We propose a novel probabilistic framework for learning
visual models of 3D object categories by combining appearance
information and geometric constraints. Objects are
represen...
This paper proposes a novel hierarchical learning strategy to deal with the data sparseness problem in relation extraction by modeling the commonality among related classes. For e...
We present a hierarchical generative model for object recognition that is constructed by weakly-supervised learning. A key component is a novel, adaptive patch feature whose width...
We develop improved risk bounds for function estimation with models such as single hidden layer neural nets, using a penalized least squares criterion to select the size of the mod...
: Fast and accurate collision detection between general solid models is a fundamental problem in solid modeling, robotics, animation and computer-simulated environments. Most of th...