{"id":805,"date":"2020-12-19T21:18:19","date_gmt":"2020-12-19T13:18:19","guid":{"rendered":"https:\/\/511cvlab.sinkers.cn\/?p=805"},"modified":"2025-10-17T16:52:01","modified_gmt":"2025-10-17T08:52:01","slug":"awr","status":"publish","type":"post","link":"https:\/\/cv.nirc.top\/zh\/2020\/awr\/","title":{"rendered":"AWR: Adaptive Weighting Regression for 3D Hand Pose Estimation"},"content":{"rendered":"
\n

1<\/sup>State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, 2<\/sup>EBUPT Information Technology Co., Ltd.<\/p>\n\n\n\n

\n \n
\n \n
\n \n \n <\/path>\n <\/svg>\n <\/div>\n
Paper<\/div>\n <\/a>\n <\/div>\n\n
\n \n
\n \n \n <\/path>\n <\/svg>\n <\/div>\n
Code<\/div>\n <\/a>\n <\/div>\n\n\n <\/div>\n<\/div>\n\n\n\n
\"\"\n\t\t\t\n\t\t\t\t\n\t\t\t<\/svg>\n\t\t<\/button>
The target joint (index fingertip) is visible (top row) or occluded (middle row) and when there exists self-similarity among fingers (bottom row).<\/figcaption><\/figure>\n\n\n\n

We introduce adaptive weighting regression (AWR)<\/strong> method. The weight distribution in weight maps<\/strong> can be adjusted adaptively<\/strong> to achieve more accurate and robust performance under the guidance of joint supervision. Top row<\/strong>: When the target joint is visible and easy to distinguish<\/strong>, the weight distribution of AWR tends to focus more on pixels around it, as standard detection-based methods do. Middle row & bottom row<\/strong>: When depth values around the target joint are heavily missing due to occlusion or under the situation of severe self-similarity among fingers<\/strong>, the weight distribution spreads out<\/strong> to capture information of adjacent joints.<\/p>\n\n\n\n

Overview<\/h2>\n\n\n\n
\"\"\/\n\t\t\t\n\t\t\t\t\n\t\t\t<\/svg>\n\t\t<\/button>
Main idea of AWR.<\/figcaption><\/figure>\n\n\n\n

We propose an adaptive weighting regression (AWR) method to leverage the advantages of both detection-based<\/strong> and regression-based<\/strong> method. <\/p>\n\n\n\n

\"\"\n\t\t\t\n\t\t\t\t\n\t\t\t<\/svg>\n\t\t<\/button>
Framework of AWR.<\/figcaption><\/figure>\n\n\n\n

Guided by adaptive weight maps<\/strong>, AWR aggregates different regions of dense representation<\/strong> through discrete integration<\/strong> of all pixels in it. This operation is differentiable so that it can be embedded into the network for end-to-end training and applies direct supervision on joint coordinates<\/strong>, drawing consensus in network\u2019s supervision and output. <\/p>\n\n\n\n

Comparison with SOTA<\/h2>\n\n\n\n
\"\"\n\t\t\t\n\t\t\t\t\n\t\t\t<\/svg>\n\t\t<\/button>
Comparison with state-of-the-art methods on HANDS 2017 dataset. \u201dSEEN\u201d and \u201dUNSEEN\u201d denotes whether or not that the hand subject has been seen in the training set. \u201dAVG\u201d denotes all-joint mean error in millimeters over all test frames.<\/figcaption><\/figure>\n\n\n\n

On HANDS 2017 dataset, our Resnet18 based method already exceeds previous state-of-the-art methods by a large margin. And our Resnet50 based method further improves the average mean joint error by 0.36mm.<\/p>\n\n\n\n

\"\"\/\n\t\t\t\n\t\t\t\t\n\t\t\t<\/svg>\n\t\t<\/button>
Comparison with state-of-the-art methods on NYU, ICVL and MSRA dataset. The all-joint and per-joint mean error (top row) and the proportions of good frames over different thresholds (bottom row)). Left: NYU dataset, middle: ICVL dataset, right: MSRA dataset. Figure is best viewed in color.<\/figcaption><\/figure>\n\n\n\n

On NYU, ICVL and MSRA dataset, our method outperforms all existing methods on the three 3D hand pose estimation datasets using either the per-joint and all-joint mean error or the proportion of good frames.<\/p>\n\n\n\n

Conclusion<\/h2>\n\n\n\n

1\ufe0f\u20e3 Presenting an adaptive weighting regression (AWR)<\/strong> method to aggregate dense representation through discrete integration. <\/p>\n\n\n\n

