Unknown
coco-text is a state-of-the-art machine learning benchmark indexed on Codesota. This page tracks published model results, top scores per metric, and the SOTA timeline for coco-text.
Higher is better
| Rank | Model | Source | Score | Year | Paper |
|---|---|---|---|---|---|
| 1 | TCM CLIP-based detector with joint-dataset training. IJCAI 2025. | Editorial | 65.9 | 2026 | Source |
| 2 | PANet (Joint) Pixel Aggregation Network with joint-dataset fine-tuning. | Editorial | 64.5 | 2026 | Source |
| 3 | LRANet Low-Rank Approximation Network. AAAI 2024 Oral. | Editorial | 61.7 | 2026 | Source |
| 4 | DPText-DETR DETR-based with dynamic point queries. Joint training. AAAI 2023. | Editorial | 61.6 | 2026 | Source |
| 5 | MAEDet MAE-based self-supervised pretraining for text detection. IJCAI 2025. | Editorial | 60.6 | 2026 | Source |
| 6 | DBNet Differentiable Binarization with fine-tuning. AAAI 2020. | Editorial | 60.5 | 2026 | Source |
| 7 | DBNet++ DB with Adaptive Scale Fusion. Joint training. TPAMI 2022. | Editorial | 59.5 | 2026 | Source |
| 8 | SRFormer Segmentation+Regression Transformer. AAAI 2024. | Editorial | 59.4 | 2026 | Source |
| 9 | FCENet Fourier Contour Embedding. CVPR 2021. | Editorial | 57.9 | 2026 | Source |
| 10 | PSENet Progressive Scale Expansion Network. CVPR 2019. | Editorial | 56 | 2026 | Source |
| 11 | ABCNet v2 Adaptive Bezier-Curve Network v2. TPAMI 2021. | Editorial | 53.2 | 2026 | Source |
| 12 | ABCNet v2 Adaptive Bezier-Curve Network v2. TPAMI 2021. | Editorial | 53.2 | 2026 | Source |
| 13 | DRRG Deep Relational Reasoning Graph. CVPR 2020. | Editorial | 31.9 | 2026 | Source |