{"updated":"2025-01-19T20:12:07.225133+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00204437","sets":["1164:4619:10081:10200"]},"path":["10200"],"owner":"44499","recid":"204437","title":["On the Quantification of the Mental Image of Visual Concepts for Multi-modal Applications"],"pubdate":{"attribute_name":"公開日","attribute_value":"2020-05-07"},"_buckets":{"deposit":"df6a3086-a97c-4ca4-b5fd-e0c16e58f581"},"_deposit":{"id":"204437","pid":{"type":"depid","value":"204437","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"On the Quantification of the Mental Image of Visual Concepts for Multi-modal Applications","author_link":["506253","506249","506245","506251","506247","506250","506254","506248","506243","506252","506246","506244"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"On the Quantification of the Mental Image of Visual Concepts for Multi-modal Applications"},{"subitem_title":"On the Quantification of the Mental Image of Visual Concepts for Multi-modal Applications","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"D論セッション","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2020-05-07","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"National Institute of Informatics"},{"subitem_text_value":"Mathematical & Data Science Center, Nagoya University／Graduate School of Informatics, Nagoya University"},{"subitem_text_value":"Graduate School of Informatics, Nagoya University"},{"subitem_text_value":"Institute of Innovation for Future Society, Nagoya University"},{"subitem_text_value":"Graduate School of Informatics, Nagoya University"},{"subitem_text_value":"Graduate School of Informatics, Nagoya University"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"National Institute of Informatics","subitem_text_language":"en"},{"subitem_text_value":"Mathematical & Data Science Center, Nagoya University / Graduate School of Informatics, Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Informatics, Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Institute of Innovation for Future Society, Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Informatics, Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Informatics, Nagoya University","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/204437/files/IPSJ-CVIM20222005.pdf","label":"IPSJ-CVIM20222005.pdf"},"date":[{"dateType":"Available","dateValue":"2022-05-07"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM20222005.pdf","filesize":[{"value":"10.4 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"20"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"5cf28d81-df1e-4b7c-9f5b-00917044fdb6","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2020 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Marc, A. Kastner"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Ichiro, Ide"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yasutomo, Kawanishi"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takatsugu, Hirayama"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Daisuke, Deguchi"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hiroshi, Murase"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Marc, A. Kastner","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Ichiro, Ide","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yasutomo, Kawanishi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takatsugu, Hirayama","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Daisuke, Deguchi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hiroshi, Murase","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11131797","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8701","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"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.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"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.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"14","bibliographic_titles":[{"bibliographic_title":"研究報告コンピュータビジョンとイメージメディア（CVIM）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2020-05-07","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"5","bibliographicVolumeNumber":"2020-CVIM-222"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T01:06:42.643863+00:00","id":204437,"links":{}}