SVRepV2(Kuaishou-MMU) | 59.77% | 76.84% | 78.36% | 19 | 17 | 5 | 618 | 4 | 147 | 166 |
TA-VTT | 53.05% | 78.75% | 74.77% | 15 | 15 | 11 | 577 | 6 | 159 | 205 |
LOGO | 49.24% | 74.04% | 59.96% | 20 | 13 | 8 | 578 | 35 | 190 | 175 |
GoMatching++ | 49.24% | 80.21% | 61.89% | 18 | 9 | 14 | 474 | 35 | 86 | 279 |
Semantic-Aware Video Text Detection | 48.10% | 79.83% | 66.61% | 9 | 15 | 17 | 434 | 5 | 55 | 349 |
TransVTSpotter | 46.83% | 77.41% | 59.22% | 6 | 18 | 17 | 388 | 14 | 19 | 386 |
GoMatching | 43.91% | 78.76% | 59.74% | 19 | 9 | 13 | 451 | 52 | 105 | 285 |
GOCR | 42.64% | 72.54% | 72.17% | 25 | 9 | 7 | 625 | 5 | 289 | 158 |
h&h_lab | 41.62% | 77.64% | 61.01% | 8 | 15 | 18 | 392 | 5 | 64 | 391 |
GOCR Offline | 40.86% | 72.83% | 69.85% | 22 | 4 | 15 | 563 | 0 | 241 | 225 |
TransDETR | 35.41% | 75.73% | 54.95% | 7 | 9 | 25 | 311 | 1 | 32 | 476 |
HIK_OCR | 31.60% | 77.69% | 45.19% | 8 | 8 | 25 | 279 | 5 | 30 | 504 |
VideoTextSCM | 30.08% | 76.63% | 53.36% | 9 | 12 | 20 | 319 | 3 | 82 | 466 |
Megvii-Image++ | 15.48% | 63.65% | 42.93% | 2 | 9 | 30 | 253 | 2 | 131 | 533 |
USTB_TexVideo II-2 | 11.42% | 71.08% | 22.01% | 0 | 8 | 33 | 126 | 13 | 36 | 649 |
SRC-B-TextProcessingLab | 8.76% | 64.80% | 22.04% | 2 | 5 | 34 | 113 | 8 | 44 | 667 |
AJOU | 1.90% | 71.76% | 39.36% | 8 | 9 | 24 | 270 | 8 | 255 | 510 |
USTB_TexVideo II-1 | -79.95% | 69.36% | 8.77% | 2 | 4 | 35 | 75 | 5 | 705 | 708 |
RTST Lucas-Kanade-2 (RealTimeSceneText_LucasKanade_v2) | -21.19% | 69.71% | 0.42% | 0 | 0 | 41 | 4 | 0 | 171 | 784 |
USTB_TexVideo | -19.80% | 69.88% | 20.72% | 2 | 9 | 30 | 151 | 9 | 307 | 628 |
StradVision-1 | -4.95% | 67.22% | 7.66% | 1 | 4 | 36 | 54 | 5 | 93 | 729 |