We propose a category-independent method to produce a bag of regions and rank them, such that top-ranked regions are likely to be good segmentations of different objects. Our key ...
We present a new unsupervised method to learn unified probabilistic object models (POMs) which can be applied to classification, segmentation, and recognition. We formulate this a...
Yuanhao Chen, Long Zhu, Alan L. Yuille, HongJiang ...
In this paper we propose a new probabilistic relaxation framework to perform robust multiple motion estimation and segmentation from a sequence of images. Our approach uses displa...
Abstract. We present a novel approach to statistically characterize histograms of model-relative image regions. A multiscale model is used as an aperture to define image regions a...
Robert E. Broadhurst, Joshua Stough, Stephen M. Pi...
As IKONOS satellite with 1m-resolution camera has been launched in 1999, mapping using space-borne images will be a hot issue in computer vision area as well as photogrammetry, ma...
Hae-Yeoun Lee, Heung-Kyu Lee, Tak-gon Kim, Wonkyu ...