Multiple Instance Learning (MIL) provides a framework for training a discriminative classifier from data with ambiguous labels. This framework is well suited for the task of learni...
Carolina Galleguillos, Boris Babenko, Andrew Rabin...
In this paper, we present a novel adaptive thresholding technique based upon an anisotropic diffusionmodel, whichmay be referred to as the anti-geometric heat flow. In contrast to...
A region based algorithm for segmentation motivated by a parallel implementation is introduced. It is obtained by combining the watershed transform with further merging based on a...
We propose a new approach to compute non-linear, intrinsic shape statistics and to incorporate them into a shape prior for an image segmentation task. Given a sample set of contou...
Guillaume Charpiat, Olivier D. Faugeras, Renaud Ke...
This study investigates variational image segmentation with an original data term, referred to as statistical overlap prior, which measures the conformity of overlap between the no...