On the Quantification of the Mental Image of Visual Concepts for Multi-modal Applications

• Item type: SIG Technical Reports(1)
• 公開日: 2020-05-07
• タイトル: On the Quantification of the Mental Image of Visual Concepts for Multi-modal Applications
• タイトル / 言語: en
• タイトル: On the Quantification of the Mental Image of Visual Concepts for Multi-modal Applications
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: D論セッション
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: National Institute of Informatics
• 著者所属: Mathematical & Data Science Center, Nagoya University／Graduate School of Informatics, Nagoya University
• 著者所属: Graduate School of Informatics, Nagoya University
• 著者所属: Institute of Innovation for Future Society, Nagoya University
• 著者所属: Graduate School of Informatics, Nagoya University
• 著者所属: Graduate School of Informatics, Nagoya University
• 著者所属(英): en
• 著者所属(英): National Institute of Informatics
• 著者所属(英): en
• 著者所属(英): Mathematical & Data Science Center, Nagoya University / Graduate School of Informatics, Nagoya University
• 著者所属(英): en
• 著者所属(英): Graduate School of Informatics, Nagoya University
• 著者所属(英): en
• 著者所属(英): Institute of Innovation for Future Society, Nagoya University
• 著者所属(英): en
• 著者所属(英): Graduate School of Informatics, Nagoya University
• 著者所属(英): en
• 著者所属(英): Graduate School of Informatics, Nagoya University
• 著者名: Marc, A. Kastner; Ichiro, Ide; Yasutomo, Kawanishi; Takatsugu, Hirayama; Daisuke, Deguchi; Hiroshi, Murase
• 著者名(英): Marc, A. Kastner; Ichiro, Ide; Yasutomo, Kawanishi; Takatsugu, Hirayama; Daisuke, Deguchi; Hiroshi, Murase
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: The semantic gap is the lack of coincidence between the information one can extract from data and its interpretation. It is an yet solved issue for multimedia applications like image captioning, where it is often challenging to select the best fitting wording out of a group of candidates. To create a measurement for the perceived differences between words, this doctoral research proposes the idea of analyzing crawled image data to gain a better semantic understanding of language and vision. Abstract words have a broad mental image due to them being less visually defined, while concrete words with a rather narrow visual feature space are visually easier to grasp. The core goal of this research is to approximate this perceived abstractness of those words as a metric. The thesis proposes two methods, looking at both relative and absolute measurements. For the relative method, a data-driven approach is proposed, while the absolute measurements train a machine-learned model on existing data from Psycholinguistics. Each method is evaluated using crowd-sourced data and compared to related approaches. With this, the thesis presents methods to analyze the mental image of words from different angles, targeting a way to quantify the semantic gap between vision and language.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: The semantic gap is the lack of coincidence between the information one can extract from data and its interpretation. It is an yet solved issue for multimedia applications like image captioning, where it is often challenging to select the best fitting wording out of a group of candidates. To create a measurement for the perceived differences between words, this doctoral research proposes the idea of analyzing crawled image data to gain a better semantic understanding of language and vision. Abstract words have a broad mental image due to them being less visually defined, while concrete words with a rather narrow visual feature space are visually easier to grasp. The core goal of this research is to approximate this perceived abstractness of those words as a metric. The thesis proposes two methods, looking at both relative and absolute measurements. For the relative method, a data-driven approach is proposed, while the absolute measurements train a machine-learned model on existing data from Psycholinguistics. Each method is evaluated using crowd-sourced data and compared to related approaches. With this, the thesis presents methods to analyze the mental image of words from different angles, targeting a way to quantify the semantic gap between vision and language.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA11131797
• 書誌情報: 研究報告コンピュータビジョンとイメージメディア（CVIM）; 巻 2020-CVIM-222, 号 5, p. 1-14, 発行日 2020-05-07
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8701
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会