Human-Art is a versatile human-centric dataset to bridge the gap between natural and artificial scenes. It includes twenty high-quality human scenes, including natural and artificial humans in both 2D representation and 3D representation. It includes 50,000 images including more than 123,000 human figures in 20 scenarios, with annotations of human bounding box, 21 2D human keypoints, human self-contact keypoints, and description text.
Variants: Human-Art
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| 2D Human Pose Estimation | UniPose | X-Pose: Detecting Any Keypoints | 2023-10-12 |
| 2D Human Pose Estimation | RTMPose-l | RTMPose: Real-Time Multi-Person Pose Estimation … | 2023-03-13 |
| 2D Human Pose Estimation | RTMPose-s | RTMPose: Real-Time Multi-Person Pose Estimation … | 2023-03-13 |
| 2D Human Pose Estimation | ED-Pose (R50) | Explicit Box Detection Unifies End-to-End … | 2023-02-03 |
| 2D Human Pose Estimation | ViTPose-h | ViTPose: Simple Vision Transformer Baselines … | 2022-04-26 |
| 2D Human Pose Estimation | ViTpose-b | ViTPose: Simple Vision Transformer Baselines … | 2022-04-26 |
| 2D Human Pose Estimation | ViTPose-l | ViTPose: Simple Vision Transformer Baselines … | 2022-04-26 |
| 2D Human Pose Estimation | ViTPose-s | ViTPose: Simple Vision Transformer Baselines … | 2022-04-26 |
| 2D Human Pose Estimation | HRNet-w32 | Deep High-Resolution Representation Learning for … | 2019-02-25 |
| 2D Human Pose Estimation | HRNet-w48 | Deep High-Resolution Representation Learning for … | 2019-02-25 |
Recent papers with results on this dataset: