Pose Estimation On Leeds Sports Poses

Métriques

PCK

Résultats

Résultats de performance de divers modèles sur ce benchmark

		Paper Title
OmniPose	99.5%	OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation
Soft-gated Skip Connections	94.8%	Toward fast and accurate human pose estimation via soft-gated skip connections
Residual Hourglass + ASR + AHO	94.5%	Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation
UniPose	94.5%	UniPose: Unified Human Pose Estimation in Single Images and Videos
Chou et al. arXiv'17	94%	Self Adversarial Training for Human Pose Estimation
Pyramid Residual Modules (PRMs)	93.9%	Learning Feature Pyramids for Human Pose Estimation
Stacked hourglass + Inception-resnet	93.9%	Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation
Multi-Context Attention	92.6%	Multi-Context Attention for Human Pose Estimation
FPD	90.8%	Fast Human Pose Estimation
Part heatmap regression (ResNet-152)	90.7%	Human pose estimation via Convolutional Part Heatmap Regression
Convolutional Pose Machines	90.5%	Convolutional Pose Machines
Soft-argmax + contextual information	90.5%	Human Pose Regression by Combining Indirect Part Detection and Contextual Information
ResNet-152 + intermediate supervision	90.1%	DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model
DG-Net (T=4)	87.5%	Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos
Trajectory Space Factorization (F=25)	83.6	Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimation
VNect (ResNet 50)	79.4	VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
Mehta	75.7	Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision
Chen&Yuille, NIPS'14	73.4%	Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations

0 of 18 row(s) selected.

Pose Estimation On Leeds Sports Poses | SOTA | HyperAI