{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00201551","sets":["1164:1165:9888:10036"]},"path":["10036"],"owner":"44499","recid":"201551","title":["Generating Emotional Region and Text Representations for Joint Visual Textual Sentiment Analysis"],"pubdate":{"attribute_name":"公開日","attribute_value":"2019-12-16"},"_buckets":{"deposit":"e5d1b1e7-0b76-4f96-adef-7e4bb7076c96"},"_deposit":{"id":"201551","pid":{"type":"depid","value":"201551","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Generating Emotional Region and Text Representations for Joint Visual Textual Sentiment Analysis","author_link":["493404","493407","493405","493406"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Generating Emotional Region and Text Representations for Joint Visual Textual Sentiment Analysis"},{"subitem_title":"Generating Emotional Region and Text Representations for Joint Visual Textual Sentiment Analysis","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2019-12-16","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Information, Production and Systems, Waseda University"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Information, Production and Systems, Waseda 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/201551/files/IPSJ-DBS19170006.pdf","label":"IPSJ-DBS19170006.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DBS19170006.pdf","filesize":[{"value":"682.6 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"13"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"9dcc4af8-fc8c-47f4-aaa6-2c11e2addcec","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2019 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Jiayi, Zhao"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Mizuho, Iwaihara"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Jiayi, Zhao","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Mizuho, Iwaihara","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10112482","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":"2188-871X","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"Recently, social media users are increasingly using images and texts to express their opinions and share their experiences. Sentiment analysis of images and texts can help better extract users' sentiments toward events or topic, where prediction of sentiment is an important task. Traditional sentiment analysis on images with textual description only considers the whole image and the whole sentence to predict the result (positive or negative). However, both the whole image and local emotional regions convey significant sentiment information and the emotional textual fragment of the description expresses sentiment as well. Therefore, we propose a deep fusion network to detect the most emotional region in the image and associate the emotional region with the most emotional textual fragment in the description. For predicting the sentiment of the whole image, we consider synthetically integrating the four parts: Textual description, emotional region, and most matching emotional textual fragment. At last, we build a fusion layer to combine the output of the representations to predict the overall sentiment. We carry out experiments on a subset selected from dataset Visual Sentiment Ontology (VSO). The results show that our proposed method can effectively predict sentiment and performs competitively to other methods. ","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Recently, social media users are increasingly using images and texts to express their opinions and share their experiences. Sentiment analysis of images and texts can help better extract users' sentiments toward events or topic, where prediction of sentiment is an important task. Traditional sentiment analysis on images with textual description only considers the whole image and the whole sentence to predict the result (positive or negative). However, both the whole image and local emotional regions convey significant sentiment information and the emotional textual fragment of the description expresses sentiment as well. Therefore, we propose a deep fusion network to detect the most emotional region in the image and associate the emotional region with the most emotional textual fragment in the description. For predicting the sentiment of the whole image, we consider synthetically integrating the four parts: Textual description, emotional region, and most matching emotional textual fragment. At last, we build a fusion layer to combine the output of the representations to predict the overall sentiment. We carry out experiments on a subset selected from dataset Visual Sentiment Ontology (VSO). The results show that our proposed method can effectively predict sentiment and performs competitively to other methods. ","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告データベースシステム（DBS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2019-12-16","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"6","bibliographicVolumeNumber":"2019-DBS-170"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":201551,"updated":"2025-01-19T20:59:02.708901+00:00","links":{},"created":"2025-01-19T01:04:48.668131+00:00"}