We consider the problem of dimensionality reduction, where given high-dimensional data we want to estimate two mappings: from high to low dimension (dimensionality reduction) and f...
The required amount of labeled training data for object detection and classification is a major drawback of current methods. Combining labeled and unlabeled data via semisupervise...
An interactive framework for soft segmentation and matting of natural images and videos is presented in this paper. The proposed technique is based on the optimal, linear time, co...
We propose a unified framework based on a general definition of geometric transform (GeT) for modeling appearance. GeT represents the appearance by applying designed functionals o...
We propose a novel approach for shape-based segmentation based on a specially designed level set function format. This format permits us to better control the process of object re...