We introduce the problem of repetitive nearest neighbor search in relevance feedback and propose an efficient search scheme for high dimensional feature spaces. Relevance feedback...
The likelihood models used in probabilistic visual tracking applications are often complex non-linear and/or nonGaussian functions, leading to analytically intractable inference. ...
We propose a geometric approach to 3-D motion segmentation from point correspondences in three perspective views. We demonstrate that after applying a polynomial embedding to the ...
A novel statistical method is proposed in this paper to overcome abrupt motion for robust visual tracking. Existing tracking methods that are based on the small motion assumption ...
The problem of estimating an illumination distribution from images is called inverse lighting. For inverse lighting, three approaches have been developed based on specular reflect...