Marsha Mariya Kappan
PhD Researcher
Autonomous Agents and Robotics Research Group
UNSW Sydney, Australia

Address
School of Computer Science and Engineering
Ainsworth Building (J17) - Desk 510-15
Kensington Campus
UNSW Sydney
NSW 2052, Australia

Contact
Email: m.marsha_mariya_kappan@unsw.edu.au

Research interests

• Neural Networks / Deep Learning
• Computer Vision

Useful links

• LinkedIn profile
• OrcID profile

Short bio: I hold a Bachelor’s and Master’s degree in Computer Science and Engineering and am currently a third-year PhD candidate at the University of New South Wales (UNSW), Sydney. My research interests lie in Deep Learning, Computer Vision, and Artificial Intelligence.

My work focuses on developing advanced methods for human pose estimation and activity monitoring under challenging real-world conditions, particularly in the presence of occlusions. I explore how modern deep learning techniques can be combined with probabilistic modelling, temporal reasoning, and generative approaches to improve the robustness and reliability of pose estimation systems. Currently, I am working on occlusion-aware 3D pose estimation models that can generate accurate and reliable predictions even when body joints are partially hidden. My broader goal is to design efficient pose estimation systems for applications in activity monitoring, and safety-critical environments and human-robot interaction.

Selected Publications	Web
Kappan, M. M., Sandoval, E. B., Meijering, E., & Cruz, F. (2026). A survey on deep learning for 2D and 3D human pose estimation. Artificial Intelligence Review, 59(1), 32.
Zhao, H., Kappan, M. M., Bamdad, M., & Cruz, F. (2025). LAPX: Lightweight Hourglass Network with Global Context. In Proceedings of the Australasian Conference on Robotics and Automation (ACRA), 2025.
Kappan, M. M., Sandoval, E. B., Meijering, E., & Cruz, F. (2024). Attention-enhanced lightweight hourglass network for human pose estimation. In Proceedings of the Australasian Conference on Robotics and Automation (ACRA), 2024..