We present an active learning approach to choose image annotation requests among both object category labels and the objects’ attribute labels. The goal is to solicit those labe...
Segmentation of video objects from background is a popular computer vision problem and has many important applications. Most existing methods are either computationally expensive ...
— An algorithm for tracking articulating objects from moving camera platforms is presented. Mixtures of mixtures are used to model the appearance of the object and the background...
Wael Abd-Almageed, Mohamed E. Hussein, Larry S. Da...
One of the key research issues with moving objects databases (MOD) is the uncertainty management problem. In this paper, we discuss how the uncertainty of network constrained movin...
Abstract. This paper presents viewpoint-dependent constraints that relate image features such as t-junctions and inflections to the pose of curved 3D objects. These constraints can...