TextSeg is a large-scale fine-annotated and multi-purpose text detection and segmentation dataset, collecting scene and design text with six types of annotations: word- and character-wise bounding polygons, masks and transcriptions.
Source: https://github.com/SHI-Labs/Rethinking-Text-Segmentation
Image Source: https://github.com/SHI-Labs/Rethinking-Text-Segmentation
Variants: TextSeg
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| self-supervised scene text recognition | CCD-ViT-Small | Self-supervised Character-to-Character Distillation for Text … | 2022-11-01 |
Recent papers with results on this dataset: