Year: 2017
Type: conference-paper
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 76:7 mAP on the MPII (multi person) dataset[3]. Our model and source codes are made publicly available.
Authors: Hao-Shu Fang, Shuqin Xie, Yu-Wing Tai, Cewu Lu
Institutions: Shanghai Jiao Tong University, Tencent (China)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Tencent
OpenAlex ID: W2963781481