TA-VTT | 76.32% | 73.58% | 86.84% | 11 | 4 | 0 | 571 | 2 | 20 | 149 |
TransDETR | 69.81% | 71.58% | 83.95% | 11 | 4 | 0 | 579 | 1 | 75 | 142 |
Semantic-Aware Video Text Detection | 69.53% | 73.80% | 82.34% | 10 | 4 | 1 | 513 | 0 | 11 | 209 |
h&h_lab | 61.50% | 74.00% | 75.70% | 8 | 7 | 0 | 505 | 4 | 61 | 213 |
LOGO | 58.86% | 67.78% | 77.96% | 11 | 3 | 1 | 527 | 1 | 102 | 194 |
TransVTSpotter | 54.57% | 75.06% | 72.06% | 11 | 3 | 1 | 483 | 5 | 89 | 234 |
SVRepV2(Kuaishou-MMU) | 49.17% | 71.89% | 71.92% | 8 | 6 | 1 | 470 | 0 | 115 | 252 |
GoMatching++ | 28.67% | 72.36% | 57.08% | 10 | 2 | 3 | 414 | 6 | 207 | 302 |
GOCR Offline | 28.53% | 67.68% | 58.07% | 6 | 6 | 3 | 370 | 1 | 164 | 351 |
GoMatching | 28.53% | 72.29% | 60.91% | 9 | 3 | 3 | 402 | 0 | 196 | 320 |
HIK_OCR | 27.56% | 75.35% | 56.53% | 7 | 5 | 3 | 340 | 0 | 141 | 382 |
GOCR | 26.32% | 67.56% | 56.90% | 7 | 5 | 3 | 373 | 5 | 183 | 344 |
VideoTextSCM | 22.99% | 70.28% | 57.03% | 4 | 9 | 2 | 374 | 4 | 208 | 344 |
AJOU | 12.88% | 67.54% | 43.24% | 4 | 5 | 6 | 240 | 1 | 147 | 481 |
USTB_TexVideo II-2 | 0.97% | 63.33% | 11.16% | 1 | 3 | 11 | 65 | 15 | 58 | 642 |
USTB_TexVideo II-1 | -192.24% | 65.10% | 0.56% | 0 | 0 | 15 | 9 | 1 | 1397 | 712 |
RTST Lucas-Kanade-2 (RealTimeSceneText_LucasKanade_v2) | -171.75% | 61.64% | 1.38% | 0 | 3 | 12 | 8 | 52 | 1248 | 662 |
USTB_TexVideo | -21.47% | 63.20% | 11.44% | 1 | 3 | 11 | 98 | 11 | 253 | 613 |
Megvii-Image++ | -21.47% | 64.04% | 32.85% | 1 | 9 | 5 | 221 | 2 | 376 | 499 |
SRC-B-TextProcessingLab | -7.89% | 58.57% | 18.26% | 0 | 5 | 10 | 87 | 0 | 144 | 635 |
StradVision-1 | -4.29% | 58.21% | 19.44% | 0 | 4 | 11 | 91 | 1 | 122 | 630 |