{"created":"2025-01-18T23:23:41.352641+00:00","updated":"2025-01-21T22:35:59.504239+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00061506","sets":["1164:4619:5663:5664"]},"path":["5664"],"owner":"10","recid":"61506","title":["画像特徴とテキスト特徴を用いた Web スポーツニュース画像のイベント分類"],"pubdate":{"attribute_name":"公開日","attribute_value":"2009-03-06"},"_buckets":{"deposit":"ada1e2e9-d20a-4257-8e08-a27d2b382d6c"},"_deposit":{"id":"61506","pid":{"type":"depid","value":"61506","revision_id":0},"owners":[10],"status":"published","created_by":10},"item_title":"画像特徴とテキスト特徴を用いた Web スポーツニュース画像のイベント分類","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"画像特徴とテキスト特徴を用いた Web スポーツニュース画像のイベント分類"},{"subitem_title":"Event Classification of Sport News Photos by Integrating Textual and Visual Features","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2009-03-06","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"電気通信大学大学院電気通信学研究科情報工学専攻"},{"subitem_text_value":"電気通信大学大学院電気通信学研究科情報工学専攻"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Department of Computer Science, The University of Electro-Communications","subitem_text_language":"en"},{"subitem_text_value":"Department of Computer Science, The University of Electro-Communications","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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":10,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/61506/files/IPSJ-CVIM09166018.pdf","label":"IPSJ-CVIM09166018"},"date":[{"dateType":"Available","dateValue":"2011-03-06"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM09166018.pdf","filesize":[{"value":"4.8 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":"e8342e91-4577-449e-a9ed-495fb14a97e9","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2009 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"北原, 章雄"},{"creatorName":"柳井, 啓司"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Akio, Kitahara","creatorNameLang":"en"},{"creatorName":"Keiji, Yanai","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_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"現在，Web 上に配信されている画像付きニュースは，ニュース内容や画像の内容によって細かく分類して配信されていないことが多いため，ユーザが目的のニュースを検索することが困難となっている．そこで，本研究では Web 画像ニュースの中のスポーツニュースを対象とし，これらスポーツニュースをスポーツの種類と，画像の内容によりプレイ中か非プレイ中かのスポーツイベント分類を行う方法を提案する．2 段階手法はテキスト特徴によりスポーツ分類を行った後に画像特徴を Multiple Kernel Learning (MKL) によって統合してイベント分類を行う方法であり，1 段階手法はテキスト特徴と画像特徴を同時に MKL によって統合することでスポーツイベント分類を同時に行う方法である．実験では，Yahoo!JAPAN 写真ニュースの記事を対象に野球，ゴルフ，F1，サッカー，テニス，相撲のプレー中／非プレー中の 12 種類に分類した．2  段階手法スポーツ分類では分類率 99.33% を達成し，イベント分類では野球 81.5%，ゴルフ 67.5%，F1 91.0%，サッカー 81.0%，テニス 71.0%，相撲 92.5% という分類率になり，ゴルフ以外で特徴統合により特徴単独よりも高い分類率を得た．一方，1 段階手法では全体の分類率 77.08% を得た．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"There are many Web news sites which deliver us news photos everyday. However, since they classified news photos only very roughly, it is not easy for us to search for photos we want from a huge amount of news photos. In this paper, we treat with event classification of sports news photos as an instance of researches on more sophisticated search methods for large-scale photo news databases. We propose two methods to classify sports news photos into one of six sports genres and to discriminate in-play photos from not-in-play ones. One is the two-step method which classifies sport genres first and recognizes in-play conditions next, and the other is the two-step method which classifies them simultaneously. In the proposed methods, we integrate textual features extracted from news articles and image features extracted from photo images by Multiple Kernel Learning (MKL). In the experiment of the two-step method, we obtained 99.33% as the classification rate for the genre classification which is the first step and 80.75% for the in-play classification which is the second step. On the other hand, in the experiment of the one-step method, we obtained 77.08% which was a little less than the result by the two-step method. ","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"126","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":"119","bibliographicIssueDates":{"bibliographicIssueDate":"2009-03-06","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"29(2009-CVIM-166)","bibliographicVolumeNumber":"2009"}]},"relation_version_is_last":true,"weko_creator_id":"10"},"id":61506,"links":{}}