{"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/globally-tuned-cascade-pose-regression-via","title":"Globally Tuned Cascade Pose Regression via Back Propagation with Application in 2D Face Pose Estimation and Heart Segmentation in 3D CT Images","arxiv_id":"1503.08843","date":"2015-03-30","proceeding":null,"authors":["Peng Sun","James K. Min","Guanglei Xiong"],"abstract":"Recently, a successful pose estimation algorithm, called Cascade Pose\nRegression (CPR), was proposed in the literature. Trained over Pose Index\nFeature, CPR is a regressor ensemble that is similar to Boosting. In this paper\nwe show how CPR can be represented as a Neural Network. Specifically, we adopt\na Graph Transformer Network (GTN) representation and accordingly train CPR with\nBack Propagation (BP) that permits globally tuning. In contrast, previous CPR\nliterature only took a layer wise training without any post fine tuning. We\nempirically show that global training with BP outperforms layer-wise\n(pre-)training. Our CPR-GTN adopts a Multi Layer Percetron as the regressor,\nwhich utilized sparse connection to learn local image feature representation.\nWe tested the proposed CPR-GTN on 2D face pose estimation problem as in\nprevious CPR literature. Besides, we also investigated the possibility of\nextending CPR-GTN to 3D pose estimation by doing experiments using 3D Computed\nTomography dataset for heart segmentation.","url_abs":"http://arxiv.org/abs/1503.08843v1","url_pdf":"http://arxiv.org/pdf/1503.08843v1.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":[{"paper_slug":"globally-tuned-cascade-pose-regression-via","repo_url":"https://github.com/pengsun/bpcpr5","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"3d-pose-estimation","task_name":"3D Pose Estimation"},{"task_slug":"heart-segmentation","task_name":"Heart Segmentation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}