Deep learning-based human pose estimation: A survey

C Zheng, W Wu, C Chen, T Yang, S Zhu, J Shen… - ACM Computing …, 2023‏ - dl.acm.org
Human pose estimation aims to locate the human body parts and build human body
representation (eg, body skeleton) from input data such as images and videos. It has drawn …

Recent advances of monocular 2d and 3d human pose estimation: A deep learning perspective

W Liu, Q Bao, Y Sun, T Mei - ACM Computing Surveys, 2022‏ - dl.acm.org
Estimation of the human pose from a monocular camera has been an emerging research
topic in the computer vision community with many applications. Recently, benefiting from the …

Alphapose: Whole-body regional multi-person pose estimation and tracking in real-time

HS Fang, J Li, H Tang, C Xu, H Zhu… - … on Pattern Analysis …, 2022‏ - ieeexplore.ieee.org
Accurate whole-body multi-person pose estimation and tracking is an important yet
challenging topic in computer vision. To capture the subtle actions of humans for complex …

Vitpose: Simple vision transformer baselines for human pose estimation

Y Xu, J Zhang, Q Zhang, D Tao - Advances in Neural …, 2022‏ - proceedings.neurips.cc
Although no specific domain knowledge is considered in the design, plain vision
transformers have shown excellent performance in visual recognition tasks. However, little …

Instructdiffusion: A generalist modeling interface for vision tasks

Z Geng, B Yang, T Hang, C Li, S Gu… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
We present InstructDiffusion a unified and generic framework for aligning computer vision
tasks with human instructions. Unlike existing approaches that integrate prior knowledge …

Revealing the dark secrets of masked image modeling

Z **e, Z Geng, J Hu, Z Zhang… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Masked image modeling (MIM) as pre-training is shown to be effective for numerous vision
downstream tasks, but how and where MIM works remain unclear. In this paper, we compare …

Multi-animal pose estimation, identification and tracking with DeepLabCut

J Lauer, M Zhou, S Ye, W Menegas, S Schneider… - Nature …, 2022‏ - nature.com
Estimating the pose of multiple animals is a challenging computer vision problem: frequent
interactions cause occlusions and complicate the association of detected keypoints to the …

Bottom-up human pose estimation via disentangled keypoint regression

Z Geng, K Sun, B **ao, Z Zhang… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
In this paper, we are interested in the bottom-up paradigm of estimating human poses from
an image. We study the dense keypoint regression framework that is previously inferior to …

Human pose regression with residual log-likelihood estimation

J Li, S Bian, A Zeng, C Wang… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
Heatmap-based methods dominate in the field of human pose estimation by modelling the
output distribution through likelihood heatmaps. In contrast, regression-based methods are …

End-to-end multi-person pose estimation with transformers

D Shi, X Wei, L Li, Y Ren, W Tan - Proceedings of the IEEE …, 2022‏ - openaccess.thecvf.com
Current methods of multi-person pose estimation typically treat the localization and
association of body joints separately. In this paper, we propose the first fully end-to-end multi …