Presentation 2010-01-21
Forming Object Concepts Based on Multimodal Information
Tomoaki NAKAMURA, Takayuki NAGAI, Naoto IWAHASHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper we propose LDA-based framework for multimodal categorization and words grounding for robots. The robot uses its physical embodiment to grasp and observe an object from various view points as well as listen to the sound during the observing period. This multimodal information is used for categorizing and forming multimodal concepts. At the same time, the words acquired during the observing period are connected to the related concepts using multimodal LDA. We also provide a relevance measure that encodes the degree of connection between words and modalities. The proposed algorithm is implemented on the robot platform and some experiments are carried out to evaluate the algorithm. We also demonstrate a simple conversation between a user and the robot based on the learned model.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Multimodal / Categorization / Symbol grounding / Latent Dirichlet Allocation
Paper # CQ2009-58,PRMU2009-157,SP2009-98,MVE2009-80
Date of Issue

Conference Information
Committee MVE
Conference Date 2010/1/14(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Media Experience and Virtual Environment (MVE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Forming Object Concepts Based on Multimodal Information
Sub Title (in English)
Keyword(1) Multimodal
Keyword(2) Categorization
Keyword(3) Symbol grounding
Keyword(4) Latent Dirichlet Allocation
1st Author's Name Tomoaki NAKAMURA
1st Author's Affiliation Dept. of Electronic Engineering, The University of Electro-Communications()
2nd Author's Name Takayuki NAGAI
2nd Author's Affiliation Dept. of Electronic Engineering, The University of Electro-Communications
3rd Author's Name Naoto IWAHASHI
3rd Author's Affiliation National Institute of Information and Communications Technology
Date 2010-01-21
Paper # CQ2009-58,PRMU2009-157,SP2009-98,MVE2009-80
Volume (vol) vol.109
Number (no) 376
Page pp.pp.-
#Pages 6
Date of Issue