{"created":"2025-01-19T01:29:32.989704+00:00","updated":"2025-01-19T11:19:02.743876+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00230032","sets":["6504:11436:11440"]},"path":["11440"],"owner":"44499","recid":"230032","title":["Transformerを活用したGANによる手振れ補正モデルの検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-02-16"},"_buckets":{"deposit":"3fed943e-2fd5-4ca5-99b6-1ab3a8c73230"},"_deposit":{"id":"230032","pid":{"type":"depid","value":"230032","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Transformerを活用したGANによる手振れ補正モデルの検討","author_link":["618879","618878"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Transformerを活用したGANによる手振れ補正モデルの検討"}]},"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":"2023-02-16","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/230032/files/IPSJ-Z85-7S-05.pdf","label":"IPSJ-Z85-7S-05.pdf"},"date":[{"dateType":"Available","dateValue":"2023-11-17"}],"format":"application/pdf","filename":"IPSJ-Z85-7S-05.pdf","filesize":[{"value":"514.2 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"a5bf1dfa-d95e-46e3-b5d0-61449951fca5","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"大口, 瑞妃"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"佐藤, 裕二"}],"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":"本研究では, GAN を利用した手振れ補正モデルの精度向上を目的として, Transformer を活用した手法を提案する. GAN はデータの分布を捉えデータを生成するモデルと, 入力データが, 生成データの実データかを識別するモデルが相互に学習し, 精度を高める. 先行研究では, GAN を発展させ, 手振れ画像から鮮明な画像を生成するモデルが提案された. CNN を利用したモデルには, 画像全体を加味した特徴を捉えることが不得手という課題がある. そこで大域的に特徴を捉えることが可能なTransformer を生成モデルに活用することで, より効果的に特徴を捉えることができる手振れ補正モデルを提案する. 画像の劣化度を示す評価指標により, 提案手法が効率的に学習を行えることを示す.","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"476","bibliographic_titles":[{"bibliographic_title":"第85回全国大会講演論文集"}],"bibliographicPageStart":"475","bibliographicIssueDates":{"bibliographicIssueDate":"2023-02-16","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2023"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":230032,"links":{}}