In this paper we address the problem of how to learn a structural prototype that can be used to represent the variations present in a set of trees. The prototype serves as a patte...
We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (Learning Object Classes with Unsupervised Segmentation...
—In this paper, we propose a novel predictive model, active volume model (AVM), for object boundary extraction. It is a dynamic “object” model whose manifestation includes a ...