{"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/human-pose-estimation-with-iterative-error","title":"Human Pose Estimation with Iterative Error Feedback","arxiv_id":"1507.06550","date":"2015-07-23","proceeding":"CVPR 2016 6","authors":["Joao Carreira","Pulkit Agrawal","Katerina Fragkiadaki","Jitendra Malik"],"abstract":"Hierarchical feature extractors such as Convolutional Networks (ConvNets)\nhave achieved impressive performance on a variety of classification tasks using\npurely feedforward processing. Feedforward architectures can learn rich\nrepresentations of the input space but do not explicitly model dependencies in\nthe output spaces, that are quite structured for tasks such as articulated\nhuman pose estimation or object segmentation. Here we propose a framework that\nexpands the expressive power of hierarchical feature extractors to encompass\nboth input and output spaces, by introducing top-down feedback. Instead of\ndirectly predicting the outputs in one go, we use a self-correcting model that\nprogressively changes an initial solution by feeding back error predictions, in\na process we call Iterative Error Feedback (IEF). IEF shows excellent\nperformance on the task of articulated pose estimation in the challenging MPII\nand LSP benchmarks, matching the state-of-the-art without requiring ground\ntruth scale annotation.","url_abs":"http://arxiv.org/abs/1507.06550v3","url_pdf":"http://arxiv.org/pdf/1507.06550v3.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":"human-pose-estimation-with-iterative-error","repo_url":"https://github.com/pulkitag/ief","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/pose-estimation-on-mpii-human-pose","task":"Pose Estimation","dataset":"MPII Human Pose","model":"IEF","rank_in_archive_order":44,"of":46,"metrics":{"PCKh-0.5":"81.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1507.06550","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}