We present an approach to tracking human activities in a monocular video. We model the human body by decomposing it into torso and limbs and use simple 3D shapes to approximate th...
In this paper, we propose a new manifold representation capable of being applied for visual speech recognition. In this regard, the real time input video data is compressed using P...
Dahai Yu, Ovidiu Ghita, Alistair Sutherland, Paul ...
Abstract. In this paper, we introduce background cut, a high quality and realtime foreground layer extraction algorithm. From a single video sequence with a moving foreground objec...
Reliably recovering 3D human pose from monocular video requires models that bias the estimates towards typical human poses and motions. We construct priors for people tracking usi...
This paper presents a novel approach to control the augmented reality (AR) objects robustly in a marker-less AR system by fingertip tracking and hand pattern recognition. It is kn...