A central problem in grounded language acquisition is learning the correspondences between a rich world state and a stream of text which references that world state. To deal with ...
This paper proposes a data driven image segmentation algorithm, based on decomposing the target output (ground truth). Classical pixel labeling methods utilize machine learning al...
We present a system to segment the medial edges of the vocal folds from stroboscopic video. The system has two components. The first learns a color transformation that optimally d...
Sonya Allin, John M. Galeotti, George D. Stetten, ...
Incorporating shape priors in image segmentation has become a key problem in computer vision. Most existing work is limited to a linearized shape space with small deformation modes...
Patrick Etyngier, Renaud Keriven, Jean-Philippe Po...
The explanation of a decision is important for the acceptance of machine learning technology in bioinformatics applications such as protein structure prediction. In past research,...
Jieyue He, Bernard Chen, Hae-Jin Hu, Robert W. Har...