{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00233729","sets":["581:11492:11496"]},"path":["11496"],"owner":"44499","recid":"233729","title":["Image-to-Text Translation for Interactive Image Recognition: A Comparative User Study with Non-expert Users"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-04-15"},"_buckets":{"deposit":"a07f62bc-9fb1-4600-a213-8b35c82aebbc"},"_deposit":{"id":"233729","pid":{"type":"depid","value":"233729","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Image-to-Text Translation for Interactive Image Recognition: A Comparative User Study with Non-expert Users","author_link":["635537","635534","635536","635535"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Image-to-Text Translation for Interactive Image Recognition: A Comparative User Study with Non-expert Users"},{"subitem_title":"Image-to-Text Translation for Interactive Image Recognition: A Comparative User Study with Non-expert Users","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"[一般論文] interactive machine learning, graphical user interface","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2024-04-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"The University of Tokyo"},{"subitem_text_value":"The University of Tokyo"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"The University of Tokyo","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"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/233729/files/IPSJ-JNL6504010.pdf","label":"IPSJ-JNL6504010.pdf"},"date":[{"dateType":"Available","dateValue":"2026-04-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL6504010.pdf","filesize":[{"value":"8.1 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"5"},{"tax":["include_tax"],"price":"0","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"6f6c2dde-e109-43db-9106-a35dd0ab1d15","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Wataru, Kawabe"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yusuke, Sugano"}],"nameIdentifiers":[{}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Wataru, Kawabe","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yusuke, Sugano","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_2_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00116647","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_2_publisher_15":{"attribute_name":"公開者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"item_2_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7764","subitem_source_identifier_type":"ISSN"}]},"item_2_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"Interactive machine learning (IML) allows users to build their custom machine learning models without expert knowledge. While most existing IML systems are designed with classification algorithms, they sometimes oversimplify the capabilities of machine learning algorithms and restrict the user's task definition. On the other hand, as recent large-scale language models have shown, natural language representation has the potential to enable more flexible and generic task descriptions. Models that take images as input and output text have the potential to represent a variety of tasks by providing appropriate text labels for training. However, the effect of introducing text labels to IML system design has never been investigated. In this work, we aim to investigate the difference between image-to-text translation and image classification for IML systems. Using our prototype systems, we conducted a comparative user study with non-expert users, where participants solved various tasks. Our results demonstrate the underlying difficulty for users in properly defining image recognition tasks while highlighting the potential and challenges of interactive image-to-text translation systems.\n------------------------------\nThis is a preprint of an article intended for publication Journal of\nInformation Processing(JIP). This preprint should not be cited. This\narticle should be cited as: Journal of Information Processing Vol.32(2024) (online)\nDOI　http://dx.doi.org/10.2197/ipsjjip.32.358\n------------------------------","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Interactive machine learning (IML) allows users to build their custom machine learning models without expert knowledge. While most existing IML systems are designed with classification algorithms, they sometimes oversimplify the capabilities of machine learning algorithms and restrict the user's task definition. On the other hand, as recent large-scale language models have shown, natural language representation has the potential to enable more flexible and generic task descriptions. Models that take images as input and output text have the potential to represent a variety of tasks by providing appropriate text labels for training. However, the effect of introducing text labels to IML system design has never been investigated. In this work, we aim to investigate the difference between image-to-text translation and image classification for IML systems. Using our prototype systems, we conducted a comparative user study with non-expert users, where participants solved various tasks. Our results demonstrate the underlying difficulty for users in properly defining image recognition tasks while highlighting the potential and challenges of interactive image-to-text translation systems.\n------------------------------\nThis is a preprint of an article intended for publication Journal of\nInformation Processing(JIP). This preprint should not be cited. This\narticle should be cited as: Journal of Information Processing Vol.32(2024) (online)\nDOI　http://dx.doi.org/10.2197/ipsjjip.32.358\n------------------------------","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicIssueDates":{"bibliographicIssueDate":"2024-04-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"4","bibliographicVolumeNumber":"65"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T10:00:30.932483+00:00","created":"2025-01-19T01:35:16.677127+00:00","id":233729}