Non-rigid object detection and articulated pose estimation
are two related and challenging problems in computer
vision. Numerous models have been proposed over the
years and oft...
Mykhaylo Andriluka (TU Darmstadt), Stefan Roth (TU...
Markerless tracking of human pose is a hard yet relevant problem. In this paper, we derive an efficient filtering algorithm for tracking human pose at 4-10 frames per second using...
Varun Ganapathi, Christian Plagemann, Sebastian Th...
It is difficult to apply machine learning to new domains because often we lack labeled problem instances. In this paper, we provide a solution to this problem that leverages domai...
Recognizing humans, estimating their pose and segmenting their body parts are key to high-level image understanding. Because humans are highly articulated, the range of deformation...
A novel procedure is presented to construct image-domain filters (receptive fields) that directly recover local motion and shape parameters. These receptive fields are derived fro...