Pose tracking
We develop probabilistic machine learning models to reconstruct pose graphs from video and automatically classify behavior. We collaborate with Prof. James Cotton and the startup StriaTech.
Lab members are shown in this color.
2025
|
James R. Cotton, Fabian H. Sinz
Biomechanical Reconstruction with Confidence Intervals from Multiview Markerless Motion Capture
EMBC 2025 fully contributed paper
|
2024
|
Pawel A. Pierzchlewicz, Caio da Silva, James Cotton, Fabian H. Sinz
Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimation
arXiv
|
2023
|
Paweł A. Pierzchlewicz, Mohammad Bashiri, R. James Cotton, Fabian H. Sinz
Optimizing MPJPE promotes miscalibration in multi-hypothesis human pose lifting
ICLR - tiny paper
|
2022
|
Paweł A. Pierzchlewicz, R. James Cotton, Mohammad Bashiri, Fabian H. Sinz
Multi-hypothesis 3D human pose estimation metrics favor miscalibrated distributions
arXiv
|