{"created":"2023-06-20T16:50:49.643920+00:00","id":23385,"links":{},"metadata":{"_buckets":{"deposit":"3a4fe112-8055-4c55-87e9-999ff50e4cfa"},"_deposit":{"created_by":3,"id":"23385","owners":[3],"pid":{"revision_id":0,"type":"depid","value":"23385"},"status":"published"},"_oai":{"id":"oai:kindai.repo.nii.ac.jp:00023385","sets":["14:2667:4819"]},"author_link":["43477"],"control_number":"23385","item_8_biblio_info_21":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2021","bibliographicIssueDateType":"Issued"},"bibliographicPageEnd":"6","bibliographicPageStart":"1","bibliographic_titles":[{"bibliographic_title":"科学研究費助成事業研究成果報告書 (2021)"}]}]},"item_8_description_25":{"attribute_name":"リンクURL","attribute_value_mlt":[{"subitem_description":"https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-19K12028/","subitem_description_type":"Other"}]},"item_8_description_33":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"研究成果の概要（和文）：本研究では、1. 物体の時空間的関係を考慮した映像検索、2. フレーム間の意味的な連続性に基づく映像の時間的特徴の抽出、3. 映像に対する人間の記憶伝達メカニズムを模倣するモデルの学習という3つのテーマに取り組んだ。特に、3つ目に関して、記憶を有限の外部ストレージと見立てて、映像全体の内容を最も適切に理解するために、各フレームをどれだけ記憶すべきかを判別する強化学習手法を開発した。加えて、この手法を、大量のアイテムが格納されたデータベースから、統計的に特徴的なパターンを構成するためにどのアイテムを追加・削除すべきか判別するように拡張した手法が国際ジャーナルIEEE Accessに掲載された。\n研究成果の概要（英文）： This project addresses three main topics, 1) Video retrieval by considering spatio-temporal relations among objects, 2) Extraction of temporal features in a video by considering the continuities of semantic contents and 3) Learning a model that captures human memory mechanism for frames in a video. In particular, regarding the third topic, a reinforcement learning method has been developed to train a model that is based on a memory defined as a finite external storage and can update it so as to achieve the optimal understanding of contents in a video. In addition, this method has been extended to the data mining field, where a dataset containing a large number of items is targeted, and a model is trained to update a set of items in order to form statistically characteristic sets.","subitem_description_type":"Abstract"}]},"item_8_description_36":{"attribute_name":"内容記述","attribute_value_mlt":[{"subitem_description":"研究種目：基盤研究(C); 研究期間：2019～2021; 課題番号：19K12028; 研究分野：マルチメディア情報処理; 科研費の分化・細目：","subitem_description_type":"Other"}]},"item_8_description_37":{"attribute_name":"資源タイプ(WEKO2)","attribute_value_mlt":[{"subitem_description":"Research Paper","subitem_description_type":"Other"}]},"item_8_description_41":{"attribute_name":"フォーマット","attribute_value_mlt":[{"subitem_description":"application/pdf","subitem_description_type":"Other"}]},"item_8_publisher_14":{"attribute_name":"出版者 名前","attribute_value_mlt":[{"subitem_publisher":"近畿大学"}]},"item_8_text_10":{"attribute_name":"著者 役割","attribute_value_mlt":[{"subitem_text_value":"研究代表者"}]},"item_8_text_7":{"attribute_name":"著者(英)","attribute_value_mlt":[{"subitem_text_language":"en","subitem_text_value":"Shirahama, Kimiaki"}]},"item_8_text_8":{"attribute_name":"著者 所属","attribute_value_mlt":[{"subitem_text_value":"近畿大学理工学部; 准教授"}]},"item_8_text_9":{"attribute_name":"著者所属(翻訳)","attribute_value_mlt":[{"subitem_text_value":"Kindai University"}]},"item_8_version_type_12":{"attribute_name":"版","attribute_value_mlt":[{"subitem_version_resource":"http://purl.org/coar/version/c_be7fb7dd8ff6fe43","subitem_version_type":"NA"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"白浜, 公章"},{"creatorName":"シラハマ, キミアキ","creatorNameLang":"ja-Kana"}],"nameIdentifiers":[{"nameIdentifier":"43477","nameIdentifierScheme":"WEKO"},{"nameIdentifier":"30467675","nameIdentifierScheme":"NRID","nameIdentifierURI":"https://nrid.nii.ac.jp/ja/search/?kw=30467675"}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2022-12-05"}],"displaytype":"detail","filename":"19K12028seika.pdf","filesize":[{"value":"275.8 kB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"19K12028seika.pdf","url":"https://kindai.repo.nii.ac.jp/record/23385/files/19K12028seika.pdf"},"version_id":"6b18ea1f-3aa2-4a50-9fd2-d0286589edf1"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"映像検索","subitem_subject_scheme":"Other"},{"subitem_subject":"物体の時空間関係","subitem_subject_scheme":"Other"},{"subitem_subject":"グラフたたみ込み","subitem_subject_scheme":"Other"},{"subitem_subject":"記憶伝達","subitem_subject_scheme":"Other"},{"subitem_subject":"強化学習","subitem_subject_scheme":"Other"},{"subitem_subject":"TRECVID","subitem_subject_scheme":"Other"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourcetype":"research report","resourceuri":"http://purl.org/coar/resource_type/c_18ws"}]},"item_title":"映像の時空間的関係を知覚可能な検索エンジンの構築","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"映像の時空間的関係を知覚可能な検索エンジンの構築","subitem_title_language":"ja"},{"subitem_title":"Building a Video Search Engine based on the Perception of Spatio-temporal Relations","subitem_title_language":"en"}]},"item_type_id":"8","owner":"3","path":["4819"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2022-12-05"},"publish_date":"2022-12-05","publish_status":"0","recid":"23385","relation_version_is_last":true,"title":["映像の時空間的関係を知覚可能な検索エンジンの構築"],"weko_creator_id":"3","weko_shared_id":-1},"updated":"2023-09-12T06:14:18.282779+00:00"}