| LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting | ✓ Link | 84.6 | 89.7 | LRANet++ (Synth150K, MLT17, IC13, IC15, TextOCR) | 2025-11-08 |
| DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting | ✓ Link | 83.6 | 89.6 | DeepSolo (ViTAEv2-S, TextOCR) | 2022-11-19 |
| DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting | ✓ Link | 82.5 | 88.7 | DeepSolo (ResNet-50, TextOCR) | 2022-11-19 |
| LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting | ✓ Link | 82.2 | 87.7 | LRANet++ (Synth150K, MLT17) | 2025-11-08 |
| DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting | ✓ Link | 79.7 | 87.0 | DeepSolo (ResNet-50) | 2022-11-19 |
| A3S: Adversarial learning of semantic representations for Scene-Text Spotting | | 79.4 | 85.1 | A3S | 2023-02-21 |
| Towards Unified Scene Text Spotting based on Sequence Generation | ✓ Link | 78.7 | 86.0 | UNITS | 2023-04-07 |
| GLASS: Global to Local Attention for Scene-Text Spotting | ✓ Link | 76.6 | 83.0 | GLASS | 2022-08-05 |
| DEER: Detection-agnostic End-to-End Recognizer for Scene Text Spotting | | 74.8 | 83.3 | DEER | 2022-03-10 |
| SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition | ✓ Link | 74.3 | 84.1 | SwinTextSpotter | 2022-03-19 |
| Text Spotting Transformers | ✓ Link | 73.3 | 83.9 | TESTR | 2022-04-05 |
| MANGO: A Mask Attention Guided One-Stage Scene Text Spotter | ✓ Link | 72.9 | 83.6 | MANGO | 2020-12-08 |
| Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting | ✓ Link | 71.2 | 78.4 | MaskTextSpotter v3 | 2020-07-18 |
| ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting | ✓ Link | 70.4 | 78.1 | ABCNet v2 | 2021-05-08 |