Existing object tracking algorithms generally use some form of local optimisation, assuming that an object's position and shape change smoothly over time. In some situations ...
Abstract This paper proposes a real-time high-precision method to track an unknown face in front of an information system by selecting appropriate model to a video image. Active Ap...
We demonstrate a system capable of tracking, in real world image sequences, landmarks such as eyes, mouth, or chin on a face. In the standard version, knowledge previously collect...
Traditional video scene analysis depends on accurate background modeling to identify salient foreground objects. However, in many important surveillance applications, saliency is ...
Brian Valentine, Senyo Apewokin, Linda M. Wills, D...
We present a probabilistic generative model of visual attributes, together with an efficient learning algorithm. Attributes are visual qualities of objects, such as ‘red’, ...