Visual representation of negation: Real world data analysis on comic image design

Yuri Sato, Koji Mineshima, Kazuhiro Ueda

研究成果: Paper査読

2 被引用数 (Scopus)

抄録

There has been a widely held view that visual representations (e.g., photographs and illustrations) do not depict negation, for example, one that can be expressed by a sentence “the train is not coming”. This view is empirically challenged by analyzing the real-world visual representations of comic (manga) illustrations. In the experiment using image captioning tasks, we gave people comic illustrations and asked them to explain what they could read from them. The collected data showed that some comic illustrations could depict negation without any aid of sequences (multiple panels) or conventional devices (special symbols). This type of comic illustrations was subjected to further experiments, classifying images into those containing negation and those not containing negation. While this image classification was easy for humans, it was difficult for data-driven machines, i.e., deep learning models (CNN), to achieve the same high performance. Given the findings, we argue that some comic illustrations evoke background knowledge and thus can depict negation with purely visual elements.

本文言語English
ページ1166-1172
ページ数7
出版ステータスPublished - 2021
イベント43rd Annual Meeting of the Cognitive Science Society: Comparative Cognition: Animal Minds, CogSci 2021 - Virtual, Online, Austria
継続期間: 2021 7月 262021 7月 29

Conference

Conference43rd Annual Meeting of the Cognitive Science Society: Comparative Cognition: Animal Minds, CogSci 2021
国/地域Austria
CityVirtual, Online
Period21/7/2621/7/29

ASJC Scopus subject areas

  • 認知神経科学
  • 人工知能
  • コンピュータ サイエンスの応用
  • 人間とコンピュータの相互作用

フィンガープリント

「Visual representation of negation: Real world data analysis on comic image design」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル