GoMatching++ | 65.48% | 78.81% | 77.41% | 223 | 42 | 49 | 5124 | 98 | 735 | 1481 |
SVRepV2(Kuaishou-MMU) | 62.14% | 75.62% | 73.43% | 204 | 62 | 48 | 4948 | 63 | 783 | 1692 |
GoMatching | 61.54% | 78.68% | 73.80% | 209 | 48 | 57 | 4883 | 85 | 758 | 1735 |
GOCR Offline | 61.39% | 73.58% | 76.10% | 224 | 46 | 44 | 5060 | 80 | 945 | 1563 |
GOCR | 59.82% | 73.53% | 74.91% | 233 | 40 | 41 | 5099 | 144 | 1089 | 1460 |
VideoTextSCM | 59.15% | 77.31% | 67.57% | 190 | 62 | 62 | 4704 | 191 | 739 | 1808 |
LOGO | 58.48% | 70.87% | 74.01% | 202 | 55 | 57 | 4892 | 69 | 972 | 1742 |
h&h_lab | 57.71% | 76.80% | 67.96% | 162 | 86 | 66 | 4637 | 98 | 769 | 1968 |
TA-VTT | 56.83% | 76.65% | 70.00% | 164 | 74 | 76 | 4403 | 129 | 594 | 2171 |
Semantic-Aware Video Text Detection | 53.16% | 76.19% | 67.75% | 133 | 84 | 97 | 4038 | 93 | 475 | 2572 |
HIK_OCR | 47.95% | 77.88% | 66.62% | 127 | 47 | 140 | 3719 | 37 | 505 | 2947 |
TransVTSpotter | 46.41% | 70.61% | 58.25% | 140 | 101 | 73 | 4027 | 313 | 916 | 2363 |
TransDETR | 45.58% | 71.37% | 65.78% | 135 | 75 | 104 | 4026 | 49 | 971 | 2628 |
Megvii-Image++ | 33.67% | 71.97% | 50.31% | 54 | 80 | 180 | 2755 | 38 | 498 | 3910 |
SRC-B-TextProcessingLab | 32.40% | 72.14% | 50.24% | 61 | 81 | 172 | 2540 | 75 | 368 | 4088 |
USTB_TexVideo | 25.06% | 74.20% | 39.47% | 37 | 92 | 185 | 2230 | 83 | 550 | 4390 |
USTB_TexVideo II-2 | 24.17% | 74.07% | 37.44% | 31 | 91 | 192 | 2046 | 92 | 426 | 4565 |
AJOU | 20.96% | 75.56% | 31.21% | 33 | 91 | 190 | 1868 | 323 | 463 | 4512 |
StradVision-1 | 13.52% | 72.97% | 28.14% | 19 | 70 | 225 | 1438 | 75 | 532 | 5190 |
USTB_TexVideo II-1 | 7.03% | 72.11% | 30.63% | 36 | 42 | 236 | 1684 | 58 | 1213 | 4961 |
RTST Lucas-Kanade-2 (RealTimeSceneText_LucasKanade_v2) | -81.68% | 65.60% | 2.48% | 8 | 46 | 260 | 213 | 684 | 5688 | 5806 |