Cross-media translation between human motions and texts based on mental image directed semantic theory

Author

Amano, Mikio ; Hironaka, Daisuke ; Oda, Seio ; Barolli, Valbona ; Capi, Genci ; Yokota, Masao

Author_Institution

Fac. of Inf. Eng., Fukuoka Inst. of Technol., Japan

fYear

2005

fDate

6-10 June 2005

Firstpage

707

Lastpage

713

Abstract

The mental image directed semantic theory (MIDST) has proposed a formal language L_md employed for many-sorted predicate logic and whose semantics is given based on an omnisensual mental image model so called "Loci in Attribute Spaces". This language can be used for intermediate knowledge representation of multimedia contents and has been applied to an integrated multimedia understanding system IMAGES-M. This paper presents brief sketches of L_md and IMAGES-M and focuses on bi-directional cross-media translation between human motions and texts by IMAGES-M.

Keywords

formal languages; formal logic; image motion analysis; knowledge representation languages; multimedia systems; text analysis; IMAGES-M; attribute spaces; cross-media translation; formal language; human motions; integrated multimedia understanding system; knowledge representation; many-sorted predicate logic; mental image directed semantic theory; Bidirectional control; Electronic mail; Facial animation; Formal languages; Humans; Knowledge representation; Logic design; Multimedia systems; Space technology; World Wide Web;

fLanguage

English

Publisher

ieee

Conference_Titel

Distributed Computing Systems Workshops, 2005. 25th IEEE International Conference on

Print_ISBN

0-7695-2328-5

Type

conf

DOI

10.1109/ICDCSW.2005.56

Filename

1437250