{"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/spatial-attention-deep-net-with-partial-pso","title":"Spatial Attention Deep Net with Partial PSO for Hierarchical Hybrid Hand Pose Estimation","arxiv_id":"1604.03334","date":"2016-04-12","proceeding":null,"authors":["Qi Ye","Shanxin Yuan","Tae-Kyun Kim"],"abstract":"Discriminative methods often generate hand poses kinematically implausible,\nthen generative methods are used to correct (or verify) these results in a\nhybrid method. Estimating 3D hand pose in a hierarchy, where the\nhigh-dimensional output space is decomposed into smaller ones, has been shown\neffective. Existing hierarchical methods mainly focus on the decomposition of\nthe output space while the input space remains almost the same along the\nhierarchy. In this paper, a hybrid hand pose estimation method is proposed by\napplying the kinematic hierarchy strategy to the input space (as well as the\noutput space) of the discriminative method by a spatial attention mechanism and\nto the optimization of the generative method by hierarchical Particle Swarm\nOptimization (PSO). The spatial attention mechanism integrates cascaded and\nhierarchical regression into a CNN framework by transforming both the input(and\nfeature space) and the output space, which greatly reduces the viewpoint and\narticulation variations. Between the levels in the hierarchy, the hierarchical\nPSO forces the kinematic constraints to the results of the CNNs. The\nexperimental results show that our method significantly outperforms four\nstate-of-the-art methods and three baselines on three public benchmarks.","url_abs":"http://arxiv.org/abs/1604.03334v2","url_pdf":"http://arxiv.org/pdf/1604.03334v2.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":"spatial-attention-deep-net-with-partial-pso","repo_url":"https://github.com/DaphneAntotsiou/task-oriented-hand-retargeting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"hand-pose-estimation","task_name":"Hand Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1604.03334","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}