WEKO3
アイテム
{"_buckets": {"deposit": "afa524e1-f2f5-41ea-a7a2-029528d975f5"}, "_deposit": {"id": "8686", "owners": [], "pid": {"revision_id": 0, "type": "depid", "value": "8686"}, "status": "published"}, "_oai": {"id": "oai:nagoya.repo.nii.ac.jp:00008686", "sets": ["1038"]}, "author_link": ["24432", "24433", "24434", "24435", "24436"], "item_18_biblio_info_6": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2006-12", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "62", "bibliographicPageStart": "61", "bibliographic_titles": [{"bibliographic_title": "4th Symposium on \"Intelligent Media Integration for Social Information Infrastructure\" December 7-8, 2006", "bibliographic_titleLang": "en"}]}]}, "item_18_description_4": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "The estimation of 3D human pose from a single image can be implemented in the way of large-scale image retrieval. For a given input image, a few similar images are retrieved from the database consisting of human figure images anotated with 3D human poses; then the 3D poses corresponding to retrieved images serve as the pose estimates of input image. This retrieval-based method sounds too simple, but it works if two conditions are met: (i)sufficient data and (ii)good image matching algorithm. Sufficient data can be generated by means of 3D character rendering software and various human motion data. As for good image matching algorithm, here we employ the chamfer distance which has proved to be an effective tool for shape comparison in many works. However, applying the chamfer distance, as well as other good image-matching algorithms, to large-scale problem would lead to high time requirements. In order to address this computational issue, here we propose an approximate chamfer distance which is capable of achieving significant efficiency improvements with slight accuracy loss: over three hundred times faster than exact chamfer distance in current implementation.", "subitem_description_language": "en", "subitem_description_type": "Abstract"}]}, "item_18_identifier_60": {"attribute_name": "URI", "attribute_value_mlt": [{"subitem_identifier_type": "HDL", "subitem_identifier_uri": "http://hdl.handle.net/2237/10437"}]}, "item_18_publisher_32": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "INTELLIGENT MEDIA INTEGRATION NAGOYA UNIVERSITY / COE", "subitem_publisher_language": "en"}]}, "item_18_select_15": {"attribute_name": "著者版フラグ", "attribute_value_mlt": [{"subitem_select_item": "publisher"}]}, "item_18_text_14": {"attribute_name": "フォーマット", "attribute_value_mlt": [{"subitem_text_value": "application/pdf"}]}, "item_access_right": {"attribute_name": "アクセス権", "attribute_value_mlt": [{"subitem_access_right": "open access", "subitem_access_right_uri": "http://purl.org/coar/access_right/c_abf2"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Cao, Hui", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24432", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Ohnishi, Noboru", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24433", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Takeuchi, Yoshinori", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24434", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Matsumoto, Tetsuya", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24435", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Kudo, Hiroaki", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24436", "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": "2018-02-19"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "p61-62_Fast_human_pose_retrieval_using_approximate_chamfer_distance.pdf", "filesize": [{"value": "8.3 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_note", "mimetype": "application/pdf", "size": 8300000.000000001, "url": {"label": "p61-62_Fast_human_pose_retrieval_using_approximate_chamfer_distance.pdf", "objectType": "fulltext", "url": "https://nagoya.repo.nii.ac.jp/record/8686/files/p61-62_Fast_human_pose_retrieval_using_approximate_chamfer_distance.pdf"}, "version_id": "0fc146a0-490b-4eee-9289-2dfcce1a3cd3"}]}, "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": "conference paper", "resourceuri": "http://purl.org/coar/resource_type/c_5794"}]}, "item_title": "FAST HUMAN POSE RETRIEVAL USING APPROXIMATE CHAMFER DISTANCE", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "FAST HUMAN POSE RETRIEVAL USING APPROXIMATE CHAMFER DISTANCE", "subitem_title_language": "en"}]}, "item_type_id": "18", "owner": "1", "path": ["1038"], "permalink_uri": "http://hdl.handle.net/2237/10437", "pubdate": {"attribute_name": "PubDate", "attribute_value": "2008-08-22"}, "publish_date": "2008-08-22", "publish_status": "0", "recid": "8686", "relation": {}, "relation_version_is_last": true, "title": ["FAST HUMAN POSE RETRIEVAL USING APPROXIMATE CHAMFER DISTANCE"], "weko_shared_id": -1}
FAST HUMAN POSE RETRIEVAL USING APPROXIMATE CHAMFER DISTANCE
http://hdl.handle.net/2237/10437
http://hdl.handle.net/2237/10437f50cf5e5-442f-420f-bbe5-8a5eb34bffeb
名前 / ファイル | ライセンス | アクション |
---|---|---|
![]() |
|
Item type | 会議発表論文 / Conference Paper(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2008-08-22 | |||||
タイトル | ||||||
タイトル | FAST HUMAN POSE RETRIEVAL USING APPROXIMATE CHAMFER DISTANCE | |||||
言語 | en | |||||
著者 |
Cao, Hui
× Cao, Hui× Ohnishi, Noboru× Takeuchi, Yoshinori× Matsumoto, Tetsuya× Kudo, Hiroaki |
|||||
アクセス権 | ||||||
アクセス権 | open access | |||||
アクセス権URI | http://purl.org/coar/access_right/c_abf2 | |||||
抄録 | ||||||
内容記述 | The estimation of 3D human pose from a single image can be implemented in the way of large-scale image retrieval. For a given input image, a few similar images are retrieved from the database consisting of human figure images anotated with 3D human poses; then the 3D poses corresponding to retrieved images serve as the pose estimates of input image. This retrieval-based method sounds too simple, but it works if two conditions are met: (i)sufficient data and (ii)good image matching algorithm. Sufficient data can be generated by means of 3D character rendering software and various human motion data. As for good image matching algorithm, here we employ the chamfer distance which has proved to be an effective tool for shape comparison in many works. However, applying the chamfer distance, as well as other good image-matching algorithms, to large-scale problem would lead to high time requirements. In order to address this computational issue, here we propose an approximate chamfer distance which is capable of achieving significant efficiency improvements with slight accuracy loss: over three hundred times faster than exact chamfer distance in current implementation. | |||||
言語 | en | |||||
内容記述タイプ | Abstract | |||||
出版者 | ||||||
言語 | en | |||||
出版者 | INTELLIGENT MEDIA INTEGRATION NAGOYA UNIVERSITY / COE | |||||
言語 | ||||||
言語 | eng | |||||
資源タイプ | ||||||
資源 | http://purl.org/coar/resource_type/c_5794 | |||||
タイプ | conference paper | |||||
書誌情報 |
en : 4th Symposium on "Intelligent Media Integration for Social Information Infrastructure" December 7-8, 2006 p. 61-62, 発行日 2006-12 |
|||||
フォーマット | ||||||
application/pdf | ||||||
著者版フラグ | ||||||
値 | publisher | |||||
URI | ||||||
識別子 | http://hdl.handle.net/2237/10437 | |||||
識別子タイプ | HDL |