Traditional learning-based coreference resolvers operate by training a mentionpair classifier for determining whether two mentions are coreferent or not. Two independent lines of ...
Scientists typically need to take a large volume of information into account in order to deal with re-occurring tasks such as inspecting proceedings, finding related work, or revi...
Algirdas Avizienis, Gintare Grigonyte, Johann Hall...
Circular anchored maps have been proposed as a drawing technique to acquire knowledge from bipartite graphs, where nodes in one set are arranged on a circumference. However, the re...
Abstract. While interactive virtual humans are becoming widely used in education, training and delivery of instructions, building the animations required for such interactive chara...
In this work, we address the problem of building recognition across two camera views with large changes in scales and viewpoints. The main idea is to construct a semantically rich...