The database consists of 150 annotated pages of three different medieval manuscripts with challenging layouts. Furthermore, we provide a layout analysis ground-truth which has been iterated on, reviewed, and refined by an expert in medieval studies.
Variants: DIVA-HisDB
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Semantic Segmentation | WACV '23 (few-shot) | Efficient few-shot learning for pixel-precise … | 2022-10-27 |
| Semantic Segmentation | U-Net | DIVA-DAF: A Deep Learning Framework … | 2022-01-20 |
Recent papers with results on this dataset: