Interactive topology formation of linguistic space and motion space

Wataru Takano; Dana Kulić; Yoshihiko Nakamura

doi:10.1109/IROS.2007.4399344

Interactive topology formation of linguistic space and motion space

Wataru Takano
, Dana Kulić
, Yoshihiko Nakamura

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

7 Citations (Scopus)

Abstract

A hierarchical model incorporating motion patterns, proto symbols and words is proposed. The proto symbols abstract motion patterns, while the words are associated with the proto symbols stochastically. This paper describes the construction of a word space, where words are located in a multidimensional space based on dissimilarities among the words. The dissimilarity between two words can be calculated by using association probabilities that the words generate motion proto symbols. The word space encapsulates relations among the words such as similar or dissimilar pairs of words. The word space also allows motion recognition based on words. The validity of the constructed word space is demonstrated on a motion capture database. Moreover, the addition of the word associations is found to change the conventional proto symbol space so that the discrimination among the proto symbols is improved.

Original language	English
Title of host publication	Proceedings of the 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	1416-1422
Number of pages	7
ISBN (Print)	1424409128, 9781424409129
DOIs	https://doi.org/10.1109/IROS.2007.4399344
Publication status	Published - 1 Dec 2007
Externally published	Yes
Event	IEEE/RSJ International Conference on Intelligent Robots and Systems 2007 - San Diego, United States of America Duration: 29 Oct 2007 → 2 Nov 2007 https://ieeexplore.ieee.org/xpl/conhome/4398943/proceeding (Proceedings)

Conference

Conference	IEEE/RSJ International Conference on Intelligent Robots and Systems 2007
Abbreviated title	IROS 2007
Country/Territory	United States of America
City	San Diego
Period	29/10/07 → 2/11/07
Internet address	https://ieeexplore.ieee.org/xpl/conhome/4398943/proceeding (Proceedings)

Access to Document

10.1109/IROS.2007.4399344

Cite this

@inproceedings{5584c4b997c5470d9563ce80d5a2b56f,

title = "Interactive topology formation of linguistic space and motion space",

abstract = "A hierarchical model incorporating motion patterns, proto symbols and words is proposed. The proto symbols abstract motion patterns, while the words are associated with the proto symbols stochastically. This paper describes the construction of a word space, where words are located in a multidimensional space based on dissimilarities among the words. The dissimilarity between two words can be calculated by using association probabilities that the words generate motion proto symbols. The word space encapsulates relations among the words such as similar or dissimilar pairs of words. The word space also allows motion recognition based on words. The validity of the constructed word space is demonstrated on a motion capture database. Moreover, the addition of the word associations is found to change the conventional proto symbol space so that the discrimination among the proto symbols is improved.",

author = "Wataru Takano and Dana Kuli{\'c} and Yoshihiko Nakamura",

year = "2007",

month = dec,

day = "1",

doi = "10.1109/IROS.2007.4399344",

language = "English",

isbn = "1424409128",

pages = "1416--1422",

booktitle = "Proceedings of the 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "IEEE/RSJ International Conference on Intelligent Robots and Systems 2007, IROS 2007 ; Conference date: 29-10-2007 Through 02-11-2007",

url = "https://ieeexplore.ieee.org/xpl/conhome/4398943/proceeding",

}

Takano, W, Kulić, D & Nakamura, Y 2007, Interactive topology formation of linguistic space and motion space. in Proceedings of the 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007. IEEE, Institute of Electrical and Electronics Engineers, pp. 1416-1422, IEEE/RSJ International Conference on Intelligent Robots and Systems 2007, San Diego, California, United States of America, 29/10/07. https://doi.org/10.1109/IROS.2007.4399344

Interactive topology formation of linguistic space and motion space. / Takano, Wataru; Kulić, Dana; Nakamura, Yoshihiko.
Proceedings of the 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007. IEEE, Institute of Electrical and Electronics Engineers, 2007. p. 1416-1422.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Interactive topology formation of linguistic space and motion space

AU - Takano, Wataru

AU - Kulić, Dana

AU - Nakamura, Yoshihiko

PY - 2007/12/1

Y1 - 2007/12/1

N2 - A hierarchical model incorporating motion patterns, proto symbols and words is proposed. The proto symbols abstract motion patterns, while the words are associated with the proto symbols stochastically. This paper describes the construction of a word space, where words are located in a multidimensional space based on dissimilarities among the words. The dissimilarity between two words can be calculated by using association probabilities that the words generate motion proto symbols. The word space encapsulates relations among the words such as similar or dissimilar pairs of words. The word space also allows motion recognition based on words. The validity of the constructed word space is demonstrated on a motion capture database. Moreover, the addition of the word associations is found to change the conventional proto symbol space so that the discrimination among the proto symbols is improved.

AB - A hierarchical model incorporating motion patterns, proto symbols and words is proposed. The proto symbols abstract motion patterns, while the words are associated with the proto symbols stochastically. This paper describes the construction of a word space, where words are located in a multidimensional space based on dissimilarities among the words. The dissimilarity between two words can be calculated by using association probabilities that the words generate motion proto symbols. The word space encapsulates relations among the words such as similar or dissimilar pairs of words. The word space also allows motion recognition based on words. The validity of the constructed word space is demonstrated on a motion capture database. Moreover, the addition of the word associations is found to change the conventional proto symbol space so that the discrimination among the proto symbols is improved.

UR - https://www.scopus.com/pages/publications/51349090538

U2 - 10.1109/IROS.2007.4399344

DO - 10.1109/IROS.2007.4399344

M3 - Conference Paper

AN - SCOPUS:51349090538

SN - 1424409128

SN - 9781424409129

SP - 1416

EP - 1422

BT - Proceedings of the 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - IEEE/RSJ International Conference on Intelligent Robots and Systems 2007

Y2 - 29 October 2007 through 2 November 2007

ER -

Interactive topology formation of linguistic space and motion space

Abstract

Conference

Access to Document

Other files and links

Cite this