| LRANet | 94.74% | 78.26% | 85.71% |
 NJU-ImagineLab | 68.42% | 68.42% | 68.42% |
| Tencent TEG OCR | 68.42% | 68.42% | 68.42% |
| TD-PPIoU (Long-Pretrain) | 52.63% | 90.91% | 66.67% |
| AntFin-Cascade Mask R-CNN | 68.42% | 61.90% | 65.00% |
| TextFuseNet (ResNeXt-101) | 63.16% | 63.16% | 63.16% |
| HOCRA | 52.63% | 71.43% | 60.61% |
| CPNText-DETR(resnet-50) | 52.63% | 71.43% | 60.61% |
| I3CL | 63.16% | 57.14% | 60.00% |
| Unicamp-SRBR-PN-1 | 57.89% | 57.89% | 57.89% |
| DPText-DETR (ResNet-50) | 47.37% | 69.23% | 56.25% |
| TP | 52.63% | 55.56% | 54.05% |
| TextFuseNet (ResNet-50) | 52.63% | 55.56% | 54.05% |
| QAQ | 47.37% | 60.00% | 52.94% |
| Fudan-Supremind Detection v3 | 57.89% | 47.83% | 52.38% |
| TMIS | 47.37% | 56.25% | 51.43% |
| SRFormer (ResNet50-#1seg) | 47.37% | 56.25% | 51.43% |
| A scene text detection method based on maskrcnn | 52.63% | 50.00% | 51.28% |
| DuXiaoman_OCR | 52.63% | 50.00% | 51.28% |
| AutoCV | 52.63% | 50.00% | 51.28% |
| CUTeOCR | 52.63% | 47.62% | 50.00% |
| SRCB_Art | 47.37% | 47.37% | 47.37% |
| CCISTD | 47.37% | 47.37% | 47.37% |
| MaskRCNN_Text | 42.11% | 50.00% | 45.71% |
| NN_Chinese_and_euro6 | 47.37% | 42.86% | 45.00% |
| TextBPN++(ResNet-50 with DCN) | 36.84% | 53.85% | 43.75% |
| ArtDet-v2 | 42.11% | 44.44% | 43.24% |
| Art_test_baseline_task1 | 47.37% | 37.50% | 41.86% |
| TextBPN++(ResNet-50) | 36.84% | 46.67% | 41.18% |
| CLTDR | 36.84% | 43.75% | 40.00% |
| Mask RCNN | 52.63% | 32.26% | 40.00% |
| mask rcnn | 42.11% | 36.36% | 39.02% |
| Alibaba-PAI | 42.11% | 36.36% | 39.02% |
| TD-PPIoU | 31.58% | 50.00% | 38.71% |
| baseline_polygon | 42.11% | 34.78% | 38.10% |
| Sogou_OCR | 36.84% | 38.89% | 37.84% |
| NN_euro6 | 31.58% | 46.15% | 37.50% |
| HOCRA_base | 26.32% | 62.50% | 37.04% |
| TEXT_SNIPER | 36.84% | 36.84% | 36.84% |
| MEGVII_Detection | 26.32% | 55.56% | 35.71% |
| Sg_ptd | 31.58% | 40.00% | 35.29% |
| MaskDet | 36.84% | 30.43% | 33.33% |
| I3CL(ViTAEv2-S) | 26.32% | 38.46% | 31.25% |
| dp_pq_nn | 21.05% | 57.14% | 30.77% |
| Art detect by vivo | 26.32% | 33.33% | 29.41% |
| MFTD: Mask Filters for Text Detection | 31.58% | 26.09% | 28.57% |
| ESRNet | 26.32% | 31.25% | 28.57% |
| dp_nn | 21.05% | 33.33% | 25.81% |
| TextMask_V1 | 26.32% | 25.00% | 25.64% |
| Mask R-CNN | 21.05% | 30.77% | 25.00% |
| DMCA | 26.32% | 20.83% | 23.26% |
| PAT-S.Y | 21.05% | 23.53% | 22.22% |
| CRAFT | 21.05% | 22.22% | 21.62% |
| Improved Progressive scale expansion Net | 21.05% | 20.00% | 20.51% |
| TextCohesion_1 | 21.05% | 15.38% | 17.78% |
| 1 | 21.05% | 14.29% | 17.02% |
| DMText_art | 10.53% | 25.00% | 14.81% |
| fdu_ai | 10.53% | 11.76% | 11.11% |
| EM-DATA | 10.53% | 11.11% | 10.81% |
| inception baseline | 5.26% | 7.69% | 6.25% |
| RAST: Robust Arbitrary Shape Text Detector | 5.26% | 6.67% | 5.88% |
| MSR | 0.00% | 0.00% | 0.00% |