| Paper | Code | mAP | mAP@0.5 | mAP@0.75 | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|
| Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History | 49.7 | 80.5 | 51.8 | PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt) | 2023-01-12 | |
| Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History | 47.8 | 78.0 | 49.9 | TOOD (Task-aligned One-stage Object Detection; trained on PeopleArt and PoPArt) | 2023-01-12 | |
| Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History | 46.5 | 76.0 | 48.4 | PVT (Pyramid Vision Transformer) | 2023-01-12 | |
| Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History | 46.1 | 75.0 | 49.0 | TOOD (Task-aligned One-stage Object Detection) | 2023-01-12 | |
| Improving Object Detection in Art Images Using Only Style Transfer | ✓ Link | 36 | 68 | 33 | FasterRCNN (trained on StyleCOCO) | 2021-02-12 |
| Detecting People in Artwork with CNNs | ✓ Link | 59.0 | Fast R-CNN | 2016-10-27 |