Deep High-Resolution Representation Learning for Human ...
Deep High-Resolution Representation Learning for Human Pose estimation Ke Sun1,2 Bin Xiao2 Dong Liu1 Jingdong Wang2. 1. University of Science and Technology of China 2 Microsoft Research Asia [ ] 25 Feb 2019. Abstract depth In this paper, we are interested in the Human pose es- 1 . timation problem with a focus on Learning reliable high - scale resolution representations. Most existing methods recover 2 . High-Resolution representations from low- resolution repre- sentations produced by a high -to-low resolution network. 4 . Instead, our proposed network maintains High-Resolution feature conv. down up representations through the whole process. maps unit samp. samp. We start from a High-Resolution subnetwork as the first stage, gradually add high -to-low resolution subnetworks Figure 1. Illustrating the architecture of the proposed HRNet.
This paper is interested in single-person pose estimation, which is the basis of other related problems, such as multi-person pose estimation [6,27,33,39,47,57,41,46,17,71], video pose estimation and tracking [49,72], etc. Equal contribution. yThis work is done when Ke Sun was an intern at Microsoft Research, Beijing, P.R. China feature maps ...
Download Deep High-Resolution Representation Learning for Human ...
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document:
Related search queries
Estimation and Comparison, Comparison of Estimation Methods for, Comparison of Estimation Methods for Vector Autoregressive, 3-D rigid body transformations: a comparison, Test Effort Estimation, Direction of Arrival Estimation, Direction of arrival, Estimation, Power, Review of the Basic Methodology, Stacked Hourglass Networks for Human Pose Estimation, Chapter 8 Weight Estimation