We propose a novel unsupervised learning algorithm to extract the layout of an image by learning latent object-related aspects. Unlike traditional image segmentation algorithms th...
In this paper we present a probabilistic framework for tracking objects based on local dynamic segmentation. We view the segn to be a Markov labeling process and abstract it as a ...
—We propose an automatic approach to soft color segmentation, which produces soft color segments with an appropriate amount of overlapping and transparency essential to synthesiz...
This paper presents a novel technique for 2D human motion estimation using a single non calibrated camera. The user’s five crucial human features (head, hands and feet) are ext...
Pedro Correa, Jacek Czyz, Toshiyuki Umeda, Ferran ...
We recently proposed a method to find cluster structure in home videos based on statistical models of visual and temporal features of video segments and sequential binary Bayesian...
Daniel Gatica-Perez, Alexander C. Loui, Ming-Ting ...