{"updated":"2025-01-19T09:22:05.117591+00:00","links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00236163","sets":["6504:11678:11689"]},"path":["11689"],"owner":"44499","recid":"236163","title":["ViTエンコーダを活用した画像キャプション生成モデルの構築と評価"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-03-01"},"_buckets":{"deposit":"674af0b6-efe0-48d9-a03a-2836e0dce6ed"},"_deposit":{"id":"236163","pid":{"type":"depid","value":"236163","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"ViTエンコーダを活用した画像キャプション生成モデルの構築と評価","author_link":["645485","645484"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"ViTエンコーダを活用した画像キャプション生成モデルの構築と評価"}]},"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":"2024-03-01","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":"愛媛大"},{"subitem_text_value":"愛媛大"}]},"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/236163/files/IPSJ-Z86-7T-05.pdf","label":"IPSJ-Z86-7T-05.pdf"},"date":[{"dateType":"Available","dateValue":"2024-07-03"}],"format":"application/pdf","filename":"IPSJ-Z86-7T-05.pdf","filesize":[{"value":"1.1 MB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"cd6be586-f379-4d19-81bc-e535cb343840","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"岡本, 翔汰"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"黒田, 久泰"}],"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":"画像キャプション生成は，画像を入力すると画像の内容を説明する文章（キャプション）を生成する処理である．この研究では，Transformerアーキテクチャを持つ事前学習済みのVision Transformer（ViT）を画像キャプション生成のためのエンコーダに採用した．ViTは，画像を細かく分割し，その特徴をTransformerによって抽出する特異的なアプローチを提供している．CNNを用いた画像キャプション生成モデルとViTエンコーダを導入したモデルを比較し，その性能を評価した．","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"652","bibliographic_titles":[{"bibliographic_title":"第86回全国大会講演論文集"}],"bibliographicPageStart":"651","bibliographicIssueDates":{"bibliographicIssueDate":"2024-03-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2024"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":236163,"created":"2025-01-19T01:38:03.840842+00:00"}