Pamuditha Somarathne
PhD Student
I am a PhD student working at the intersection of human-centered AI and machine learning, with a focus on modeling and understanding human motion. My research explores representation learning methods for predicting, synthesizing, and analyzing human movement from multimodal and biological signals, aiming to enable accurate pose estimation and robust motion understanding in realistic, interactive settings. I am also interested in biological signal processing, including applications of PPG and PCG for health monitoring.
Research Interests
Publications
A Dual Classifier-Regressor Architecture for Heart Sound Onset/Offset Detection
P Somarathne, S Herath, G Gargiulo, P Breen, N Anderson, Y Yao, T Liu, A Withana
Just Before Touch: Manipulating Perceived Haptic Sensations through Proactive Vibrotactile Cues in Virtual Reality
Y Dong, P Somarathne, CT Jin, J Kim, A Bianchi, A Withana
NeverLagging: Enhancing Virtual Reality Finger Tracking with a Physics-Inspired Time-Agnostic Graph Neural Network
T Li, P Somarathne, Z Sarsenbayeva, A Withana
TA-GNN: Physics Inspired Time-Agnostic Graph Neural Network for Finger Motion Prediction
T Li, P Somarathne, Z Sarsenbayeva, A Withana
Efficient and Robust Heart Rate Estimation Approach for Noisy Wearable PPG Sensors Using Ideal Representation Learning
A Niwarthana, P Somarathne, P Qian, KT Yong, A Withana
PairPlayVR: Shared Hand Control for Virtual Games
H Zhou, P Somarathne, TA Peirispulle, C Fan, Z Sarsenbayeva, ...