GoMatching++ | 68.26% | 81.48% | 75.03% | 163 | 69 | 84 | 9297 | 142 | 1189 | 2439 |
h&h_lab | 63.77% | 78.64% | 73.64% | 139 | 92 | 85 | 9054 | 137 | 1479 | 2687 |
GoMatching | 63.21% | 81.18% | 71.75% | 135 | 81 | 100 | 8666 | 124 | 1158 | 3088 |
GOCR | 62.94% | 74.35% | 73.67% | 185 | 51 | 80 | 9513 | 207 | 2037 | 2158 |
LOGO | 62.90% | 72.71% | 72.41% | 145 | 78 | 93 | 9148 | 172 | 1677 | 2558 |
GOCR Offline | 62.67% | 74.50% | 74.11% | 170 | 39 | 107 | 9345 | 140 | 1901 | 2393 |
VideoTextSCM | 62.01% | 78.31% | 66.70% | 139 | 94 | 83 | 8827 | 267 | 1462 | 2784 |
SVRepV2(Kuaishou-MMU) | 61.96% | 78.06% | 73.33% | 155 | 94 | 67 | 8789 | 171 | 1429 | 2918 |
TransDETR | 60.48% | 73.73% | 74.10% | 129 | 86 | 101 | 8891 | 65 | 1707 | 2922 |
TA-VTT | 57.55% | 77.42% | 69.62% | 119 | 76 | 121 | 8207 | 160 | 1371 | 3511 |
Semantic-Aware Video Text Detection | 56.51% | 77.10% | 68.49% | 108 | 72 | 136 | 7768 | 133 | 1056 | 3977 |
HIK_OCR | 47.87% | 79.83% | 63.76% | 93 | 63 | 160 | 6383 | 58 | 697 | 5437 |
TransVTSpotter | 44.25% | 73.25% | 60.08% | 96 | 101 | 119 | 7606 | 278 | 2350 | 3994 |
SRC-B-TextProcessingLab | 32.72% | 74.00% | 48.66% | 43 | 57 | 216 | 4692 | 62 | 805 | 7124 |
AJOU | 26.31% | 72.53% | 45.94% | 45 | 67 | 204 | 4412 | 184 | 1287 | 7282 |
USTB_TexVideo | 19.84% | 77.44% | 35.52% | 22 | 75 | 219 | 3782 | 167 | 1425 | 7929 |
StradVision-1 | 19.41% | 74.52% | 34.00% | 26 | 48 | 242 | 3506 | 172 | 1201 | 8200 |
USTB_TexVideo II-2 | 19.14% | 77.88% | 32.30% | 12 | 59 | 245 | 3128 | 123 | 854 | 8627 |
Megvii-Image++ | 19.08% | 68.60% | 44.24% | 22 | 103 | 191 | 5224 | 88 | 2958 | 6566 |
RTST Lucas-Kanade-2 (RealTimeSceneText_LucasKanade_v2) | -79.07% | 69.73% | 2.94% | 3 | 40 | 273 | 483 | 1229 | 9875 | 10166 |
USTB_TexVideo II-1 | -0.46% | 71.30% | 29.36% | 16 | 57 | 243 | 3143 | 96 | 3198 | 8639 |