{"id":2007530,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:02007530","sets":["1164:3027:1766467250990:1771205384679"]},"path":["1771205384679"],"owner":"80578","recid":"2007530","title":["マルチモーダルAIモデルを用いたコーディネート提案システムの構築"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2026-03-02"},"_buckets":{"deposit":"247026fd-a583-400b-9df3-018617a6e837"},"_deposit":{"id":"2007530","pid":{"type":"depid","value":"2007530","revision_id":0},"owners":[80578],"status":"published","created_by":80578},"item_title":"マルチモーダルAIモデルを用いたコーディネート提案システムの構築","author_link":[],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"マルチモーダルAIモデルを用いたコーディネート提案システムの構築","subitem_title_language":"ja"},{"subitem_title":"Construction of a Clothing Coordination Suggestion System Using Multimodal AI Models","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2026-03-02","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"和歌山大学大学院システム工学研究科"},{"subitem_text_value":"和歌山大学システム工学部"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Wakayama University","subitem_text_language":"en"},{"subitem_text_value":"Wakayama University","subitem_text_language":"en"}]},"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/2007530/files/IPSJ-HCI26217017.pdf","label":"IPSJ-HCI26217017.pdf"},"date":[{"dateType":"Available","dateValue":"2028-03-02"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-HCI26217017.pdf","filesize":[{"value":"1.2 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"33"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"d3ff0789-ba70-43cc-b34e-88a4673b1cec","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2026 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"蘇,晏"}]},{"creatorNames":[{"creatorName":"坂間,千秋"}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Su Yan","creatorNameLang":"en"}]},{"creatorNames":[{"creatorName":"Chiaki Sakama","creatorNameLang":"en"}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA1221543X","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":"2188-8760","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本研究では，物体検出，視覚-言語モデル，大規模言語モデル(LLM)，および画像生成モデルを統合したマルチモーダルファッション提案システムを開発する．先ず物体検出モデルYOLOを用いて服装領域を抽出し，視覚-言語モデルCLIP-ViTにより服装の構造および属性を意味的に判別する. 次にLLMを用いて視覚モデルの出力結果とユーザ入力の文脈情報を統合し，自然言語によるコーディネート説明文を生成する．最後に提案システムの有効性を，実験評価する．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In this study, we develop a multimodal fashion recommendation system that integrates object detection, vision-language models, LLMs, and image generation models. First, we use the YOLO object detection model to extract clothing regions with high precision, followed by the CLIP-ViT vision-language model to semantically determine the structure and attributes of the garments. Next, an LLM is utilized to integrate the output from the vision models with the contextual information of user inputs to generate natural language descriptions for coordinated outfits. Finally, the effectiveness of the proposed multimodal system is verified through experiments.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告ヒューマンコンピュータインタラクション（HCI）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2026-03-02","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"17","bibliographicVolumeNumber":"2026-HCI-217"}]},"relation_version_is_last":true,"weko_creator_id":"80578"},"updated":"2026-02-18T02:46:52.115384+00:00","created":"2026-02-18T02:46:48.165397+00:00","links":{}}