イサハラ　ヒトシ   井佐原　均    所属   追手門学院大学  心理学部 心理学科    追手門学院大学  大学院　心理学研究科    職種   教授
言語種別	英語
発行・発表の年月	2016/12
形態種別	論文
査読	査読あり
標題	Estimation of structure of four-scene comics by convolutional neural networks
執筆形態	共著・編著（代表編著を除く）
掲載誌名	ACM International Conference Proceeding Series
掲載区分	国内
出版社・発行元	Association for Computing Machinery
著者・共著者	Miki Ueno,Toshinori Suenaga,Naoki Mori,Hitoshi Isahara
概要	The computational interpretation of comics is one of the important topics being studied in the Field of artiFicial in- telligence and image recognition. There are a lot of chal- lenging tasks to undertake in order to interpret comics, i.e., recognize objects in gray-scaled drawing image, extract emo- tional information of scenes, and deFine models of continuous scenes by considering the structure of comics. In this paper, we focused on four scene comics and their transition. Four- scene comics have a structure which originated in four-part of Chinese-poetry so creators clearly draw the semantic dis- tance between each scene. It is very important for expressing the interesting and lyrical aspects of comics. To detect the transition of scenes, convolutional neural networks(CNNs) are constructed and computer experiments were carried out. The results suggest that CNN is able to detect the transi- tion of scenes and that the features of each scene are quite difierent.
DOI	10.1145/3011549.3011558