{"id":19633817,"url":"https://github.com/shivamsouravjha/pose-estimators","last_synced_at":"2025-04-28T07:31:00.486Z","repository":{"id":118530091,"uuid":"297053202","full_name":"shivamsouravjha/Pose-estimators","owner":"shivamsouravjha","description":"In progress deployment of pose estimation.","archived":false,"fork":false,"pushed_at":"2020-10-15T16:39:43.000Z","size":426,"stargazers_count":37,"open_issues_count":2,"forks_count":6,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-05T07:33:10.428Z","etag":null,"topics":["art","convolutional-networks","fcns","hacktoberfest","hourglass","paper"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/shivamsouravjha.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-09-20T10:37:16.000Z","updated_at":"2024-02-08T17:35:47.000Z","dependencies_parsed_at":"2023-07-03T23:01:44.316Z","dependency_job_id":null,"html_url":"https://github.com/shivamsouravjha/Pose-estimators","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shivamsouravjha%2FPose-estimators","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shivamsouravjha%2FPose-estimators/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shivamsouravjha%2FPose-estimators/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shivamsouravjha%2FPose-estimators/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/shivamsouravjha","download_url":"https://codeload.github.com/shivamsouravjha/Pose-estimators/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251271101,"owners_count":21562490,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["art","convolutional-networks","fcns","hacktoberfest","hourglass","paper"],"created_at":"2024-11-11T12:18:42.103Z","updated_at":"2025-04-28T07:31:00.479Z","avatar_url":"https://github.com/shivamsouravjha.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Toward fast and accurate human pose estimation via soft-gated skip connections\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/toward-fast-and-accurate-human-pose/pose-estimation-on-leeds-sports-poses)](https://paperswithcode.com/sota/pose-estimation-on-leeds-sports-poses?p=toward-fast-and-accurate-human-pose)\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/toward-fast-and-accurate-human-pose/pose-estimation-on-mpii-human-pose)](https://paperswithcode.com/sota/pose-estimation-on-mpii-human-pose?p=toward-fast-and-accurate-human-pose)\n# INTRODUCTION\nBeing one of the most challenging computer vision problems with a multitude of applications, human pose estimation\nhas been one of the primary research areas that the computer\nvision community tried to solve with Deep Learning and\nConvolutional Neural Networks (CNNs). Given that the\nresults produced by existing state-of-the-art methods look\nat least impressive both qualitatively and quantitatively, it is\nnatural to question how much progress can be expected on\nthis problem over the next years and whether there is room\nfor further improvement.\n\n# Abstract of Research Paper\nThis paper is on highly accurate and highly\nefficient human pose estimation. Recent works based on Fully\nConvolutional Networks (FCNs) have demonstrated excellent\nresults for this difficult problem. While residual connections\nwithin FCNs have proved to be quintessential for achieving\nhigh accuracy, we re-analyze this design choice in the context of\nimproving both the accuracy and the efficiency over the state-ofthe-art. In particular, we make the following contributions: (a)\nWe propose gated skip connections with per-channel learnable\nparameters to control the data flow for each channel within the\nmodule within the macro-module. (b) We introduce a hybrid\nnetwork that combines the HourGlass and U-Net architectures\nwhich minimizes the number of identity connections within the\nnetwork and increases the performance for the same parameter\nbudget. Our model achieves state-of-the-art results on the MPII\nand LSP datasets. In addition, with a reduction of 3× in model\nsize and complexity, we show no decrease in performance when\ncompared to the original HourGlass network.\n# Skip -Gates \n![img](https://img2020.cnblogs.com/blog/1033571/202009/1033571-20200907190733717-1742101000.png)\n\n# Feature Integration\n![imh](https://img2020.cnblogs.com/blog/1033571/202009/1033571-20200907192227591-124027453.png)\n\n# References\nhttps://arxiv.org/pdf/2002.11098v1.pdf\n\n# Research Paper \n@1adrianb is the original author of the paper \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshivamsouravjha%2Fpose-estimators","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fshivamsouravjha%2Fpose-estimators","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshivamsouravjha%2Fpose-estimators/lists"}