High-level generative models provide elegant descriptions of videos and are commonly used as the inference framework in many unsupervised motion segmentation schemes. However, app...
Capacity scaling is a hierarchical approach to graph representation that can improve theoretical complexity and practical efficiency of max-flow/min-cut algorithms. Introduced by ...
Given a set of n points S in the plane, a triangulation of S is a subdivision of the convex hull into triangles whose vertices are from S. In the kinetic setting, the input point ...
It is crucial in many information systems to organize short text segments, such as keywords in documents and queries from users, into a well-formed topic hierarchy. In this paper,...
This paper presents a robust object tracking method via a spatial bias appearance model learned dynamically in video. Motivated by the attention shifting among local regions of a ...