We present a method to classify and localize human actions in video using a Hough transform voting framework. Random trees are trained to learn a mapping between densely-sampled f...
We introduce a novel probabilistic approach for nonparametric nonrigid image registration using generalized elastic nets, a model previously used for topographic maps. The idea of...
Fitting statistical 2D and 3D shape models to images is necessary for a variety of tasks, such as video editing and face recognition. Much progress has been made on local fitting...
Traditional stereo matching algorithms are limited in their ability to produce accurate results near depth discontinuities, due to partial occlusions and violation of smoothness co...
—Evolutionary gradient search is a hybrid algorithm that exploits the complementary features of gradient search and evolutionary algorithm to achieve a level of efficiency and r...
Chi Keong Goh, Yew-Soon Ong, Kay Chen Tan, Eu Jin ...