TransDETR | 51.57% | 74.50% | 73.36% | 37 | 12 | 12 | 1122 | 0 | 254 | 561 |
LOGO | 47.06% | 70.32% | 71.45% | 34 | 16 | 11 | 1129 | 3 | 337 | 551 |
TransVTSpotter | 39.45% | 76.06% | 65.12% | 29 | 17 | 15 | 1030 | 20 | 366 | 633 |
GoMatching++ | 30.66% | 74.33% | 63.69% | 39 | 4 | 18 | 1052 | 4 | 536 | 627 |
Semantic-Aware Video Text Detection | 29.35% | 78.31% | 58.99% | 24 | 12 | 25 | 864 | 9 | 370 | 810 |
SVRepV2(Kuaishou-MMU) | 29.11% | 70.87% | 62.15% | 27 | 20 | 14 | 993 | 7 | 503 | 683 |
TA-VTT | 28.46% | 77.52% | 60.48% | 27 | 16 | 18 | 943 | 15 | 464 | 725 |
GoMatching | 27.87% | 73.72% | 61.91% | 34 | 8 | 19 | 1011 | 4 | 542 | 668 |
VideoTextSCM | 27.27% | 74.40% | 58.63% | 29 | 13 | 19 | 893 | 16 | 434 | 774 |
h&h_lab | 25.31% | 75.79% | 59.14% | 22 | 23 | 16 | 943 | 9 | 517 | 731 |
HIK_OCR | 20.32% | 76.05% | 51.65% | 25 | 7 | 29 | 724 | 7 | 382 | 952 |
SRC-B-TextProcessingLab | 13.61% | 63.58% | 37.21% | 9 | 14 | 38 | 496 | 10 | 267 | 1177 |
AJOU | 7.90% | 72.89% | 40.40% | 15 | 9 | 37 | 575 | 13 | 442 | 1095 |
USTB_TexVideo II-2 | 6.48% | 65.72% | 14.43% | 1 | 14 | 46 | 201 | 34 | 92 | 1448 |
USTB_TexVideo | 1.66% | 64.22% | 23.10% | 0 | 21 | 40 | 357 | 38 | 329 | 1288 |
RTST Lucas-Kanade-2 (RealTimeSceneText_LucasKanade_v2) | -79.26% | 65.40% | 2.99% | 0 | 17 | 44 | 51 | 159 | 1385 | 1473 |
USTB_TexVideo II-1 | -32.38% | 66.49% | 14.89% | 1 | 15 | 45 | 236 | 26 | 781 | 1421 |
GOCR | -15.75% | 70.30% | 50.18% | 36 | 5 | 20 | 989 | 4 | 1254 | 690 |
Megvii-Image++ | -14.38% | 61.18% | 26.81% | 3 | 20 | 38 | 378 | 5 | 620 | 1300 |
GOCR Offline | -14.02% | 70.34% | 50.50% | 35 | 5 | 21 | 986 | 2 | 1222 | 695 |
StradVision-1 | -2.32% | 62.25% | 23.52% | 5 | 14 | 42 | 332 | 29 | 371 | 1322 |