This paper presents a novel approach for tracking humans and objects under severe occlusion. We introduce a new paradigm for multiple hypotheses tracking, observe-and-explain, as ...
In this paper we propose an approach for action recognition based on a vocabulary forest of local motionappearance features. Large numbers of features with associated motion vecto...
Restoration of a degraded image from motion blurring is highly dependent on the estimation of the blurring kernel. Most of the existing motion deblurring techniques model the blur...
This paper presents a method for recognizing human actions based on pose primitives. In learning mode, the parameters representing poses and activities are estimated from videos. ...
Rigid registration of intraoperative ultrasound (US) and CT is an important technique to provide real-time guidance for preoperative images and models. Due to the speckle noise an...