Sciweavers

63 search results - page 2 / 13
» On the Integration of Grounding Language and Learning Object...
Sort
View
AAAI
2012
11 years 7 months ago
A Testbed for Learning by Demonstration from Natural Language and RGB-Depth Video
We are developing a testbed for learning by demonstration combining spoken language and sensor data in a natural real-world environment. Microsoft Kinect RGBDepth cameras allow us...
Young Chol Song, Henry A. Kautz
EELC
2006
121views Languages» more  EELC 2006»
13 years 9 months ago
Symbol Grounding Through Cumulative Learning
Abstract. We suggest that the primary motivation for an agent to construct a symbol-meaning mapping is to solve a task. The meaning space of an agent should be derived from the tas...
Samarth Swarup, Kiran Lakkaraju, Sylvian R. Ray, L...
EDOC
2005
IEEE
13 years 11 months ago
An Interactive Approach for Specifying OWL-S Groundings
12 OWL-S is an instance of the Web Ontology Language (OWL) that is used to describe and specify semantic web services. While OWL-S provides a promising mechanism for specification...
Gerald C. Gannod, Raynette J. Brodie, John T. E. T...
EMMCVPR
2001
Springer
13 years 9 months ago
A Hierarchical Markov Random Field Model for Figure-Ground Segregation
To segregate overlapping objects into depth layers requires the integration of local occlusion cues distributed over the entire image into a global percept. We propose to model thi...
Stella X. Yu, Tai Sing Lee, Takeo Kanade
IROS
2006
IEEE
165views Robotics» more  IROS 2006»
13 years 11 months ago
Grounded Situation Models for Robots: Where words and percepts meet
— Our long-term objective is to develop robots that engage in natural language-mediated cooperative tasks with humans. To support this goal, we are developing an amodal represent...
Nikolaos Mavridis, Deb Roy