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...
Developing an efficient object localization system for complicated industrial objects is an important, yet difficult robotic task. To tackle this problem, we have developed a syst...
We consider the problem of recognizing an object from its silhouette. We focus on the case in which the camera translates, and rotates about a known axis parallel to the image, suc...
In this paper, we address a challenging image segmentation problem called multiple foreground cosegmentation (MFC), which concerns a realistic scenario in general Webuser photo se...
Background: Mean-based clustering algorithms such as bisecting k-means generally lack robustness. Although componentwise median is a more robust alternative, it can be a poor cent...
Yuanyuan Ding, Xin Dang, Hanxiang Peng, Dawn Wilki...