High-level generative models provide elegant descriptions of videos and are commonly used as the inference framework in many unsupervised motion segmentation schemes. However, app...
It has been demonstrated by Serre et al. that the biologically inspired model (BIM) is effective for object recognition. It outperforms many state-of-the-art methods in challengin...
Studies support the need for high resolution imagery to identify persons in surveillance videos[13]. However, the use of telephoto lenses sacrifices a wider field of view and ther...
Graphical models such as Bayesian Networks (BNs) are being increasingly applied to various computer vision problems. One bottleneck in using BN is that learning the BN model param...
Pairwise constraints specify whether or not two samples should be in one cluster. Although it has been successful to incorporate them into traditional clustering methods, such as ...