TextSeg
Introduced by Xu et al. in Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach
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-SegmentationBenchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
TextSeg
|
CCD-ViT-Small
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
