{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/region-ensemble-network-improving","title":"Region Ensemble Network: Improving Convolutional Network for Hand Pose Estimation","arxiv_id":"1702.02447","date":"2017-02-08","proceeding":null,"authors":["Hengkai Guo","Guijin Wang","Xinghao Chen","Cairong Zhang","Fei Qiao","Huazhong Yang"],"abstract":"Hand pose estimation from monocular depth images is an important and\nchallenging problem for human-computer interaction. Recently deep convolutional\nnetworks (ConvNet) with sophisticated design have been employed to address it,\nbut the improvement over traditional methods is not so apparent. To promote the\nperformance of directly 3D coordinate regression, we propose a tree-structured\nRegion Ensemble Network (REN), which partitions the convolution outputs into\nregions and integrates the results from multiple regressors on each regions.\nCompared with multi-model ensemble, our model is completely end-to-end\ntraining. The experimental results demonstrate that our approach achieves the\nbest performance among state-of-the-arts on two public datasets.","url_abs":"http://arxiv.org/abs/1702.02447v2","url_pdf":"http://arxiv.org/pdf/1702.02447v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"hand-pose-estimation","task_name":"Hand Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/hand-pose-estimation-on-icvl-hands","task":"Hand Pose Estimation","dataset":"ICVL Hands","model":"REN","rank_in_archive_order":14,"of":15,"metrics":{"Average 3D Error":" 7.5"},"uses_additional_data":false},{"leaderboard":"/sota/hand-pose-estimation-on-msra-hands","task":"Hand Pose Estimation","dataset":"MSRA Hands","model":"REN","rank_in_archive_order":11,"of":11,"metrics":{"Average 3D Error":" 9.8"},"uses_additional_data":false},{"leaderboard":"/sota/hand-pose-estimation-on-nyu-hands","task":"Hand Pose Estimation","dataset":"NYU Hands","model":"REN","rank_in_archive_order":16,"of":17,"metrics":{"Average 3D Error":"12.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.02447","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}