This paper presents a novel domain-independent text segmentation method, which identifies the boundaries of topic changes in long text documents and/or text streams. The method c...
Depth estimation in computer vision and robotics is most commonly done via stereo vision (stereopsis), in which images from two cameras are used to triangulate and estimate distan...
In recent years, the eld of active-contour based image segmentation have seen the emergence of two competing approaches. The rst and oldest approach represents active contours in ...
This paper proposes a probabilistic graphical model for the problem of propagating labels in video sequences, also termed the label propagation problem. Given a limited amount of ...
Abstract. This paper presents a novel approach for object segmentation in medical images that respects the topological relationships of multiple structures as given by a template. ...