We present a method for optimizing the stereo matching process when it is applied to a series of images with similar depth structures. We observe that there are similar regions wit...
We propose a family of learning algorithms based on a new form of regularization that allows us to exploit the geometry of the marginal distribution. We focus on a semi-supervised...
In this paper, we deal with a generative model for multi-label, interactive segmentation. To estimate the pixel likelihoods for each label, we propose a new higher-order formulatio...
Tae Hoon Kim (Seoul National University), Kyoung M...
For supervised and unsupervised learning, positive definite kernels allow to use large and potentially infinite dimensional feature spaces with a computational cost that only depe...
We describe efficient techniques for construction of large term co-occurrence graphs, and investigate an application to the discovery of numerous fine-grained (specific) topics. A...