SRFormer (ResNet-50)

Reported on 4 benchmarks across 1 task · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

Scene Text DetectiononSCUT-CTW1500
F-Measure· 2023-08-21
89.6
best: 89.8 (MixNet)
SOTA
SRFormer: Text Detection Transformer with Incorporated Segmentation and Regression arXiv:2308.10531
Scene Text DetectiononSCUT-CTW1500
Recall· 2023-08-21
87.7
best: 88.3 (MixNet)
SOTA
SRFormer: Text Detection Transformer with Incorporated Segmentation and Regression arXiv:2308.10531
Scene Text DetectiononIC19-Art
H-Mean· 2023-08-21
79.3
best: 79.7 (MixNet)
SOTA
SRFormer: Text Detection Transformer with Incorporated Segmentation and Regression arXiv:2308.10531
Scene Text DetectiononSCUT-CTW1500
Precision· 2023-08-21
91.6
best: 91.7 (DPText-DETR (ResNet50))
SRFormer: Text Detection Transformer with Incorporated Segmentation and Regression arXiv:2308.10531