Decomposing video frames into coherent two-dimensional motion layers is a powerful method for representing videos. Such a representation provides an intermediate description that e...
Active Shape Model (ASM) is one of the most popular methods for image alignment. To improve its matching accuracy, in this paper, ASM searching method is combined with a simplifie...
Human activity recognition and speech recognition appear to be two loosely related research areas. However, on a careful thought, there are several analogies between activity and ...
We propose a novel Active Volume Model (AVM) which deforms in a free-form manner to minimize energy. Unlike Snakes and level-set active contours which only consider curves or surfa...
We propose a framework to learn statistical shape models for faces as piecewise linear models. Specifically, our methodology builds upon primitive active shape models(ASM) to hand...