On the Integration of Grounding Language and Learning Objects

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

• Type: Conference
• Year: 2004
• Where: AAAI
• Authors: Chen Yu, Dana H. Ballard
• Keywords: AAAI 2004, Co-occurring Multisensory Input, Intelligent Agents, Multimodal Data, Multimodal Learning