no code implementations • ICCV 2023 • Lennart Bramlage, Michelle Karg, Cristóbal Curio
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).
1 code implementation • 25 Apr 2022 • Dennis Burgermeister, Cristóbal Curio
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
1 code implementation • 19 Apr 2019 • Dennis Ludl, Thomas Gulde, Cristóbal Curio
Recognizing human actions is a core challenge for autonomous systems as they directly share the same space with humans.