Presentation 2001/6/21
Analysis of eye-movement strategy for application to machine vision
Masachika Aochi, Satoru Odo, Sihoko Kamisato, Kiyoshi Hoshino,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Imitation learning by watching is the way that a teacher or other person shows how to solve a task and a student translates the process into his own dynamics to realize the same motion with the teachers'. Some researches reported that the imitation learning can be carried out by robots with CCD vision. The recent studies switched their focus from simple trajectory learning to high-level task learning, where the key to success is to choose proper motion parameters in each tasks. In this study, eye movements and subjective focus point in a subject were measured when a subject observed novel dance motions, and these features were compared with his reproducing pattern of the motions. The purpose was to understand how to choose the motion parameters and how to shift his strategy in imitation learning of novel, fine and complex movements.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Okinawa folk dancing / Imitation learning by watching / The gaze point
Paper # NC2001-14
Date of Issue

Conference Information
Committee NC
Conference Date 2001/6/21(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Analysis of eye-movement strategy for application to machine vision
Sub Title (in English)
Keyword(1) Okinawa folk dancing
Keyword(2) Imitation learning by watching
Keyword(3) The gaze point
1st Author's Name Masachika Aochi
1st Author's Affiliation ()
2nd Author's Name Satoru Odo
2nd Author's Affiliation
3rd Author's Name Sihoko Kamisato
3rd Author's Affiliation
4th Author's Name Kiyoshi Hoshino
4th Author's Affiliation
Date 2001/6/21
Paper # NC2001-14
Volume (vol) vol.101
Number (no) 153
Page pp.pp.-
#Pages 5
Date of Issue