Improving Content-based Social Image Retrieval Based on an Image-tag Relationship Model

• Item type: Trans(1)
• 公開日: 2012-09-28
• タイトル: Improving Content-based Social Image Retrieval Based on an Image-tag Relationship Model
• タイトル / 言語: en
• タイトル: Improving Content-based Social Image Retrieval Based on an Image-tag Relationship Model
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [研究論文] content based image retrieval, social image, social tag, graph model
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: Department of Social Informatics, Kyoto University
• 著者所属: Department of Social Informatics, Kyoto University
• 著者所属: Department of Social Informatics, Kyoto University
• 著者所属: Department of Social Informatics, Kyoto University
• 著者所属(英): en
• 著者所属(英): Department of Social Informatics, Kyoto University
• 著者所属(英): en
• 著者所属(英): Department of Social Informatics, Kyoto University
• 著者所属(英): en
• 著者所属(英): Department of Social Informatics, Kyoto University
• 著者所属(英): en
• 著者所属(英): Department of Social Informatics, Kyoto University
• 著者名: Jiyi, Li; Qiang, Ma; Yasuhito, Asano; Masatoshi, Yoshikawa
• 著者名(英): Jiyi, Li; Qiang, Ma; Yasuhito, Asano; Masatoshi, Yoshikawa
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: With the recent rapid growth of social image hosting websites, such as Flickr, it is easier to construct a large database with social tagged images. We propose an unsupervised approach for automatic ranking social images to improve content-based social image retrieval. We construct an image-tag relationship graph model with both social images and tags. The approach extracts visual and textual information and combines them for ranking by propagating them through the graph links with an optimized mutual reinforcement process. We conduct experiments showing that our approach can successfully use social tags for ranking and improving content-based social image search results, and performs better than other approaches.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: With the recent rapid growth of social image hosting websites, such as Flickr, it is easier to construct a large database with social tagged images. We propose an unsupervised approach for automatic ranking social images to improve content-based social image retrieval. We construct an image-tag relationship graph model with both social images and tags. The approach extracts visual and textual information and combines them for ranking by propagating them through the graph links with an optimized mutual reinforcement process. We conduct experiments showing that our approach can successfully use social tags for ranking and improving content-based social image search results, and performs better than other approaches.
• 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: AA11464847
• 書誌情報: 情報処理学会論文誌データベース（TOD）; 巻 5, 号 3, p. 117-125, 発行日 2012-09-28
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-7799
• 出版者 / 言語: ja
• 出版者: 情報処理学会