Search Results for author:
Found 3 papers, 2 papers with code
Plausible Uncertainties for Human Pose Regression
Here, we propose a straightforward human pose regression framework to examine the behavior of two established methods for simultaneous aleatoric and epistemic uncertainty estimation: maximum a-posteriori (MAP) estimation with Monte-Carlo variational inference and deep evidential regression (DER).
PedRecNet: Multi-task deep neural network for full 3D human pose and orientation estimation
We present a multitask network that supports various deep neural network based pedestrian detection functions.
Ranked #198 on
3D Human Pose Estimation
on Human3.6M
Simple yet efficient real-time pose-based action recognition
Recognizing human actions is a core challenge for autonomous systems as they directly share the same space with humans.
