WEKO3
アイテム
{"_buckets": {"deposit": "93478465-6b61-4fc4-917f-0f391fd92520"}, "_deposit": {"created_by": 13, "id": "8868", "owners": [13], "pid": {"revision_id": 0, "type": "depid", "value": "8868"}, "status": "published"}, "_oai": {"id": "oai:uec.repo.nii.ac.jp:00008868", "sets": ["6"]}, "author_link": ["24112", "24111", "24113", "24110", "24114", "24109"], "item_10001_biblio_info_7": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2020-01", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "1", "bibliographicPageEnd": "337", "bibliographicPageStart": " 324", "bibliographicVolumeNumber": "50", "bibliographic_titles": [{}, {"bibliographic_title": "IEEE Transactions on Cybernetics", "bibliographic_titleLang": "en"}]}]}, "item_10001_description_5": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "Face hallucination is a technique that reconstruct high-resolution (HR) faces from low-resolution (LR) faces, by using the prior knowledge learned from HR/LR face pairs. Most state-of-the-arts leverage position-patch prior knowledge of human face to estimate the optimal representation coefficients for each image patch. However, they focus only the position information and usually ignore the context information of image patch. In addition, when they are confronted with misalignment or the Small Sample Size (SSS) problem, the hallucination performance is very poor. To this end, this study incorporates the contextual information of image patch and proposes a powerful and efficient context-patch based face hallucination approach, namely Thresholding Locality-constrained Representation and Reproducing learning (TLcR-RL). Under the context-patch based framework, we advance a thresholding based representation method to enhance the reconstruction accuracy and reduce the computational complexity. To further improve the performance of the proposed algorithm, we propose a promotion strategy called reproducing learning. By adding the estimated HR face to the training set, which can simulates the case that the HR version of the input LR face is present in the training set, thus iteratively enhancing the final hallucination result. Experiments demonstrate that the proposed TLcR-RL method achieves a substantial increase in the hallucinated results, both subjectively and objectively. Additionally, the proposed framework is more robust to face misalignment and the SSS problem, and its hallucinated HR face is still very good when the LR test face is from the real-world. The MATLAB source code is available at https://github.com/junjun-jiang/TLcR-RL.", "subitem_description_type": "Abstract"}]}, "item_10001_publisher_8": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "IEEE (Institute of Electrical and Electronics Engineers) "}]}, "item_10001_relation_14": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type": "isVersionOf", "subitem_relation_type_id": {"subitem_relation_type_id_text": "10.1109/TCYB.2018.2868891", "subitem_relation_type_select": "DOI"}}]}, "item_10001_relation_17": {"attribute_name": "関連サイト", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "https://doi.org/10.1109/TCYB.2018.2868891", "subitem_relation_type_select": "DOI"}}]}, "item_10001_rights_15": {"attribute_name": "権利", "attribute_value_mlt": [{"subitem_rights": "© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. This is not the published version. Please cite only the published version."}]}, "item_10001_source_id_9": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "2168-2275", "subitem_source_identifier_type": "ISSN"}]}, "item_10001_version_type_20": {"attribute_name": "著者版フラグ", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_ab4af688f83e57aa", "subitem_version_type": "AM"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Jiang, Junjun", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24109", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Yu, Yi", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24110", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Tang, Suhua", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24111", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Ma, Jiayi", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24112", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Qi, Guo-Jun", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24113", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Aizawa, Akiko", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24114", "nameIdentifierScheme": "WEKO"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2019-02-18"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "TLcR.PDF", "filesize": [{"value": "3.1 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 3100000.0, "url": {"label": "TLcR", "url": "https://uec.repo.nii.ac.jp/record/8868/files/TLcR.PDF"}, "version_id": "bc3bab1c-6dc7-46e6-b7d0-b4dadaaac477"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "Image