Learning Feature Pyramids for Human Pose Estimation
@article{Yang2017LearningFP, title={Learning Feature Pyramids for Human Pose Estimation}, author={Wei Yang and Shuang Li and Wanli Ouyang and Hongsheng Li and Xiaogang Wang}, journal={2017 IEEE International Conference on Computer Vision (ICCV)}, year={2017}, pages={1290-1299} }
Articulated human pose estimation is a fundamental yet challenging task in computer vision. [...] Key ResultOur approach obtains state-of-the-art results on both benchmarks. Code is available at https://github.com/bearpaw/PyraNet. Expand Abstract
Figures, Tables, and Topics from this paper.
Citations
Publications citing this paper.
SHOWING 1-10 OF 119 CITATIONS
Human Pose Estimation with Spatial Contextual Information
VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED
Graph Clustering Graph Clustering Graph Clustering Graph Deconvolution Graph Deconvolution Graph Deconvolution Skip Connection Skip Connection Skip Connection Convolution Features F Enhanced Convolution Features F r E Learnable Adjacency Matrix Node Representation Graph Clustering Graph Deconvolutio
VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED
Human Pose Estimation With Deeply Learned Multi-Scale Compositional Models
VIEW 19 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED
Improving Human Pose Estimation With Self-Attention Generative Adversarial Networks
VIEW 11 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED
Layout-Graph Reasoning for Fashion Landmark Detection
VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED
Multi-scale Adaptive Structure Network for Human Pose Estimation from Color Images
VIEW 4 EXCERPTS
CITES BACKGROUND & RESULTS
HIGHLY INFLUENCED
Anti-Confusing: Region-Aware Network for Human Pose Estimation
VIEW 8 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED
DNANet: De-Normalized Attention Based Multi-Resolution Network for Human Pose Estimation
VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED
Deep High-Resolution Representation Learning for Human Pose Estimation
VIEW 6 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED
Does Learning Specific Features for Related Parts Help Human Pose Estimation?
VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED
FILTER CITATIONS BY YEAR
CITATION STATISTICS
19 Highly Influenced Citations
Averaged 39 Citations per year from 2017 through 2019
References
Publications referenced by this paper.
SHOWING 1-10 OF 57 REFERENCES
Aggregated Residual Transformations for Deep Neural Networks
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL
Stacked Hourglass Networks for Human Pose Estimation
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL
Clustered Pose and Nonlinear Appearance Models for Human Pose Estimation
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL
Convolutional Pose Machines
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL
Identity Mappings in Deep Residual Networks
VIEW 12 EXCERPTS
HIGHLY INFLUENTIAL
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL
Wide Residual Networks
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL