People-Art is an object detection dataset which consists of people in 43 different styles. People contained in this dataset are quite different from those in common photographs. There are 42 categories of art styles and movements including Naturalism, Cubism, Socialist Realism, Impressionism, and Suprematism
Source: Point Linking Network for Object Detection
Image Source: https://www.researchgate.net/figure/Generalization-results-on-Picasso-and-People-Art-datasets-Joseph-Redmon-2016_fig12_328175597
Variants: PeopleArt
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Object Detection | PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt) | Poses of People in Art: … | 2023-01-12 |
| Object Detection | TOOD (Task-aligned One-stage Object Detection; trained on PeopleArt and PoPArt) | Poses of People in Art: … | 2023-01-12 |
| Object Detection | PVT (Pyramid Vision Transformer) | Poses of People in Art: … | 2023-01-12 |
| Object Detection | TOOD (Task-aligned One-stage Object Detection) | Poses of People in Art: … | 2023-01-12 |
| Object Detection | FasterRCNN (trained on StyleCOCO) | Improving Object Detection in Art … | 2021-02-12 |
| Object Detection | Fast R-CNN | Detecting People in Artwork with … | 2016-10-27 |
Recent papers with results on this dataset: