{"id":214869,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00214869","sets":["6504:10735:10808"]},"path":["10808"],"owner":"44499","recid":"214869","title":["セマンティックセグメンテーションネットワークを用いた超解像"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-03-04"},"_buckets":{"deposit":"63356776-468c-417e-8b8f-c01313c0ee72"},"_deposit":{"id":"214869","pid":{"type":"depid","value":"214869","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"セマンティックセグメンテーションネットワークを用いた超解像","author_link":["552976","552977"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"セマンティックセグメンテーションネットワークを用いた超解像"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"人工知能と認知科学","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2021-03-04","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_22_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"法大"},{"subitem_text_value":"法大"}]},"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/214869/files/IPSJ-Z83-5M-08.pdf","label":"IPSJ-Z83-5M-08.pdf"},"date":[{"dateType":"Available","dateValue":"2021-12-28"}],"format":"application/pdf","filename":"IPSJ-Z83-5M-08.pdf","filesize":[{"value":"816.9 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"668cf8d7-2cac-4e07-9f0e-8f974e3b0729","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"廣瀬, 理陽"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"藤田, 悟"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_22_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00349328","subitem_source_identifier_type":"NCID"}]},"item_22_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"近年，画像の高解像度化を目指す超解像技術は，畳み込みニューラルネットワーク(CNN)を用いることにより，年々その性能が向上している．2014年には3層の畳み込み層で構成されたSRCNNが提案され，その後GANによる損失関数を用いたSRGANや，特徴マップに重みづけをするRCANなど，特に画像の高周波成分の再現に注力したネットワークがこれまで提案されてきた．しかしこれらは，物体の輪郭や質感など，特に高い性能を示す画像領域が異なるため，領域ごとにネットワークを使い分けることでさらなる性能の向上が期待できる．本研究では，セグメンテーションネットワークを用いて，画像領域ごとに最適な超解像CNNを選択する手法を提案する．","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"128","bibliographic_titles":[{"bibliographic_title":"第83回全国大会講演論文集"}],"bibliographicPageStart":"127","bibliographicIssueDates":{"bibliographicIssueDate":"2021-03-04","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2021"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T16:25:47.974330+00:00","created":"2025-01-19T01:15:39.763089+00:00","links":{}}