Shanaka Ramesh Gunasekara

I am a Computer Vision Scientist and Engineer at RMIT, where I develop computer vision and AI-based solutions to address real-world industry challenges.

I completed my PhD in Computer Science and Engineering at the Advanced Multimedia Research Lab, University of Wollongong, Australia, under the supervision of Prof. Wanqing Li.

My doctoral research focused on spatiotemporal representation learning for human motion analysis using 3D skeleton sequences, with applications in human action recognition and person identification. I have worked on projects involving Convolutional Neural Networks (CNNs), Graph Convolutional Networks (GCNs), Transformers, and Generative AI, including diffusion models for motion analysis.

Prior to my PhD, I worked as a Research Engineer at the Department of Electrical and Electronic Engineering at the University of Peradeniya, Sri Lanka, where I also completed my B.Sc.Eng. (Hons) in Electrical and Electronic Engineering in 2019. My work there covered medical image analysis, low-light object detection, and control systems for robotic manipulators.