GoMatching++ | 85.78% | 83.77% | 90.60% | 104 | 10 | 46 | 4629 | 17 | 203 | 514 |
GoMatching | 84.07% | 82.73% | 89.15% | 109 | 8 | 43 | 4548 | 18 | 210 | 594 |
VideoTextSCM | 81.96% | 80.29% | 75.27% | 98 | 14 | 48 | 4447 | 54 | 218 | 659 |
GOCR Offline | 80.04% | 76.63% | 87.09% | 95 | 10 | 55 | 4453 | 19 | 323 | 688 |
SVRepV2(Kuaishou-MMU) | 78.93% | 79.55% | 83.88% | 97 | 23 | 40 | 4417 | 24 | 344 | 719 |
LOGO | 78.55% | 75.79% | 86.14% | 101 | 12 | 47 | 4479 | 23 | 426 | 658 |
h&h_lab | 78.28% | 82.58% | 79.63% | 87 | 20 | 53 | 4376 | 25 | 337 | 759 |
GOCR | 76.72% | 76.49% | 85.44% | 101 | 18 | 41 | 4527 | 49 | 568 | 584 |
TransDETR | 75.33% | 77.29% | 85.13% | 86 | 11 | 63 | 4246 | 11 | 359 | 903 |
HIK_OCR | 74.48% | 81.61% | 83.50% | 87 | 11 | 62 | 4106 | 26 | 263 | 1028 |
TA-VTT | 71.01% | 79.54% | 79.53% | 77 | 26 | 57 | 4012 | 49 | 348 | 1099 |
Semantic-Aware Video Text Detection | 67.71% | 79.21% | 78.16% | 68 | 30 | 62 | 3769 | 36 | 275 | 1355 |
TransVTSpotter | 67.52% | 77.39% | 74.94% | 77 | 21 | 62 | 4015 | 78 | 531 | 1067 |
SRC-B-TextProcessingLab | 49.57% | 72.02% | 66.80% | 50 | 30 | 80 | 2990 | 29 | 432 | 2141 |
AJOU | 45.89% | 71.98% | 61.97% | 39 | 34 | 87 | 2689 | 57 | 321 | 2414 |
USTB_TexVideo | 41.57% | 73.56% | 54.21% | 26 | 47 | 87 | 2522 | 50 | 377 | 2588 |
USTB_TexVideo II-2 | 35.97% | 73.82% | 48.09% | 19 | 48 | 93 | 2154 | 66 | 298 | 2940 |
Megvii-Image++ | 35.74% | 66.04% | 56.46% | 27 | 54 | 79 | 2789 | 33 | 945 | 2338 |
StradVision-1 | 33.02% | 73.02% | 47.76% | 22 | 53 | 85 | 2252 | 85 | 548 | 2823 |
USTB_TexVideo II-1 | 15.83% | 70.09% | 47.74% | 28 | 44 | 88 | 2311 | 46 | 1494 | 2803 |
RTST Lucas-Kanade-2 (RealTimeSceneText_LucasKanade_v2) | -79.79% | 67.88% | 5.23% | 8 | 33 | 119 | 310 | 778 | 4427 | 4072 |