{"links":{},"id":195881,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00195881","sets":["1164:4619:9659:9791"]},"path":["9791"],"owner":"44499","recid":"195881","title":["画像を説明する多言語音声データを利用したクロスモーダル探索"],"pubdate":{"attribute_name":"公開日","attribute_value":"2019-05-23"},"_buckets":{"deposit":"085ddfa1-5dfd-404f-9a64-c9cc579eb465"},"_deposit":{"id":"195881","pid":{"type":"depid","value":"195881","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"画像を説明する多言語音声データを利用したクロスモーダル探索","author_link":["467957","467959","467962","467954","467956","467953","467958","467961","467963","467952","467960","467955"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"画像を説明する多言語音声データを利用したクロスモーダル探索"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"一般セッション2","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2019-05-23","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"日本電信電話株式会社コミュニケーション科学基礎研究所"},{"subitem_text_value":"日本電信電話株式会社コミュニケーション科学基礎研究所"},{"subitem_text_value":"日本電信電話株式会社コミュニケーション科学基礎研究所"},{"subitem_text_value":"日本電信電話株式会社コミュニケーション科学基礎研究所"},{"subitem_text_value":"Spoken Language Systems Croup, MIT Computer Science and Artificial Intelligence Laboratory"},{"subitem_text_value":"Spoken Language Systems Croup, MIT Computer Science and Artificial Intelligence Laboratory"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"NTT Communication Science Laboratories, NTT Corporation","subitem_text_language":"en"},{"subitem_text_value":"NTT Communication Science Laboratories, NTT Corporation","subitem_text_language":"en"},{"subitem_text_value":"NTT Communication Science Laboratories, NTT Corporation","subitem_text_language":"en"},{"subitem_text_value":"NTT Communication Science Laboratories, NTT Corporation","subitem_text_language":"en"},{"subitem_text_value":"Spoken Language Systems Croup, MIT Computer Science and Artificial Intelligence Laboratory","subitem_text_language":"en"},{"subitem_text_value":"Spoken Language Systems Croup, MIT Computer Science and Artificial Intelligence Laboratory","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":44499,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/195881/files/IPSJ-CVIM19217042.pdf","label":"IPSJ-CVIM19217042.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM19217042.pdf","filesize":[{"value":"3.2 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"20"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"58dca26e-729c-4cf6-a81a-1fd787088108","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2019 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"大石, 康智"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"木村, 昭悟"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"川西, 隆仁"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"柏野, 邦夫"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"David, Harwath"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"James, Glass"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yasunori, Ohishi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Akisato, Kimura","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takahito, Kawanishi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kunio, Kashino","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"David, Harwath","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"James, Glass","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11131797","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":"2188-8701","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"画像とその内容を説明する音声キャプションを対応付けるためのニューラルネットワークモデルをクロスモーダル探索の観点で評価する．英語やヒンディ語に加えて，新たに収録した日本語音声キャプションからなる 3 か国語で学習したモデルは 1 か国語だけで学習したモデルよりも精度が高いことを確認した．この 3 か国語モデルは，画像を基点として，異なる言語における音声単語を教師なしで対応付け，単語レベルの翻訳知識を獲得することを示す．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"We evaluate a deep neural network model capable of learning to associate images and audio captions describing the content of those images on crossmodal search ( image and speech retrieval ). We show that training a trilingual model simultaneously on English, Hindi, and newly recorded Japanese audio caption data offers improved performance over the monolingual models. Further, we demonstrate the trilingual model implicitly learns meaningful word-level translations based on images.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告コンピュータビジョンとイメージメディア（CVIM）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2019-05-23","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"42","bibliographicVolumeNumber":"2019-CVIM-217"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T01:00:45.869776+00:00","updated":"2025-01-19T22:51:16.577352+00:00"}