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 pri...
For handwritten character recognition, a new elastic image matching (EM) technique based on a class-dependent deformation model is proposed. In the deformation model, any deformat...
Figure 1 Flowers expanded using self-similarity based texture warping. We present a simple method of interactive texture editing that utilizes self-similarity to replicate intende...
We propose a simple framework that utilizes online appearance models for 3D face and facial feature tracking with a deformable model. Adapting the geometrical parameters for each ...
This paper addresses action spotting, the spatiotemporal detection and localization of human actions in video. A novel compact local descriptor of video dynamics in the context of...
Konstantinos Derpanis, Mikhail Sizintsev, Kevin Ca...