| OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation | ✓ Link | 99.5% | OmniPose | 2021-03-18 |
| Toward fast and accurate human pose estimation via soft-gated skip connections | ✓ Link | 94.8% | Soft-gated Skip Connections | 2020-02-25 |
| UniPose: Unified Human Pose Estimation in Single Images and Videos | ✓ Link | 94.5% | UniPose | 2020-01-22 |
| Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation | | 94.5% | Residual Hourglass + ASR + AHO | 2018-05-24 |
| Self Adversarial Training for Human Pose Estimation | ✓ Link | 94% | Chou et al. arXiv'17 | 2017-07-08 |
| Learning Feature Pyramids for Human Pose Estimation | ✓ Link | 93.9% | Pyramid Residual Modules (PRMs) | 2017-08-03 |
| Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation | ✓ Link | 93.9% | Stacked hourglass + Inception-resnet | 2017-05-05 |
| Multi-Context Attention for Human Pose Estimation | ✓ Link | 92.6% | Multi-Context Attention | 2017-02-24 |
| Fast Human Pose Estimation | ✓ Link | 90.8% | FPD | 2018-11-13 |
| Human pose estimation via Convolutional Part Heatmap Regression | ✓ Link | 90.7% | Part heatmap regression (ResNet-152) | 2016-09-06 |
| Convolutional Pose Machines | ✓ Link | 90.5% | Convolutional Pose Machines | 2016-01-30 |
| Human Pose Regression by Combining Indirect Part Detection and Contextual Information | ✓ Link | 90.5% | Soft-argmax + contextual information | 2017-10-06 |
| DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model | ✓ Link | 90.1% | ResNet-152 + intermediate supervision | 2016-05-10 |
| Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos | | 87.5% | DG-Net (T=4) | 2021-09-15 |
| Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimation | ✓ Link | 83.6 | Trajectory Space Factorization (F=25) | 2019-08-22 |
| VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera | ✓ Link | 79.4 | VNect (ResNet 50) | 2017-05-03 |
| Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision | | 75.7 | Mehta | 2016-11-29 |
| Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations | | 73.4% | Chen&Yuille, NIPS'14 | 2014-07-12 |