{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00229258","sets":["1164:4619:11188:11420"]},"path":["11420"],"owner":"44499","recid":"229258","title":["人物3次元姿勢逐次予測のためのRecurrent Graph Convolutional Network"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-11-09"},"_buckets":{"deposit":"3877be1f-ebc4-40f2-95a6-c8d97e561aa6"},"_deposit":{"id":"229258","pid":{"type":"depid","value":"229258","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"人物3次元姿勢逐次予測のためのRecurrent Graph Convolutional Network","author_link":["616205","616206"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"人物3次元姿勢逐次予測のためのRecurrent Graph Convolutional Network"}]},"item_type_id":"4","publish_date":"2023-11-09","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"理化学研究所ガーディアンロボットプロジェクト"},{"subitem_text_value":"理化学研究所ガーディアンロボットプロジェクト"}]},"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/229258/files/IPSJ-CVIM23235038.pdf","label":"IPSJ-CVIM23235038.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM23235038.pdf","filesize":[{"value":"1.4 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"20"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"29b06ca8-55b6-49fc-a3f0-1ae5616c2810","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 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":"藤田, 倫弘"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"川西, 康友"}],"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_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8701","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"関節点の 3 次元座標の組で表される人物の 3 次元姿勢の系列からその先の時刻における姿勢系列を正確に予測するために，グラフ畳み込みネットワークを用いた手法が近年注目を集めている．しかしグラフ畳み込みを用いた多くの既存手法では入力系列のすべてから 1 つの特徴量を抽出して一度に予測するため，予測に必要な時間計算量及び空間計算量が高く，入出力処理の待ち時間が長いという問題点がある．本発表では，小さい計算量で時系列を逐次処理可能な RNN の利点に着目し，グラフ構造を持つ時系列データを逐次処理することが可能な Recurrent Graph Convolutional Network とそれを用いる姿勢予測手法を提案し，計算量と待ち時間の改善を試みる．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告コンピュータビジョンとイメージメディア（CVIM）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2023-11-09","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"38","bibliographicVolumeNumber":"2023-CVIM-235"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":229258,"updated":"2025-01-19T11:35:08.402236+00:00","links":{},"created":"2025-01-19T01:28:24.035899+00:00"}