Abstract. In this work, we present an automated system for creating hedcut illustrations, portraits rendered using small image feature aligned dots (stipples). We utilize edge dete...
SungYe Kim, Insoo Woo, Ross Maciejewski, David S. ...
To separate object motion from camera motion in an aerial video, consecutive frames are registered at their planar background. Feature points are selected in consecutive frames an...
We present a system that learns to follow navigational natural language directions. Where traditional models learn from linguistic annotation or word distributions, our approach i...
We describe our experiments with training algorithms for tree-to-tree synchronous tree-substitution grammar (STSG) for monolingual translation tasks such as sentence compression a...
The pipeline of most Phrase-Based Statistical Machine Translation (PB-SMT) systems starts from automatically word aligned parallel corpus. But word appears to be too fine-grained ...