2\ufe0f\u20e3 AWR unifies the dense representation and hand joint regression<\/strong> to enable direct supervision on joint coordinates<\/strong>, narrowing the gap between training and inferencing<\/strong>. <\/p>\n\n\n\n

3\ufe0f\u20e3 Comprehensive exploration experiments have been done to validate the improvement in network\u2019s accuracy and robustness<\/strong> brought by AWR as well as its generality<\/strong> to work under various experimental settings. <\/p>\n\n\n\n

4\ufe0f\u20e3 The overall network is simple yet effective<\/strong> and achieves state-of-the-art performance<\/strong> on four publicly available datasets.<\/p>\n\n\n\n

Bibtex<\/h2>\n\n\n\n
@inproceedings{awr,\n  title={AWR: Adaptive Weighting Regression for 3D Hand Pose Estimation},\n  author={Weiting Huang and Pengfei Ren and Jingyu Wang and Qi Qi and Haifeng Sun},\n  booktitle={AAAI Conference on Artificial Intelligence (AAAI)},\n  year={2020}\n}<\/code><\/pre>\n\n\n\n
<\/p>\n<\/div>","protected":false},"excerpt":{"rendered":"
1State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, 2EBUPT Information Technology Co., Ltd. Paper Code We introduce adaptive weighting regression (AWR) method. The weight distribution in weight maps can be adjusted adaptively to achieve more accurate and robust performance under the guidance of joint supervision. Top row: When the […]<\/p>\n","protected":false},"author":1,"featured_media":1735,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":"","_links_to":"","_links_to_target":""},"categories":[16],"tags":[],"class_list":["post-805","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-depth-based-3d-hand-pose-estimation"],"acf":{"writer":{"simple_value_formatted":"This data type is not supported! Please contact the author for help.<\/em><\/code>","value_formatted":[{"writer_link":{"simple_value_formatted":"Weiting Huang<\/a>","value_formatted":{"title":"Weiting Huang","url":"http:\/\/Weiting Huang","target":""},"value":{"title":"Weiting Huang","url":"http:\/\/Weiting Huang","target":""},"field":{"ID":2368,"key":"field_687f0c15f3394","label":"\u4f5c\u8005\u4e0e\u4f5c\u8005\u4e3b\u9875","name":"writer_link","aria-label":"","prefix":"acf","type":"link","value":null,"menu_order":0,"instructions":"","required":1,"id":"","class":"","conditional_logic":0,"parent":2366,"wrapper":{"width":"","class":"","id":""},"return_format":"array","allow_in_bindings":1,"_name":"writer_link","_valid":1,"parent_repeater":"field_687f08dfb7e07"}}},{"writer_link":{"simple_value_formatted":"Pengfei Ren*<\/a>","value_formatted":{"title":"Pengfei Ren*","url":"https:\/\/pengfeiren96.github.io\/","target":"_blank"},"value":{"title":"Pengfei Ren*","url":"https:\/\/pengfeiren96.github.io\/","target":"_blank"},"field":{"ID":2368,"key":"field_687f0c15f3394","label":"\u4f5c\u8005\u4e0e\u4f5c\u8005\u4e3b\u9875","name":"writer_link","aria-label":"","prefix":"acf","type":"link","value":null,"menu_order":0,"instructions":"","required":1,"id":"","class":"","conditional_logic":0,"parent":2366,"wrapper":{"width":"","class":"","id":""},"return_format":"array","allow_in_bindings":1,"_name":"writer_link","_valid":1,"parent_repeater":"field_687f08dfb7e07"}}},{"writer_link":{"simple_value_formatted":"Jingyu Wang<\/a>","value_formatted":{"title":"Jingyu Wang","url":"https:\/\/scholar.google.com\/citations?user=H441DjwAAAAJ","target":"_blank"},"value":{"title":"Jingyu Wang","url":"https:\/\/scholar.google.com\/citations?user=H441DjwAAAAJ","target":"_blank"},"field":{"ID":2368,"key":"field_687f0c15f3394","label":"\u4f5c\u8005\u4e0e\u4f5c\u8005\u4e3b\u9875","name":"writer_link","aria-label":"","prefix":"acf","type":"link","value":null,"menu_order":0,"instructions":"","required":1,"id":"","class":"","conditional_logic":0,"parent":2366,"wrapper":{"width":"","class":"","id":""},"return_format":"array","allow_in_bindings":1,"_name":"writer_link","_valid":1,"parent_repeater":"field_687f08dfb7e07"}}},{"writer_link":{"simple_value_formatted":"Qi