Detecting text regions in natural scene images
Dataset from Papers With Code
Leading models on coco-text.
| # | Model | 1-1-accuracy | Year | Source |
|---|---|---|---|---|
| ★ | CLIP4STR-L✓ | 81.9 | 2023 | paper ↗ |
| 2 | MGP-STR✓ | 81.7 | 2022 | paper ↗ |
| 3 | CLIP4STR-B✓ | 81.1 | 2023 | paper ↗ |
| 4 | TCM | 65.9 | 2026 | paper ↗ |
| 5 | PANet (Joint) | 64.5 | 2026 | paper ↗ |
| 6 | Corner-based Region Proposals✓ | 63.3 | 2018 | paper ↗ |
| 7 | LRANet | 61.7 | 2026 | paper ↗ |
| 8 | DPText-DETR | 61.6 | 2026 | paper ↗ |
| 9 | TextBoxes++_MS✓ | 60.9 | 2018 | paper ↗ |
| 10 | MAEDet | 60.6 | 2026 | paper ↗ |
Didn't find the model, metric, or dataset you needed? Tell us in one line. We read every message and reply within 48 hours.
11 datasets tracked for this task.
Still looking for something on Scene Text Detection? A missing model, a stale score, a benchmark we should cover — drop it here and we'll handle it.
Real humans read every message. We track what people are asking for and prioritize accordingly.