We propose a highly efficient framework for penalized likelihood kernel methods applied to multiclass models with a large, structured set of classes. As opposed to many previous a...
Multiple observation improves the performance of 3D object classification. However, since the distribution of feature vectors obtained from multiple view points have strong nonlin...
This paper presents a novel method for image classification. It differs from previous approaches by computing image similarity based on region matching. Firstly, the images to be ...
Atypical observations, which are called outliers, are one of difficulties to apply standard Gaussian density based pattern classification methods. Large number of outliers makes di...
In this paper, a new learning framework?probabilistic boosting-tree (PBT), is proposed for learning two-class and multi-class discriminative models. In the learning stage, the pro...