{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00211203","sets":["581:10433:10438"]},"path":["10438"],"owner":"44499","recid":"211203","title":["MirrorNet: A Deep Reflective Approach to 2D Pose Estimation for Single-Person Images"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-05-15"},"_buckets":{"deposit":"fdabc6cd-ae6f-4248-a0c4-229927dc6e47"},"_deposit":{"id":"211203","pid":{"type":"depid","value":"211203","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"MirrorNet: A Deep Reflective Approach to 2D Pose Estimation for Single-Person Images","author_link":["536198","536200","536194","536196","536195","536204","536197","536199","536202","536193","536201","536203"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"MirrorNet: A Deep Reflective Approach to 2D Pose Estimation for Single-Person Images"},{"subitem_title":"MirrorNet: A Deep Reflective Approach to 2D Pose Estimation for Single-Person Images","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"[一般論文] 2D pose estimation, amortized variational inference, variational autoencoder, mirror system","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2021-05-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Waseda University"},{"subitem_text_value":"Kyoto University"},{"subitem_text_value":"National Institute of Advanced Industrial Science and Technology (AIST)"},{"subitem_text_value":"National Institute of Advanced Industrial Science and Technology (AIST)"},{"subitem_text_value":"National Institute of Advanced Industrial Science and Technology (AIST)"},{"subitem_text_value":"Waseda Research Institute for Science and Engineering"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Waseda University","subitem_text_language":"en"},{"subitem_text_value":"Kyoto University","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Advanced Industrial Science and Technology (AIST)","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Advanced Industrial Science and Technology (AIST)","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Advanced Industrial Science and Technology (AIST)","subitem_text_language":"en"},{"subitem_text_value":"Waseda Research Institute for Science and Engineering","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/211203/files/IPSJ-JNL6205013.pdf","label":"IPSJ-JNL6205013.pdf"},"date":[{"dateType":"Available","dateValue":"2023-05-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL6205013.pdf","filesize":[{"value":"6.0 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":"0d0f3f7a-0b20-46e8-adbf-0efd8c02b4d3","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Takayuki, Nakatsuka"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kazuyoshi, Yoshii"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yuki, Koyama"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Satoru, Fukayama"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Masataka, Goto"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shigeo, Morishima"}],"nameIdentifiers":[{}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Takayuki, Nakatsuka","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kazuyoshi, Yoshii","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yuki, Koyama","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Satoru, Fukayama","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Masataka, Goto","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shigeo, Morishima","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_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":"This paper proposes a statistical approach to 2D pose estimation from human images. The main problems with the standard supervised approach, which is based on a deep recognition (image-to-pose) model, are that it often yields anatomically implausible poses, and its performance is limited by the amount of paired data. To solve these problems, we propose a semi-supervised method that can make effective use of images with and without pose annotations. Specifically, we formulate a hierarchical generative model of poses and images by integrating a deep generative model of poses from pose features with that of images from poses and image features. We then introduce a deep recognition model that infers poses from images. Given images as observed data, these models can be trained jointly in a hierarchical variational autoencoding (image-to-pose-to-feature-to-pose-to-image) manner. The results of experiments show that the proposed reflective architecture makes estimated poses anatomically plausible, and the pose estimation performance is improved by integrating the recognition and generative models and also by feeding non-annotated images.\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.29(2021) (online)\nDOI　http://dx.doi.org/10.2197/ipsjjip.29.406\n------------------------------","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"This paper proposes a statistical approach to 2D pose estimation from human images. The main problems with the standard supervised approach, which is based on a deep recognition (image-to-pose) model, are that it often yields anatomically implausible poses, and its performance is limited by the amount of paired data. To solve these problems, we propose a semi-supervised method that can make effective use of images with and without pose annotations. Specifically, we formulate a hierarchical generative model of poses and images by integrating a deep generative model of poses from pose features with that of images from poses and image features. We then introduce a deep recognition model that infers poses from images. Given images as observed data, these models can be trained jointly in a hierarchical variational autoencoding (image-to-pose-to-feature-to-pose-to-image) manner. The results of experiments show that the proposed reflective architecture makes estimated poses anatomically plausible, and the pose estimation performance is improved by integrating the recognition and generative models and also by feeding non-annotated images.\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.29(2021) (online)\nDOI　http://dx.doi.org/10.2197/ipsjjip.29.406\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":"2021-05-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"5","bibliographicVolumeNumber":"62"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":211203,"updated":"2025-01-19T17:52:49.202686+00:00","links":{},"created":"2025-01-19T01:12:23.383741+00:00"}