super-resolution", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "face hallucination", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "context-patch", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "position-patch", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "reproducing learning", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "eng"}]}, "item_resource_type": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"resourcetype": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "Context-Patch Face Hallucination Based on Thresholding Locality-Constrained Representation and Reproducing Learning", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Context-Patch Face Hallucination Based on Thresholding Locality-Constrained Representation and Reproducing Learning", "subitem_title_language": "en"}]}, "item_type_id": "10001", "owner": "13", "path": ["6"], "permalink_uri": "https://uec.repo.nii.ac.jp/records/8868", "pubdate": {"attribute_name": "公開日", "attribute_value": "2019-01-15"}, "publish_date": "2019-01-15", "publish_status": "0", "recid": "8868", "relation": {}, "relation_version_is_last": true, "title": ["Context-Patch Face Hallucination Based on Thresholding Locality-Constrained Representation and Reproducing Learning"], "weko_shared_id": -1}
Context-Patch Face Hallucination Based on Thresholding Locality-Constrained Representation and Reproducing Learning
https://uec.repo.nii.ac.jp/records/8868
https://uec.repo.nii.ac.jp/records/88687d7137f0-cf1f-46a1-9f85-32a902db5c68
名前 / ファイル | ライセンス | アクション |
---|---|---|
TLcR (3.1 MB)
|
|
Item type | 学術雑誌論文 / Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2019-01-15 | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | Context-Patch Face Hallucination Based on Thresholding Locality-Constrained Representation and Reproducing Learning | |||||
言語 | ||||||
言語 | eng | |||||
キーワード | ||||||
言語 | en | |||||
主題 | Image super-resolution | |||||
キーワード | ||||||
言語 | en | |||||
主題 | face hallucination | |||||
キーワード | ||||||
言語 | en | |||||
主題 | context-patch | |||||
キーワード | ||||||
言語 | en | |||||
主題 | position-patch | |||||
キーワード | ||||||
言語 | en | |||||
主題 | reproducing learning | |||||
資源タイプ | ||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||
資源タイプ | journal article | |||||
著者 |
Jiang, Junjun
× Jiang, Junjun× Yu, Yi× Tang, Suhua× Ma, Jiayi× Qi, Guo-Jun× Aizawa, Akiko |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | Face hallucination is a technique that reconstruct high-resolution (HR) faces from low-resolution (LR) faces, by using the prior knowledge learned from HR/LR face pairs. Most state-of-the-arts leverage position-patch prior knowledge of human face to estimate the optimal representation coefficients for each image patch. However, they focus only the position information and usually ignore the context information of image patch. In addition, when they are confronted with misalignment or the Small Sample Size (SSS) problem, the hallucination performance is very poor. To this end, this study incorporates the contextual information of image patch and proposes a powerful and efficient context-patch based face hallucination approach, namely Thresholding Locality-constrained Representation and Reproducing learning (TLcR-RL). Under the context-patch based framework, we advance a thresholding based representation method to enhance the reconstruction accuracy and reduce the computational complexity. To further improve the performance of the proposed algorithm, we propose a promotion strategy called reproducing learning. By adding the estimated HR face to the training set, which can simulates the case that the HR version of the input LR face is present in the training set, thus iteratively enhancing the final hallucination result. Experiments demonstrate that the proposed TLcR-RL method achieves a substantial increase in the hallucinated results, both subjectively and objectively. Additionally, the proposed framework is more robust to face misalignment and the SSS problem, and its hallucinated HR face is still very good when the LR test face is from the real-world. The MATLAB source code is available at https://github.com/junjun-jiang/TLcR-RL. | |||||
書誌情報 |
en : IEEE Transactions on Cybernetics 巻 50, 号 1, p. 324-337, 発行日 2020-01 |
|||||
出版者 | ||||||
出版者 | IEEE (Institute of Electrical and Electronics Engineers) | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 2168-2275 | |||||
DOI | ||||||
関連タイプ | isVersionOf | |||||
識別子タイプ | DOI | |||||
関連識別子 | 10.1109/TCYB.2018.2868891 | |||||
権利 | ||||||
権利情報 | © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. This is not the published version. Please cite only the published version. | |||||
関連サイト | ||||||
識別子タイプ | DOI | |||||
関連識別子 | https://doi.org/10.1109/TCYB.2018.2868891 | |||||
著者版フラグ | ||||||
出版タイプ | AM | |||||
出版タイプResource | http://purl.org/coar/version/c_ab4af688f83e57aa |