RMPE: Regional Multi-person Pose Estimation

December 01, 2016 · Entered Twilight · 🏛 IEEE International Conference on Computer Vision

"Last commit was 7.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .Doxyfile, .gitignore, .travis.yml, CMakeLists.txt, CONTRIBUTING.md, CONTRIBUTORS.md, INSTALL.md, LICENSE, Makefile, Makefile.config.example, README.md, caffe.cloc, cmake, data, docker, docs, examples, include, matlab, models, python, readme, scripts, src, tools

Authors Hao-Shu Fang, Shuqin Xie, Yu-Wing Tai, Cewu Lu arXiv ID 1612.00137 Category cs.CV: Computer Vision Citations 1.7K Venue IEEE International Conference on Computer Vision Repository https://github.com/Fang-Haoshu/RMPE ⭐ 97 Last Checked 1 month ago

Abstract

Multi-person pose estimation in the wild is challenging. Although state-of-the-art human detectors have demonstrated good performance, small errors in localization and recognition are inevitable. These errors can cause failures for a single-person pose estimator (SPPE), especially for methods that solely depend on human detection results. In this paper, we propose a novel regional multi-person pose estimation (RMPE) framework to facilitate pose estimation in the presence of inaccurate human bounding boxes. Our framework consists of three components: Symmetric Spatial Transformer Network (SSTN), Parametric Pose Non-Maximum-Suppression (NMS), and Pose-Guided Proposals Generator (PGPG). Our method is able to handle inaccurate bounding boxes and redundant detections, allowing it to achieve a 17% increase in mAP over the state-of-the-art methods on the MPII (multi person) dataset.Our model and source codes are publicly available.