Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

13

AAAI
2004

favoriteEmaildiscussreport

91views Intelligent Agents» more AAAI 2004»

On the Integration of Grounding Language and Learning Objects

13 years 6 months ago

On the Integration of Grounding Language and Learning Objects

Download www.indiana.edu

This paper presents a multimodal learning system that can ground spoken names of objects in their physical referents and learn to recognize those objects simultaneously from naturally co-occurring multisensory input. There are two technical problems involved: (1) the correspondence problem in symbol grounding

Chen Yu, Dana H. Ballard

Real-time Traffic

AAAI 2004 | Co-occurring Multisensory Input | Intelligent Agents | Multimodal Data | Multimodal Learning |

claim paper

Related Content

» Systematically Grounding Language through Vision in a Deep Recurrent Neural Network

» Learning visually grounded words and syntax for a scene description task

» Exploiting Social Information in Grounded Language Learning via Grammatical Reduction

» Embodied Active Vision in Language Learning and Grounding

» A Testbed for Learning by Demonstration from Natural Language and RGBDepth Video

» Symbol Grounding Through Cumulative Learning

» An Interactive Approach for Specifying OWLS Groundings

» A Hierarchical Markov Random Field Model for FigureGround Segregation

» Grounded Situation Models for Robots Where words and percepts meet

Post Info
More Details (n/a)

Added	30 Oct 2010
Updated	30 Oct 2010
Type	Conference
Year	2004
Where	AAAI
Authors	Chen Yu, Dana H. Ballard

Comments (0)