In this paper we propose a new framework for modeling 2D shapes. A shape is first described by a sequence of local features (e.g., curvature) of the shape boundary. The resulting ...
We propose a principled framework to model persistent motion in dynamic scenes. In contrast to previous efforts on object tracking and optical flow estimation that focus on local...
We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a lowdimensional embedding of the pose manifol...
Tobias Jaeggli, Esther Koller-Meier, Luc J. Van Go...
: Online communities are islands of people and topics that are not interlinked. Complementary discussions exist on disparate systems but it is currently difficult to exploit the av...
John G. Breslin, Stefan Decker, Andreas Harth, Uld...
We address the problem of unsupervised segmentation and grouping in 2D and 3D space, where samples are corrupted by noise, and in the presence of outliers. The problem has attract...