We propose a linear programming relaxation scheme for the class of multiple object tracking problems where the inter-object interaction metric is convex and the intraobject term q...
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...
The Object Constraint Language (OCL) is part of the Unified Modeling Language (UML) to specify restrictions on values of a given UML model. As part of the UML 2.0 standardization ...
In this paper, we proposed a fast and accurate human pose estimation framework that combines top-down and bottom-up methods. The framework consists of an initialization stage and a...
Yanchao Su, Haizhou Ai, Takayoshi Yamashita, Shiho...
We propose a novel formulation of stereo matching that considers each pixel as a feature vector. Under this view, matching two or more images can be cast as matching point clouds i...