We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor pr...
Many computer vision systems try to infer semantic information about a video scene content by looking at the time series of the silhouettes of the moving objects. This paper propo...
Changes in motion properties of trajectories provide useful cues for modeling and recognizing human activities. We associate an event with significant changes that are localized in...
Naresh P. Cuntoor, B. Yegnanarayana, Rama Chellapp...
— In this paper, we present an approach that allows a robot to observe, generalize, and reproduce tasks observed from multiple demonstrations. Motion capture data is recorded in ...
We present a novel representation and rendering method for free-viewpoint video of human characters based on multiple input video streams. The basic idea is to approximate the art...
Marcel Germann, Alexander Hornung, Richard Keiser,...