.School of Data and Computer ScienceSun Yat-sen UniversityGuangzhouChina
  2. 2.School of Data and Computer ScienceSun Yat-sen UniversityGuangzhouChina
  3. 3.School of Information EngineeringThe Chinese University of Hong KongHong KongHong Kong
  4. 4.School of Computer ScienceHarbin Institute of TechnologyHarbinChina

Bibliographic information

  • DOI https://doi.org/10.1007/978-981-13-2387-4
  • Copyright Information Springer Nature Singapore Pte Ltd. 2020
  • Publisher Name Springer, Singapore
  • eBook Packages Computer Science
  • Print ISBN 978-981-13-2386-7
  • Online ISBN 978-981-13-2387-4
  • Buy this book on publisher's site