Pose Estimation On Mpii Human Pose

评估指标

PCKh-0.5

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
PCT (swin-l, test set)	94.3	Human Pose as Compositional Tokens
Soft-gated Skip Connections	94.1	Toward fast and accurate human pose estimation via soft-gated skip connections
Cascade Feature Aggregation	93.9	Cascade Feature Aggregation for Human Pose Estimation	-
PCT (swin-b, test set)	93.8	Human Pose as Compositional Tokens
TransPose	93.5	TransPose: Keypoint Localization via Transformer
UniHCP (FT)	93.2	UniHCP: A Unified Model for Human-Centric Perceptions
4xRSN-50	93.0	Learning Delicate Local Representations for Multi-Person Pose Estimation
UniPose	92.7	UniPose: Unified Human Pose Estimation in Single Images and Videos
MSPN	92.6	Rethinking on Multi-Stage Networks for Human Pose Estimation
Spatial Context	92.5	Human Pose Estimation with Spatial Contextual Information	-
HRNet-W32	92.3	Deep High-Resolution Representation Learning for Human Pose Estimation
DLCM	92.3	Deeply Learned Compositional Models for Human Pose Estimation	-
Multi-Scale Structure-Aware Network	92.1	Multi-Scale Structure-Aware Network for Human Pose Estimation	-
Pyramid Residual Modules (PRMs)	92.0	Learning Feature Pyramids for Human Pose Estimation
Chen et al. ICCV'17	91.9	Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
Chou et al. arXiv'17	91.8	Self Adversarial Training for Human Pose Estimation
Multi-Context Attention	91.5	Multi-Context Attention for Human Pose Estimation
Residual Hourglass +ASR+AHO	91.5	Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation	-
DU-Net	91.2	Quantized Densely Connected U-Nets for Efficient Landmark Localization
Stacked hourglass + Inception-resnet	91.2	Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation

0 of 46 row(s) selected.