1 citations · 2 across the 3 of their papers we have counts for
3 papers
Trajectory Optimization for Physics-Based Reconstruction of 3d Human Pose from Monocular Video
Erik Gärtner, Mykhaylo Andriluka, Hongyi Xu +1
We focus on the task of estimating a physically plausible articulated human motion from monocular video. Existing approaches that do not consider physics often produce temporally i…
Embodied Learning for Lifelong Visual Perception
David Nilsson, Aleksis Pirinen, Erik Gärtner +1
We study lifelong visual perception in an embodied setup, where we develop new models and compare various agents that navigate in buildings and occasionally request annotations whi…
Deep Reinforcement Learning for Active Human Pose Estimation
Erik Gärtner, Aleksis Pirinen, Cristian Sminchisescu
Most 3d human pose estimation methods assume that input -- be it images of a scene collected from one or several viewpoints, or from a video -- is given. Consequently, they focus o…