Deep High-Resolution Representation Learning for Human Pose Estimation

@article{Sun2019DeepHR,
  title={Deep High-Resolution Representation Learning for Human Pose Estimation},
  author={Ke Sun and Bin Xiao and Dong Liu and Jingdong Wang},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={5686-5696}
}
  • Ke Sun, Bin Xiao, +1 author Jingdong Wang
  • Published 25 February 2019
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
In this paper, we are interested in the human pose estimation problem with a focus on learning reliable high-resolution representations. [...] Key Method 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.Expand
Bottom-up Higher-Resolution Networks for Multi-Person Pose Estimation
TLDR
Higher-Resolution Network (HigherHRNet) is proposed, which is a simple extension of the High-Res resolution Network (HRNet), which generates higher-resolution feature maps by deconvolving the high- resolution feature maps outputted by HRNet, which are spatially more accurate for small and medium persons. Expand
Deep High-Resolution Representation Learning for Visual Recognition
TLDR
The superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, is shown, suggesting that the HRNet is a stronger backbone for computer vision problems. Expand
Human Pose Estimation based on Attention Multi-resolution Network
TLDR
An attention-mechanism-based multi-resolution network is proposed, which adds an attention mechanism to the High-Resolution Network (HRNet) to enhance the feature representation of the network. Expand
A Novel Approach of Intelligent Computing for Multiperson Pose Estimation with Deep High Spatial Resolution and Multiscale Features
Currently, human pose estimation (HPE) methods mainly rely on the design framework of Convolutional Neural Networks (CNNs). These CNNs typically consist of high-to-low-resolution subnetworksExpand
Parallel Multi-Branch Model with Multi-Resolution Interaction for Human Pose Estiation
In recent years, human pose estimation has become a research hotspot in the field of computer vision, and has extensive application value in many fields, such as activity recognition [1], actionExpand
Enhancing feature fusion for human pose estimation
TLDR
A new feature fusion method for human pose estimation is proposed that introduces high level semantic information into low-level features to enhance feature fusion and uses Global Convolutional Network blocks to bridge the gap between low- level and high- level features. Expand
High-Resolution Representations for Labeling Pixels and Regions
TLDR
A simple modification is introduced to augment the high-resolution representation by aggregating the (upsampled) representations from all the parallel convolutions rather than only the representation from thehigh-resolution convolution, which leads to stronger representations, evidenced by superior results. Expand
Low-resolution Human Pose Estimation
  • Chen Wang, Feng Zhang, Xiatian Zhu, Shuzhi Sam Ge
  • Computer Science
  • ArXiv
  • 2021
TLDR
A novel Confidence-Aware Learning (CAL) method is proposed which selectively weighs the learning of heatmap and offset with respect to ground-truth and most confident prediction, whilst capturing the statistical importance of model output in mini-batch learning manner. Expand
Human Pose Estimation Based on the Multistage Learning and the Dense Connection
  • Wei-Min Shi, Qiaoning Yang, Juan Chen
  • Computer Science
  • 2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)
  • 2020
TLDR
This work proposes a novel Multistage Learning Network named MS-Net, which predicts joints at different stages of the network in a coarse-to-fine manner and achieves remarkable improvements over state-of-the-art baselines. Expand
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
TLDR
HigherHRNet is presented, a novel bottom-up human pose estimation method for learning scale-aware representations using high-resolution feature pyramids that surpasses all top-down methods on CrowdPose test and achieves new state-of-the-art result on COCO test-dev, suggesting its robustness in crowded scene. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 105 REFERENCES
Multi-Scale Structure-Aware Network for Human Pose Estimation
TLDR
A robust multi-scale structure-aware neural network for human pose estimation that effectively improves state-of-the-art pose estimation methods that suffer from difficulties in scale varieties, occlusions, and complex multi-person scenarios. Expand
Learning Feature Pyramids for Human Pose Estimation
TLDR
This work designs a Pyramid Residual Module (PRMs) to enhance the invariance in scales of DCNNs and provides theoretic derivation to extend the current weight initialization scheme to multi-branch network structures. Expand
Multi-source Deep Learning for Human Pose Estimation
TLDR
By extracting the non-linear representation from multiple information sources, the deep model outperforms state-of-the-art by up to 8.6 percent on three public benchmark datasets. Expand
Flowing ConvNets for Human Pose Estimation in Videos
TLDR
This work proposes a ConvNet architecture that is able to benefit from temporal context by combining information across the multiple frames using optical flow and outperforms a number of others, including one that uses optical flow solely at the input layers, one that regresses joint coordinates directly, and one that predicts heatmaps without spatial fusion. Expand
Human Pose Estimation via Convolutional Part Heatmap Regression
TLDR
A CNN cascaded architecture specifically designed for learning part relationships and spatial context, and robustly inferring pose even for the case of severe part occlusions is proposed, and achieves top performance on the MPII and LSP data sets. Expand
Towards Accurate Multi-person Pose Estimation in the Wild
TLDR
This work proposes a method for multi-person detection and 2-D pose estimation that achieves state-of-art results on the challenging COCO keypoints task by using a novel form of keypoint-based Non-Maximum-Suppression (NMS), instead of the cruder box-level NMS, and by introducing a novel aggregation procedure to obtain highly localized keypoint predictions. Expand
Cascaded Pyramid Network for Multi-person Pose Estimation
TLDR
A novel network structure called Cascaded Pyramid Network (CPN) is presented which targets to relieve the problem from these "hard" keypoints, with state-of-art results on the COCO keypoint benchmark, with average precision at 73.0. Expand
Human Pose Estimation Using Global and Local Normalization
TLDR
A two-stage normalization scheme, human body normalization and limb normalization, is presented to make the distribution of the relative joint locations compact, resulting in easier learning of convolutional spatial models and more accurate pose estimation. Expand
Human Pose Regression by Combining Indirect Part Detection and Contextual Information
TLDR
This paper uses the proposed Soft-argmax function to convert feature maps directly to joint coordinates, resulting in a fully differentiable framework that is able to learn heat maps representations indirectly, without additional steps of artificial ground truth generation. Expand
DeepPose: Human Pose Estimation via Deep Neural Networks
TLDR
The pose estimation is formulated as a DNN-based regression problem towards body joints and a cascade of such DNN regres- sors which results in high precision pose estimates. Expand
...
1
2
3
4
5
...