Qi<\/a>","value_formatted":{"title":"Qi Qi","url":"https:\/\/scholar.google.com\/citations?user=2W2h0SwAAAAJ","target":"_blank"},"value":{"title":"Qi Qi","url":"https:\/\/scholar.google.com\/citations?user=2W2h0SwAAAAJ","target":"_blank"},"field":{"ID":2368,"key":"field_687f0c15f3394","label":"\u4f5c\u8005\u4e0e\u4f5c\u8005\u4e3b\u9875","name":"writer_link","aria-label":"","prefix":"acf","type":"link","value":null,"menu_order":0,"instructions":"","required":1,"id":"","class":"","conditional_logic":0,"parent":2366,"wrapper":{"width":"","class":"","id":""},"return_format":"array","allow_in_bindings":1,"_name":"writer_link","_valid":1,"parent_repeater":"field_687f08dfb7e07"}}},{"writer_link":{"simple_value_formatted":"Haifeng Sun<\/a>","value_formatted":{"title":"Haifeng Sun","url":"https:\/\/scholar.google.com\/citations?user=dwhbTsEAAAAJ","target":"_blank"},"value":{"title":"Haifeng Sun","url":"https:\/\/scholar.google.com\/citations?user=dwhbTsEAAAAJ","target":"_blank"},"field":{"ID":2368,"key":"field_687f0c15f3394","label":"\u4f5c\u8005\u4e0e\u4f5c\u8005\u4e3b\u9875","name":"writer_link","aria-label":"","prefix":"acf","type":"link","value":null,"menu_order":0,"instructions":"","required":1,"id":"","class":"","conditional_logic":0,"parent":2366,"wrapper":{"width":"","class":"","id":""},"return_format":"array","allow_in_bindings":1,"_name":"writer_link","_valid":1,"parent_repeater":"field_687f08dfb7e07"}}}],"value":[{"field_687f0c15f3394":{"title":"Weiting Huang","url":"http:\/\/Weiting Huang","target":""}},{"field_687f0c15f3394":{"title":"Pengfei Ren*","url":"https:\/\/pengfeiren96.github.io\/","target":"_blank"}},{"field_687f0c15f3394":{"title":"Jingyu Wang","url":"https:\/\/scholar.google.com\/citations?user=H441DjwAAAAJ","target":"_blank"}},{"field_687f0c15f3394":{"title":"Qi Qi","url":"https:\/\/scholar.google.com\/citations?user=2W2h0SwAAAAJ","target":"_blank"}},{"field_687f0c15f3394":{"title":"Haifeng Sun","url":"https:\/\/scholar.google.com\/citations?user=dwhbTsEAAAAJ","target":"_blank"}}],"field":{"ID":2366,"key":"field_687f08dfb7e07","label":"\u4f5c\u8005","name":"writer","aria-label":"","prefix":"acf","type":"repeater","value":null,"menu_order":0,"instructions":"","required":1,"id":"","class":"","conditional_logic":0,"parent":52,"wrapper":{"width":"","class":"","id":""},"acfe_repeater_stylised_button":0,"layout":"row","pagination":0,"min":0,"max":0,"collapsed":"","button_label":"Add Row","rows_per_page":20,"_name":"writer","_valid":1,"sub_fields":[{"ID":2368,"key":"field_687f0c15f3394","label":"\u4f5c\u8005\u4e0e\u4f5c\u8005\u4e3b\u9875","name":"writer_link","aria-label":"","prefix":"acf","type":"link","value":null,"menu_order":0,"instructions":"","required":1,"id":"","class":"","conditional_logic":0,"parent":2366,"wrapper":{"width":"","class":"","id":""},"return_format":"array","allow_in_bindings":1,"_name":"writer_link","_valid":1,"parent_repeater":"field_687f08dfb7e07"}]}},"\u4f1a\u8bae\u540d\u79f0":{"simple_value_formatted":"AAAI","value_formatted":"AAAI","value":"AAAI","field":{"ID":53,"key":"field_6759c5b33fdb3","label":"\u4f1a\u8bae\u540d\u79f0","name":"\u4f1a\u8bae\u540d\u79f0","aria-label":"","prefix":"acf","type":"text","value":null,"menu_order":1,"instructions":"","required":1,"id":"","class":"","conditional_logic":0,"parent":52,"wrapper":{"width":"","class":"","id":""},"default_value":"\u586b\u5199\u4f1a\u8bae","maxlength":"","allow_in_bindings":1,"placeholder":"","prepend":"","append":"","_name":"\u4f1a\u8bae\u540d\u79f0","_valid":1}},"\u