In this paper, we propose an algorithm for estimating dense depth information of dynamic scenes from multiple video streams captured using unsynchronized stationary cameras. We so...
Abstract. We use a simple yet powerful higher-order conditional random field (CRF) to model optical flow. It consists of a standard photoconsistency cost and a prior on affine mo...
This paper presents a unified approach to human activity capturing and recognition. It targets applications such as a speaker walking, turning around, sitting and getting up from ...
We propose a novel learning algorithm to detect moving pedestrians from a stationary camera in real-time. The algorithm learns a discriminative model based on eigenflow, i.e. the ...
This paper describes algorithms for the animation of men and women performing three dynamic athletic behaviors: running, bicycling, and vaulting. We animate these behaviors using ...
Jessica K. Hodgins, Wayne L. Wooten, David C. Brog...