{"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/post-data-augmentation-to-improve-deep-pose","title":"Post-Data Augmentation to Improve Deep Pose Estimation of Extreme and Wild Motions","arxiv_id":"1902.04250","date":"2019-02-12","proceeding":null,"authors":["Kohei Toyoda","Michinari Kono","Jun Rekimoto"],"abstract":"Contributions of recent deep-neural-network (DNN) based techniques have been\nplaying a significant role in human-computer interaction (HCI) and user\ninterface (UI) domains. One of the commonly used DNNs is human pose estimation.\nThis kind of technique is widely used for motion capturing of humans, and to\ngenerate or modify virtual avatars. However, in order to gain accuracy and to\nuse such systems, large and precise datasets are required for the machine\nlearning (ML) procedure. This can be especially difficult for extreme/wild\nmotions such as acrobatic movements or motions in specific sports, which are\ndifficult to estimate in typically provided training models. In addition,\ntraining may take a long duration, and will require a high-grade GPU for\nsufficient speed. To address these issues, we propose a method to improve the\npose estimation accuracy for extreme/wild motions by using pre-trained models,\ni.e., without performing the training procedure by yourselves. We assume our\nmethod to encourage usage of these DNN techniques for users in application\nareas that are out of the ML field, and to help users without high-end\ncomputers to apply them for personal and end use cases.","url_abs":"http://arxiv.org/abs/1902.04250v1","url_pdf":"http://arxiv.org/pdf/1902.04250v1.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":"post-data-augmentation-to-improve-deep-pose","repo_url":"https://github.com/ktoyod/rotatedpose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":null,"task_name":"GPU"},{"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}