{"links":{},"id":52235,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00052235","sets":["1164:4619:4631:4635"]},"path":["4635"],"owner":"1","recid":"52235","title":["講師行動の統計的性質に基づいた講義撮影のための講義状況の認識手法"],"pubdate":{"attribute_name":"公開日","attribute_value":"2006-03-17"},"_buckets":{"deposit":"70bb6f8c-ab28-441f-9577-5eafea450c11"},"_deposit":{"id":"52235","pid":{"type":"depid","value":"52235","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"講師行動の統計的性質に基づいた講義撮影のための講義状況の認識手法","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"講師行動の統計的性質に基づいた講義撮影のための講義状況の認識手法"},{"subitem_title":"Lecture Context Recognition based on Statistical Feature of Lecturer Action for Automatic Video Recording","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2006-03-17","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"京都大学 情報学研究科"},{"subitem_text_value":"京都大学 情報学研究科"},{"subitem_text_value":"京都大学 学術情報メディアセンター"},{"subitem_text_value":"京都大学 学術情報メディアセンター"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Informatics Kyoto Univ.","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Informatics Kyoto Univ.","subitem_text_language":"en"},{"subitem_text_value":"Academic Center for Computing and Media Studies Kyoto Univ.","subitem_text_language":"en"},{"subitem_text_value":"Academic Center for Computing and Media Studies Kyoto Univ.","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":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/52235/files/IPSJ-CVIM06153028.pdf"},"date":[{"dateType":"Available","dateValue":"2008-03-17"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM06153028.pdf","filesize":[{"value":"1.3 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":"322fdc51-37af-45f5-bc82-48f3c8a6ef44","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2006 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"杉本, 吉隆"},{"creatorName":"丸谷, 宜史"},{"creatorName":"角所, 考"},{"creatorName":"美濃導彦"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yoshitaka, SUGIMOTO","creatorNameLang":"en"},{"creatorName":"Takafumi, MARUTANI","creatorNameLang":"en"},{"creatorName":"Koh, KAKUSHO","creatorNameLang":"en"},{"creatorName":"Michihiko, MINOH","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":"講義を撮影した映像(講義映像)を遠隔講義や講義アーカイブなどで利用する試みが行われるのに伴い 講義を自動撮影する研究が行われている.講義映像では講義内容を理解できるものである必要があるため 自動撮影では適切な撮影対象を選択することが重要である.本研究では 講義内容を理解するために映すべき被写体を捉えた講義映像を作成することを考える.講義内容を理解するために映すべき被写体の組合せを講義状況と定義すると そのような講義映像作成を行うためには各時刻での講義状況を認識する必要がある.そこで本研究ではそのような講義状況の認識を目的とする.従来の講義自動撮影の研究では講義状況として講師位置や講師行動を考え 画像などの観測情報からそのような講義状況を認識してきた.この場合 講師位置や講師行動は各時刻または決まった時間区間の観測情報から一意に認識されていた.しかしながら本研究で扱うような講義状況では 同じ講義状況でもおきる講師行動や講師位置は様々であるため 従来のように観測情報から一意に決定する手法では講義状況を高い精度で認識することが難しい.そこで本研究では講師行動の頻度 講義状況間の遷移確率という統計的性質に着目し この統計的性質を表現したHMMに基づく講義状況認識手法を提案する.実験では実際に行われた講義を対象とし 提案手法の有効性 講義状況に基づいて作成した講義映像の有用性を確認する.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In this paper, we discuss the problem of recognizing situations of lectures for shooting lecture videos automatically. We classify the situations of the lectures based on the subjects to be gazed at for understanding the lectures in a lecture room. However it is not easy to recognize the lecture situations by conventional approaches based on the features of the sensory data obtained in a lecture room because the same sensory data occurs in the different lecture situations. We employ statistical properties for the occurrence of sensory data in each lecture situation together with the transition probability between lecture situations. This process is realized by Hidden Markov Model that represents those statistical properties.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"186","bibliographic_titles":[{"bibliographic_title":"情報処理学会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":"179","bibliographicIssueDates":{"bibliographicIssueDate":"2006-03-17","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"25(2006-CVIM-153)","bibliographicVolumeNumber":"2006"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"created":"2025-01-18T23:16:36.419741+00:00","updated":"2025-01-22T06:52:14.423096+00:00"}