GoMatching | 65.37% | 76.37% | 64.54% | 32 | 7 | 7 | 802 | 20 | 77 | 287 |
GoMatching++ | 64.20% | 76.36% | 69.62% | 32 | 8 | 6 | 833 | 14 | 121 | 262 |
h&h_lab | 53.38% | 75.09% | 61.42% | 17 | 17 | 12 | 624 | 13 | 32 | 472 |
VideoTextSCM | 48.51% | 71.75% | 56.72% | 15 | 15 | 16 | 551 | 23 | 13 | 535 |
HIK_OCR | 45.54% | 73.38% | 46.13% | 16 | 12 | 18 | 526 | 48 | 21 | 535 |
SVRepV2(Kuaishou-MMU) | 45.27% | 74.81% | 62.00% | 22 | 15 | 9 | 637 | 61 | 135 | 411 |
GOCR Offline | 42.47% | 68.94% | 48.45% | 25 | 10 | 11 | 722 | 44 | 251 | 343 |
TA-VTT | 40.76% | 71.89% | 56.99% | 18 | 15 | 13 | 577 | 14 | 125 | 518 |
GOCR | 40.04% | 68.94% | 46.86% | 31 | 11 | 4 | 765 | 80 | 321 | 264 |
LOGO | 39.77% | 72.02% | 49.73% | 17 | 16 | 13 | 579 | 24 | 138 | 506 |
Semantic-Aware Video Text Detection | 37.69% | 72.21% | 57.49% | 12 | 17 | 17 | 519 | 7 | 101 | 583 |
TransDETR | 31.56% | 74.21% | 36.71% | 19 | 9 | 18 | 485 | 85 | 135 | 539 |
AJOU | 23.08% | 70.02% | 35.97% | 2 | 16 | 28 | 337 | 13 | 81 | 759 |
TransVTSpotter | 15.51% | 71.81% | 21.11% | 2 | 17 | 27 | 222 | 40 | 50 | 847 |
SRC-B-TextProcessingLab | 7.39% | 65.66% | 24.11% | 0 | 10 | 36 | 170 | 2 | 88 | 937 |
StradVision-1 | 4.15% | 69.08% | 11.78% | 0 | 7 | 39 | 139 | 17 | 93 | 953 |
USTB_TexVideo II-1 | 2.80% | 68.92% | 9.06% | 0 | 3 | 43 | 67 | 2 | 36 | 1040 |
USTB_TexVideo II-2 | 2.34% | 69.08% | 6.70% | 0 | 1 | 45 | 40 | 1 | 14 | 1068 |
USTB_TexVideo | 2.16% | 68.79% | 7.13% | 0 | 1 | 45 | 46 | 1 | 22 | 1062 |
RTST Lucas-Kanade-2 (RealTimeSceneText_LucasKanade_v2) | -21.91% | 68.75% | 2.82% | 0 | 2 | 44 | 23 | 18 | 266 | 1068 |
Megvii-Image++ | -12.80% | 59.58% | 7.57% | 1 | 8 | 37 | 72 | 5 | 214 | 1032 |