ホウチン　テルヒサ   Teruhisa Hochin   寶珍　輝尚    所属   追手門学院大学  理工学部 情報工学科    職種   教授
言語種別	英語
発行・発表の年月	2017
形態種別	論文
査読	査読あり
標題	Emotional Video Scene Retrieval Using Multilayer Convolutional Network
執筆形態	共著・編著（代表編著を除く）
掲載誌名	APPLIED COMPUTING AND INFORMATION TECHNOLOGY
掲載区分	国外
出版社・発行元	SPRINGER INTERNATIONAL PUBLISHING AG
巻・号・頁	695,pp.105-117
著者・共著者	Hiroki Nomiya,Shota Sakaue,Mitsuaki Maeda,Teruhisa Hochin
概要	In order to retrieve impressive scene from a video database, a scene retrieval method based on facial expression recognition (FER) is proposed. The proposed method will be useful to retrieve interesting scenes from lifelog videos. When an impressive event occurs, a certain facial expression will be observed in a person in the video. It is, therefore, important for the impressive scene retrieval to precisely recognize the facial expression of the person. In this paper, we try to construct accurate FER models by introducing a learning framework on the basis of multilayer convolutional network using a number of facial features defined as the positional relations between some facial feature points. The effectiveness of the proposed method is evaluated through an experiment to retrieve emotional scenes from a lifelog video database.
DOI	10.1007/978-3-319-51472-7_8
ISSN	1860-949X