GoMatching++ | 76.88% | 79.46% | 81.30% | 42 | 10 | 21 | 2842 | 16 | 152 | 641 |
GoMatching | 76.76% | 79.64% | 80.80% | 41 | 13 | 19 | 2835 | 12 | 149 | 652 |
SVRepV2(Kuaishou-MMU) | 75.88% | 76.80% | 84.72% | 37 | 21 | 15 | 2844 | 7 | 189 | 648 |
LOGO | 74.71% | 75.07% | 80.02% | 38 | 14 | 21 | 2813 | 15 | 199 | 671 |
h&h_lab | 73.96% | 80.12% | 79.36% | 38 | 16 | 19 | 2804 | 16 | 216 | 679 |
GOCR | 73.02% | 76.28% | 82.11% | 36 | 19 | 18 | 2822 | 18 | 267 | 659 |
GOCR Offline | 72.48% | 76.39% | 82.03% | 34 | 14 | 25 | 2765 | 12 | 229 | 722 |
HIK_OCR | 69.62% | 79.34% | 79.71% | 30 | 14 | 29 | 2546 | 10 | 110 | 943 |
TransDETR | 68.82% | 76.84% | 77.43% | 39 | 17 | 17 | 2796 | 15 | 388 | 688 |
VideoTextSCM | 68.48% | 77.07% | 65.21% | 33 | 21 | 19 | 2585 | 17 | 189 | 897 |
TA-VTT | 64.62% | 79.82% | 75.47% | 28 | 20 | 25 | 2424 | 9 | 163 | 1066 |
Semantic-Aware Video Text Detection | 58.33% | 79.38% | 70.75% | 21 | 24 | 28 | 2178 | 12 | 137 | 1309 |
TransVTSpotter | 55.59% | 75.81% | 59.33% | 19 | 33 | 21 | 2211 | 41 | 266 | 1247 |
AJOU | 22.55% | 73.82% | 41.48% | 6 | 21 | 46 | 1094 | 15 | 305 | 2390 |
SRC-B-TextProcessingLab | 22.06% | 70.43% | 39.71% | 5 | 21 | 47 | 1011 | 10 | 239 | 2478 |
USTB_TexVideo II-2 | 15.26% | 68.79% | 25.37% | 1 | 19 | 53 | 661 | 41 | 127 | 2797 |
USTB_TexVideo | 14.95% | 69.32% | 29.37% | 3 | 16 | 54 | 749 | 21 | 226 | 2729 |
StradVision-1 | 8.43% | 67.24% | 27.62% | 3 | 13 | 57 | 872 | 27 | 577 | 2600 |
Megvii-Image++ | 5.94% | 64.80% | 38.21% | 4 | 30 | 39 | 1227 | 12 | 1019 | 2260 |
RTST Lucas-Kanade-2 (RealTimeSceneText_LucasKanade_v2) | -68.11% | 59.72% | 4.42% | 1 | 12 | 60 | 155 | 228 | 2538 | 3116 |
USTB_TexVideo II-1 | -7.80% | 67.57% | 23.25% | 1 | 15 | 57 | 626 | 9 | 899 | 2864 |