GoMatching | 81.92% | 71.94% | 78.29% | 3 | 0 | 1 | 620 | 8 | 13 | 113 |
GoMatching++ | 73.82% | 73.28% | 80.97% | 2 | 1 | 1 | 558 | 4 | 11 | 179 |
LOGO | 71.66% | 67.46% | 80.33% | 2 | 1 | 1 | 554 | 4 | 23 | 183 |
GOCR | 56.68% | 69.93% | 69.72% | 2 | 2 | 0 | 556 | 7 | 136 | 178 |
TransDETR | 56.14% | 75.90% | 52.81% | 0 | 4 | 0 | 445 | 12 | 29 | 284 |
GOCR Offline | 55.60% | 70.42% | 72.07% | 1 | 3 | 0 | 530 | 4 | 118 | 207 |
SVRepV2(Kuaishou-MMU) | 51.15% | 79.50% | 75.16% | 3 | 0 | 1 | 575 | 10 | 196 | 156 |
TA-VTT | 49.12% | 79.77% | 67.80% | 0 | 3 | 1 | 399 | 2 | 35 | 340 |
Semantic-Aware Video Text Detection | 43.59% | 81.22% | 61.75% | 0 | 3 | 1 | 345 | 3 | 22 | 393 |
h&h_lab | 41.84% | 78.91% | 64.12% | 0 | 3 | 1 | 386 | 1 | 76 | 354 |
TransVTSpotter | 39.00% | 77.84% | 30.57% | 0 | 3 | 1 | 312 | 10 | 23 | 419 |
VideoTextSCM | 38.46% | 74.26% | 61.71% | 0 | 4 | 0 | 382 | 5 | 97 | 354 |
HIK_OCR | 32.25% | 77.32% | 48.87% | 0 | 3 | 1 | 256 | 1 | 17 | 484 |
SRC-B-TextProcessingLab | 29.82% | 70.33% | 47.69% | 0 | 3 | 1 | 237 | 0 | 16 | 504 |
USTB_TexVideo | 20.11% | 71.09% | 21.70% | 0 | 3 | 1 | 203 | 16 | 54 | 522 |
StradVision-1 | 17.68% | 76.70% | 21.88% | 0 | 3 | 1 | 178 | 21 | 47 | 542 |
Megvii-Image++ | 16.60% | 73.00% | 34.21% | 0 | 3 | 1 | 221 | 4 | 98 | 516 |
USTB_TexVideo II-2 | 12.55% | 77.51% | 13.54% | 0 | 2 | 2 | 127 | 14 | 34 | 600 |
RTST Lucas-Kanade-2 (RealTimeSceneText_LucasKanade_v2) | -211.74% | 66.15% | 0.77% | 0 | 0 | 4 | 7 | 13 | 1576 | 721 |
AJOU | -15.25% | 76.20% | 34.27% | 0 | 3 | 1 | 314 | 6 | 427 | 421 |
USTB_TexVideo II-1 | -14.44% | 71.05% | 18.18% | 0 | 3 | 1 | 160 | 9 | 267 | 572 |