This paper describes a system that can annotate a video sequence with: a description of the appearance of each actor; when the actor is in view; and a representation of the actorâ...
— We consider the problem of ï¬nding sufï¬ciently simple models of high-dimensional physical systems that are consistent with observed trajectories, and using these models to s...
We propose a method to recover the global structure with local details around a point. To handle a large scale of motion i.e. 360 degree around the point, we use an optimization-b...
Siu-Hang Or, Kin-hong Wong, Michael Ming-Yuen Chan...
We present a fast and robust system for estimating structure
and motion using a stereo pair, with straight lines as
features. Our first set of contributions are efficient algorit...
Abstract. Humans demonstrate a remarkable ability to parse complicated motion sequences into their constituent structures and motions. We investigate this problem, attempting to le...