TRR360D is based on the ICDAR2019MTD modern table detection dataset, it refers to the annotation format of the DOTA dataset. The training set contains 600 rotated images and 977 annotated instances, and the test set contains 240 rotated images and 499 annotated instances.
Source: T360RRD: A dataset for 360 degree rotated rectangular box table detection
Image Source: https://github.com/vansin/TRR360D
Variants: TRR360D
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| 2D Object Detection | rotated-retinanet-rbox-r360_r50_fpn_6x.py | TRR360D: A dataset for 360 … | 2023-03-03 |
Recent papers with results on this dataset: