It is difficult to apply machine learning to new domains because often we lack labeled problem instances. In this paper, we provide a solution to this problem that leverages domai...
In this paper, we propose a modular cascaded approach to data driven dependency parsing. Each module or layer leading to the complete parse produces a linguistically valid partial...
Deterministic annealing and relaxation labeling algorithms for classification and matching are presented and discussed. A new approach--self annealing--is introduced to bring dete...
We propose a novel directed graphical model for label propagation in lengthy and complex video sequences. Given hand-labelled start and end frames of a video sequence, a variation...
Ignas Budvytis, Vijay Badrinarayanan, Roberto Cipo...
Given a directed graph in which some of the nodes are labeled, we investigate the question of how to exploit the link structure of the graph to infer the labels of the remaining u...