Parameterized Appearance Models (PAMs) (e.g. eigentracking, active appearance models, morphable models) use Principal Component Analysis (PCA) to model the shape and appearance of...
We propose a novel and robust model to represent and learn generic 3D object categories. We aim to solve the problem of true 3D object categorization for handling arbitrary rotati...
The invariance of the similarity measure in photometric distortions as well as its capability in producing subpixel accuracy are two desired and often required features in most st...
We introduce a new graph-theoretic approach to image segmentation based on minimizing a novel class of `mean cut' cost functions. Minimizing these cost functions corresponds ...
Abstract. We propose a novel method for action detection based on a new action descriptor called a shape flow that represents both the shape and movement of an object in a holistic...