Data-driven robust human action recognition

Jian Liu

Research output: Thesis › Doctoral Thesis

360 Downloads (Pure)

Abstract

Human action recognition has wide applications in security, entertainment, sports, and medicine. It is very challenging to develop robust action recognition models for real-life scenarios, where human movements are associated with numerous irrelevant variations such as viewpoints, backgrounds, and illuminations. This thesis proposes novel data-driven methods to address the fundamental problems in robust action recognition, including human data synthesis, spatio-temporal representation, action classification, and human pose recovery. Besides, the adversarial robustness of human action recognition is investigated in this thesis.
Original languageEnglish
QualificationDoctor of Philosophy
Awarding Institution
  • The University of Western Australia
Supervisors/Advisors
  • Mian, Ajmal, Supervisor
  • Akhtar, Naveed, Supervisor
Thesis sponsors
Award date26 Jan 2020
DOIs
Publication statusUnpublished - 2020

Access to Document

  • THESIS_DOCTOR_OF_PHILOSOPHY_LIU_Jian

    This work is protected by Copyright. You may print or download ONE copy of this document for the purpose of your own non-commercial research or study. Any other use requires permission from the copyright owner. The Copyright Act requires you to attribute any copyright works you quote or paraphrase.

    Fingerprint Dive into the research topics of 'Data-driven robust human action recognition'. Together they form a unique fingerprint.

    Cite this