Abstract. Learned, activity-specific motion models are useful for human pose and motion estimation. Nevertheless, while the use of activityspecific models simplifies monocular t...
For the task of near-duplicated document detection, both traditional fingerprinting techniques used in database community and bag-of-word comparison approaches used in information...
A novel method for the segmentation of multiple objects from 3D medical images using inter-object constraints is presented. Our method is motivated by the observation that neighbor...
We develop a semi-supervised learning method that constrains the posterior distribution of latent variables under a generative model to satisfy a rich set of feature expectation c...
Abstract. We present a new generic problem solving approach for overconstrained problems based on Max-SAT. We first define a clausal form formalism that deals with blocks of clau...