Abstract. Tree-structured models have been widely used for human pose estimation, in either 2D or 3D. While such models allow efficient learning and inference, they fail to capture...
In this paper we propose a new framework for modeling 2D shapes. A shape is first described by a sequence of local features (e.g., curvature) of the shape boundary. The resulting ...
We consider Gaussian multiresolution (MR) models in which coarser, hidden variables serve to capture statistical dependencies among the finest scale variables. Tree-structured MR ...
Myung Jin Choi, Venkat Chandrasekaran, Alan S. Wil...
We propose Laplace max-margin Markov networks (LapM3 N), and a general class of Bayesian M3 N (BM3 N) of which the LapM3 N is a special case with sparse structural bias, for robus...
Fusion of 3D laser radar (LIDAR) imagery and aerial optical imagery is an efficient method for constructing 3D virtual reality models. One difficult aspect of creating such models...