Bottom-up human pose estimation via disentangled keypoint regression

Z Geng, K Sun, B ** for multi-person pose estimation
S **, W Liu, E **e, W Wang, C Qian, W Ouyang… - Computer Vision–ECCV …, 2020 - Springer
Multi-person pose estimation is challenging because it localizes body keypoints for multiple
persons simultaneously. Previous methods can be divided into two streams, ie top-down …

Zoomnas: searching for whole-body human pose estimation in the wild

L Xu, S **, W Liu, C Qian, W Ouyang… - … on Pattern Analysis …, 2022 - ieeexplore.ieee.org
This paper investigates the task of 2D whole-body human pose estimation, which aims to
localize dense landmarks on the entire human body including body, feet, face, and hands …

Graph-pcnn: Two stage human pose estimation with graph pose refinement

J Wang, X Long, Y Gao, E Ding, S Wen - … 28, 2020, Proceedings, Part XI 16, 2020 - Springer
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 …

When human pose estimation meets robustness: Adversarial algorithms and benchmarks

J Wang, S **, W Liu, W Liu… - Proceedings of the …, 2021 - openaccess.thecvf.com
Human pose estimation is a fundamental yet challenging task in computer vision, which
aims at localizing human anatomical keypoints. However, unlike human vision that is robust …