Visual dictionaries are widely employed in object recognition to map unordered bags of local region descriptors into feature vectors for image classification. Most visual dictiona...
We present a novel object-specific segmentation method which can be used in view-based object recognition systems. Previous object segmentation approaches generate inexact results ...
Minsu Cho (Seoul National University), Kyoung Mu L...
In this paper we propose an efficient, non-iterative method for estimating optical flow. We develop a probabilistic framework that is appropriate for describing the inherent uncer...
By mapping a set of input images to points in a lowdimensional manifold or subspace, it is possible to efficiently account for a small number of degrees of freedom. For example, i...
In this paper, we present a novel maximum correlation sample subspace method and apply it to human face detection [1] in still images. The algorithm starts by projecting all the t...