2020/07/21 by Jian Wang, Wang, Jian, Xiang Long +7 · 12 citations
Computer Science · Mathematics · #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #FOS: Computer and information sciences #Graph #Hand Gesture Recognition Systems #Human Pose and Action Recognition #Machine learning #Margin (machine learning) #Mathematics #Pattern recognition (psychology) #Pose #Regression #Statistics #Subnet #Theoretical computer science #Video Surveillance and Tracking Methods #cs.CV
paper · pdf · doi:10.48550/arxiv.2007.10599
published in arXiv (Cornell University) (Cornell University) · Accepted to ECCV2020
arxiv created 2020/07/21 · openalex publication_date 2020/07/21 · arxiv updated 2020/07/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recently, most of the state-of-the-art human pose estimation methods are based on heatmap regression. The final coordinates of keypoints are obtained by decoding heatmap directly. In this paper, we aim to find a better approach to get more accurate localization results. We mainly put forward two suggestions for improvement: 1) different features and methods should be applied for rough and accurate localization, 2) relationship between keypoints should be considered. Specifically, we propose a two-stage graph-based and model-agnostic framework, called Graph-PCNN, with a localization subnet and a graph pose refinement module added onto the original heatmap regression network. In the first stage, heatmap regression network is applied to obtain a rough localization result, and a set of proposal keypoints, called guided points, are sampled. In the second stage, for each guided point, different visual feature is extracted by the localization subnet. The relationship between guided points is explored by the graph pose refinement module to get more accurate localization results. Experiments show that Graph-PCNN can be used in various backbones to boost the performance by a large margin. Without bells and whistles, our best model can achieve a new state-of-the-art 76.8% AP on COCO test-dev split.