We present a fully-automated method for real-time and marker-free 3D human motion capture. The system computes the 3D shape of the person filmed from a synchronized camera set. We...
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. ...
Abstract. Using silhouettes in uncontrolled environments typically requires handling occlusions as well as changing or cluttered backgrounds, which limits the applicability of most...
This paper presents a learning-based method for combining the shape and appearance feature types for 3D human pose estimation from single-view images. Our method is based on clust...
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...