Details for entry HRNet

Short Name:
HRNet
Long Name:
Deep High-Resolution Representation Learning for Human Pose Estimation
Use MPII Pose for training:
no
Use COCO for training:
yes
Use external training:
no
Use multiple frames for pose estimation:
yes
Predict pose tracks:
yes
URL:
https://github.com/leoxiaobin/deep-high-resolution-net.pytorch
Description:
In this paper, we are interested in the human pose estimation problem with a focus on learning reliable high-resolution representations. Most existing methods recover high-resolution representations from low-resolution representations produced by a high-to-low resolution network. Instead, our proposed network maintains high-resolution representations through the whole process. We start from a high-resolution subnetwork as the first stage, gradually add high-to-low resolution subnetworks one by one to form more stages, and connect the mutli-resolution subnetworks in parallel. We conduct repeated multi-scale fusions such that each of the high-to-low resolution representations receives information from other parallel representations over and over, leading to rich high-resolution representations. As a result, the predicted keypoint heatmap is potentially more accurate and spatially more precise. We empirically demonstrate the effectiveness of our network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset. In addition, we show the superiority of our network in pose tracking on the PoseTrack dataset. The code and models are publicly available at https://github.com/leoxiaobin/deep-high-resolution-net.pytorch.
Bibtex:
@inproceedings{SunXLWang2019, title={Deep High-Resolution Representation Learning for Human Pose Estimation}, author={Ke Sun, Bin Xiao, Dong Liu, and Jingdong Wang}, booktitle={CVPR}, year={2019} } @inproceedings{xiao2018simple, author={Xiao, Bin and Wu, Haiping and Wei, Yichen}, title={Simple Baselines for Human Pose Estimation and Tracking}, booktitle = {European Conference on Computer Vision (ECCV)}, year = {2018} }
Specs:
P100
Runtime:
3600
Open Source:
no
Number of submissions:
yes
Last Submission:
2018-11-07 06:26:24
Published:
2018-11-12 10:13:02

Imprint | Data Protection


© PoseTrack