{"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/simple-pose-rethinking-and-improving-a-bottom","title":"Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation","arxiv_id":"1911.10529","date":"2019-11-24","proceeding":null,"authors":["Jia Li","Wen Su","Zengfu Wang"],"abstract":"We rethink a well-know bottom-up approach for multi-person pose estimation and propose an improved one. The improved approach surpasses the baseline significantly thanks to (1) an intuitional yet more sensible representation, which we refer to as body parts to encode the connection information between keypoints, (2) an improved stacked hourglass network with attention mechanisms, (3) a novel focal L2 loss which is dedicated to hard keypoint and keypoint association (body part) mining, and (4) a robust greedy keypoint assignment algorithm for grouping the detected keypoints into individual poses. Our approach not only works straightforwardly but also outperforms the baseline by about 15% in average precision and is comparable to the state of the art on the MS-COCO test-dev dataset. The code and pre-trained models are publicly available online.","url_abs":"https://arxiv.org/abs/1911.10529v1","url_pdf":"https://arxiv.org/pdf/1911.10529v1.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":"simple-pose-rethinking-and-improving-a-bottom","repo_url":"https://github.com/hellojialee/Improved-Body-Parts","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"simple-pose-rethinking-and-improving-a-bottom","repo_url":"https://github.com/diamondto/IBP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"simple-pose-rethinking-and-improving-a-bottom","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"simple-pose-rethinking-and-improving-a-bottom","repo_url":"https://github.com/2023-MindSpore-4/Code11/tree/main/simple_pose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"simple-pose-rethinking-and-improving-a-bottom","repo_url":"https://github.com/Mind23-2/MindCode-88/tree/main/simple_pose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"simple-pose-rethinking-and-improving-a-bottom","repo_url":"https://github.com/code-implementation1/Code8/tree/main/simple_pose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"simple-pose-rethinking-and-improving-a-bottom","repo_url":"https://github.com/hellojialee/Multi-Person-Pose-using-Body-Parts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"simple-pose-rethinking-and-improving-a-bottom","repo_url":"https://github.com/hellojialee/OffsetGuided","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"2d-human-pose-estimation","task_name":"2D Human Pose Estimation"},{"task_slug":"keypoint-detection","task_name":"Keypoint Detection"},{"task_slug":"multi-person-pose-estimation","task_name":"Multi-Person Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"hourglass-module","method_name":"Hourglass Module"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"stacked-hourglass-network","method_name":"Stacked Hourglass Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/keypoint-detection-on-coco-test-dev","task":"Keypoint Detection","dataset":"COCO test-dev","model":"Simple Pose","rank_in_archive_order":9,"of":16,"metrics":{"AP":"68.1","APL":"70.5","APM":"66.8","AR":"72.1","AR50":"88.2"},"uses_additional_data":false},{"leaderboard":"/sota/multi-person-pose-estimation-on-coco-test-dev","task":"Multi-Person Pose Estimation","dataset":"COCO test-dev","model":"Identity Mapping Hourglass","rank_in_archive_order":9,"of":15,"metrics":{"AP":"68.1","APL":"70.5","APM":"66.8","AR":"72.1","AR50":"88.2"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-coco-test-dev","task":"Pose Estimation","dataset":"COCO test-dev","model":"Simple Pose","rank_in_archive_order":36,"of":47,"metrics":{"AP":"68.1","APL":"70.5","APM":"66.8","AR":"88.2"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.10529","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}