| Human Pose as Compositional Tokens | ✓ Link | 94.3 | PCT (swin-l, test set) | 2023-03-21 |
| Toward fast and accurate human pose estimation via soft-gated skip connections | ✓ Link | 94.1 | Soft-gated Skip Connections | 2020-02-25 |
| Cascade Feature Aggregation for Human Pose Estimation | | 93.9 | Cascade Feature Aggregation | 2019-02-21 |
| Human Pose as Compositional Tokens | ✓ Link | 93.8 | PCT (swin-b, test set) | 2023-03-21 |
| TransPose: Keypoint Localization via Transformer | ✓ Link | 93.5 | TransPose | 2020-12-28 |
| UniHCP: A Unified Model for Human-Centric Perceptions | ✓ Link | 93.2 | UniHCP (FT) | 2023-03-06 |
| Learning Delicate Local Representations for Multi-Person Pose Estimation | ✓ Link | 93.0 | 4xRSN-50 | 2020-03-09 |
| UniPose: Unified Human Pose Estimation in Single Images and Videos | ✓ Link | 92.7 | UniPose | 2020-01-22 |
| Rethinking on Multi-Stage Networks for Human Pose Estimation | ✓ Link | 92.6 | MSPN | 2019-01-01 |
| Human Pose Estimation with Spatial Contextual Information | | 92.5 | Spatial Context | 2019-01-07 |
| Deep High-Resolution Representation Learning for Human Pose Estimation | ✓ Link | 92.3 | HRNet-W32 | 2019-02-25 |
| Deeply Learned Compositional Models for Human Pose Estimation | | 92.3 | DLCM | 2018-09-01 |
| Multi-Scale Structure-Aware Network for Human Pose Estimation | | 92.1 | Multi-Scale Structure-Aware Network | 2018-03-27 |
| Learning Feature Pyramids for Human Pose Estimation | ✓ Link | 92.0 | Pyramid Residual Modules (PRMs) | 2017-08-03 |
| Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation | ✓ Link | 91.9 | Chen et al. ICCV'17 | 2017-04-30 |
| Self Adversarial Training for Human Pose Estimation | ✓ Link | 91.8 | Chou et al. arXiv'17 | 2017-07-08 |
| Multi-Context Attention for Human Pose Estimation | ✓ Link | 91.5 | Multi-Context Attention | 2017-02-24 |
| Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation | | 91.5 | Residual Hourglass +ASR+AHO | 2018-05-24 |
| Quantized Densely Connected U-Nets for Efficient Landmark Localization | ✓ Link | 91.2 | DU-Net | 2018-08-07 |
| Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation | ✓ Link | 91.2 | Stacked hourglass + Inception-resnet | 2017-05-05 |
| EfficientPose: Scalable single-person pose estimation | ✓ Link | 91.2 | EfficientPose IV | 2020-04-25 |
| Fast Human Pose Estimation | ✓ Link | 91.1 | FPD | 2018-11-13 |
| Integral Human Pose Regression | ✓ Link | 91.0 | Integral Regression | 2017-11-22 |
| Stacked Hourglass Networks for Human Pose Estimation | ✓ Link | 90.9 | Stacked Hourglass Networks | 2016-03-22 |
| Distribution-Aware Coordinate Representation for Human Pose Estimation | ✓ Link | 90.6 | DarkPose | 2019-10-14 |
| TFPose: Direct Human Pose Estimation with Transformers | | 90.4 | TFPose(ResNet-50) | 2021-03-29 |
| Human pose estimation via Convolutional Part Heatmap Regression | ✓ Link | 89.7 | Human Pose Estimation | 2016-09-06 |
| Human pose estimation via Convolutional Part Heatmap Regression | ✓ Link | 89.7 | Part heatmap regression (ResNet-152) | 2016-09-06 |
| Numerical Coordinate Regression with Convolutional Neural Networks | ✓ Link | 89.5 | DSNTr ResNet-50@28px | 2018-01-23 |
| CU-Net: Coupled U-Nets | ✓ Link | 89.4 | CU-Net | 2018-08-20 |
| EfficientPose: Scalable single-person pose estimation | ✓ Link | 88.8 | OpenPose | 2020-04-25 |
| Convolutional Pose Machines | ✓ Link | 88.52 | Convolutional Pose Machines | 2016-01-30 |
| DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model | ✓ Link | 88.52 | ResNet-152 + intermediate supervision | 2016-05-10 |
| Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation | ✓ Link | 87.6 | Dite-HRNet-30 | 2022-04-22 |
| T-Net: Parametrizing Fully Convolutional Nets with a Single High-Order Tensor | | 87.5 | Tucker T-Net | 2019-04-04 |
| Compositional Human Pose Regression | ✓ Link | 86.4 | CHPR | 2017-04-01 |
| Human Pose Estimation using Deep Consensus Voting | | 85.0 | Lifshitz et al. | 2016-03-27 |
| EfficientPose: Scalable single-person pose estimation | ✓ Link | 84.8 | EfficientPose RT | 2020-04-25 |
| Matrix and tensor decompositions for training binary neural networks | | 82.5 | Matrix | 2019-04-16 |
| DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation | ✓ Link | 82.40 | DeepCut | 2015-11-20 |
| Bottom-Up and Top-Down Reasoning with Hierarchical Rectified Gaussians | ✓ Link | 82.4 | QP2 | 2015-07-21 |
| Efficient Object Localization Using Convolutional Networks | ✓ Link | 82.0 | Tompson et al. | 2014-11-16 |
| Hierarchical binary CNNs for landmark localization with limited resources | ✓ Link | 81.3 | x | 2018-08-14 |
| Human Pose Estimation with Iterative Error Feedback | ✓ Link | 81.3 | IEF | 2015-07-23 |
| Bottom-Up and Top-Down Reasoning with Hierarchical Rectified Gaussians | ✓ Link | 81.1 | QP1 | 2015-07-21 |
| Improved training of binary networks for human pose estimation and image recognition | ✓ Link | 80.9 | Improved Binary Network (HourGlass) | 2019-04-11 |