We present an algorithm for jointly learning a consistent bidirectional generative-recognition model that combines top-down and bottom-up processing for monocular 3d human motion ...
Cristian Sminchisescu, Atul Kanaujia, Dimitris N. ...
We consider the fully automated recognition of actions in uncontrolled environment. Most existing work relies on domain knowledge to construct complex handcrafted features from in...
In this paper, we propose a Bayesian approach to video object segmentation. Our method consists of two stages. In the first stage, we partition the video data into a set of 3D wate...
Visual-geometric scene reconstructions capture the visual appearance and geometry of real 3D scenes from image streams. Depending on the type of camera motion and type of scene st...
The importance of faces in human interaction explains the desire for synthetic faces as a communication vehicle in computer graphics. Unfortunately, animating a face is a very com...