5e74":{"simple_value_formatted":"2020","value_formatted":"2020","value":"2020","field":{"ID":254,"key":"field_675b036a7706e","label":"\u5e74","name":"\u5e74","aria-label":"","prefix":"acf","type":"text","value":null,"menu_order":2,"instructions":"","required":1,"id":"","class":"","conditional_logic":0,"parent":52,"wrapper":{"width":"","class":"","id":""},"default_value":2024,"maxlength":"","allow_in_bindings":1,"placeholder":"","prepend":"","append":"","_name":"\u5e74","_valid":1}},"code":{"simple_value_formatted":"Code<\/a>","value_formatted":{"title":"Code","url":"https:\/\/github.com\/Elody-07\/AWR-Adaptive-Weighting-Regression","target":"_blank"},"value":{"title":"Code","url":"https:\/\/github.com\/Elody-07\/AWR-Adaptive-Weighting-Regression","target":"_blank"},"field":{"ID":54,"key":"field_6759c5dc3fdb4","label":"code","name":"code","aria-label":"","prefix":"acf","type":"link","value":null,"menu_order":3,"instructions":"","required":0,"id":"","class":"","conditional_logic":0,"parent":52,"wrapper":{"width":"","class":"","id":""},"return_format":"array","allow_in_bindings":1,"_name":"code","_valid":1}},"arxiv":{"simple_value_formatted":"","value_formatted":"","value":"","field":{"ID":55,"key":"field_6759c5f83fdb5","label":"arXiv","name":"arxiv","aria-label":"","prefix":"acf","type":"link","value":null,"menu_order":4,"instructions":"","required":0,"id":"","class":"","conditional_logic":0,"parent":52,"wrapper":{"width":"","class":"","id":""},"return_format":"array","allow_in_bindings":0,"_name":"arxiv","_valid":1}},"pdf":{"simple_value_formatted":"PDF<\/a>","value_formatted":{"title":"PDF","url":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/6761","target":"_blank"},"value":{"title":"PDF","url":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/6761","target":"_blank"},"field":{"ID":56,"key":"field_6759c6b83fdb6","label":"pdf","name":"pdf","aria-label":"","prefix":"acf","type":"link","value":null,"menu_order":5,"instructions":"","required":0,"id":"","class":"","conditional_logic":0,"parent":52,"wrapper":{"width":"","class":"","id":""},"return_format":"array","allow_in_bindings":0,"_name":"pdf","_valid":1}},"rank":{"simple_value_formatted":"CCF-A","value_formatted":"CCF-A","value":"CCF-A","field":{"ID":2316,"key":"field_686b28a2069eb","label":"\u4f1a\u8bae\/\u671f\u520a\u7ea7\u522b","name":"rank","aria-label":"","prefix":"acf","type":"text","value":null,"menu_order":6,"instructions":"","required":0,"id":"","class":"","conditional_logic":0,"parent":52,"wrapper":{"width":"","class":"","id":""},"default_value":"CCF-A","maxlength":"","allow_in_bindings":0,"placeholder":"","prepend":"","append":"","_name":"rank","_valid":1}}},"_links":{"self":[{"href":"https:\/\/cv.nirc.top\/zh\/wp-json\/wp\/v2\/posts\/805","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cv.nirc.top\/zh\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cv.nirc.top\/zh\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/cv.nirc.top\/zh\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/cv.nirc.top\/zh\/wp-json\/wp\/v2\/comments?post=805"}],"version-history":[{"count":35,"href":"https:\/\/cv.nirc.top\/zh\/wp-json\/wp\/v2\/posts\/805\/revisions"}],"predecessor-version":[{"id":2536,"href":"https:\/\/cv.nirc.top\/zh\/wp-json\/wp\/v2\/posts\/805\/revisions\/2536"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cv.nirc.top\/zh\/wp-json\/wp\/v2\/media\/1735"}],"wp:attachment":[{"href":"https:\/\/cv.nirc.top\/zh\/wp-json\/wp\/v2\/media?parent=805"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cv.nirc.top\/zh\/wp-json\/wp\/v2\/categories?post=805"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cv.nirc.top\/zh\/wp-json\/wp\/v2\/tags?post=805"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}