Model learning for structured predictions from complementary data sources

Uzair Nadeem

Research output: ThesisDoctoral Thesis

402 Downloads (Pure)

Abstract

This dissertation explores novel model learning approaches to advance human brain-like capabilities of solving intricate tasks by simultaneously processing multiple information sources. It proposes an efficient self-supervised classification technique for set-based samples with no training requirements. It also develops a robust deep model for improved multimodal classification. Furthermore, it proposes a learning-based method to estimate any classifier's confidence and uses it for enhanced multimodal analyses. Lastly, a novel approach is presented for direct cross-modality feature matching. The developed techniques are evaluated for numerous applications including face recognition, surveillance, coral classification, emotion analysis and image pose localization, with significant performance gains.
Original languageEnglish
QualificationDoctor of Philosophy
Awarding Institution
  • The University of Western Australia
Supervisors/Advisors
  • Bennamoun, Mohammed, Supervisor
  • Togneri, Roberto, Supervisor
  • Sohel, Ferdous, Supervisor
Award date15 Dec 2020
DOIs
Publication statusUnpublished - 2020

Fingerprint

Dive into the research topics of 'Model learning for structured predictions from complementary data sources'. Together they form a unique fingerprint.

Cite this