{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00236162","sets":["6504:11678:11689"]},"path":["11689"],"owner":"44499","recid":"236162","title":["ゼロショット参照表現理解のためのReCLIPの改良"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-03-01"},"_buckets":{"deposit":"35910d3a-58ad-417f-8f67-6e68fd7fb41f"},"_deposit":{"id":"236162","pid":{"type":"depid","value":"236162","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"ゼロショット参照表現理解のためのReCLIPの改良","author_link":["645483","645482"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"ゼロショット参照表現理解のためのReCLIPの改良"}]},"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":"名工大"},{"subitem_text_value":"名工大"}]},"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/236162/files/IPSJ-Z86-7T-04.pdf","label":"IPSJ-Z86-7T-04.pdf"},"date":[{"dateType":"Available","dateValue":"2024-07-03"}],"format":"application/pdf","filename":"IPSJ-Z86-7T-04.pdf","filesize":[{"value":"541.0 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"d5423a66-ddfe-4034-8316-de63430e65f8","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":"野村, 大輝"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"田口, 亮"}],"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":"テキストの参照表現から画像内のオブジェクトを指定する参照表現理解（Referring Expression Comprehension）というタスクにおいて，言語と画像のマルチモーダルモデルであるCLIPとヒューリスティックス的な手法を組み合わせて追加学習無し（ゼロショット）で実現したReCLIPと呼ばれるモデルがある．このReCLIPに対して，セグメンテーションのための基盤モデルであるSegment Anything Modelを用いて，ゼロショットを維持したまま任意の画像とテキストで実行できるように拡張した．また，テキスト中の参照表現に関係のないオブジェクトを事前に省くことで精度の向上を図った．","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"650","bibliographic_titles":[{"bibliographic_title":"第86回全国大会講演論文集"}],"bibliographicPageStart":"649","bibliographicIssueDates":{"bibliographicIssueDate":"2024-03-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2024"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":236162,"updated":"2025-01-19T09:22:06.585405+00:00","links":{},"created":"2025-01-19T01:38:03.745706+00:00"}