For interaction with its environment, a robot is required to learn models of objects and to perceive these models in the livestreams from its sensors. In this paper, we propose a ...
This paper focuses on an important step in the creation of a system of meaning representation and the development of semantically-annotated parallel corpora, for use in applicatio...
Bonnie J. Dorr, Rebecca J. Passonneau, David Farwe...
Many information sources use multiple modalities, such as textbooks, which contain both text and diagrams. Each captures information that is hard to express in the other, and evid...
Web object is defined to represent any meaningful object embedded in web pages (e.g. images, music) or pointed to by hyperlinks (e.g. downloadable files). Users usually search for...
In this work, we address the problem of segmenting multiple objects, under possible occlusions, in a level set framework. A variational energy that incorporates a piecewise constan...
Sheshadri Thiruvenkadam, Tony F. Chan, Byung-Woo H...