GoMatching | 63.06% | 75.77% | 71.30% | 115 | 40 | 19 | 5216 | 124 | 1017 | 1319 |
SVRepV2(Kuaishou-MMU) | 62.38% | 77.25% | 53.26% | 98 | 48 | 28 | 4832 | 125 | 678 | 1702 |
GoMatching++ | 58.36% | 74.92% | 67.15% | 120 | 33 | 21 | 5252 | 155 | 1366 | 1252 |
GOCR Offline | 56.92% | 73.38% | 69.22% | 99 | 37 | 38 | 4605 | 82 | 815 | 1972 |
HIK_OCR | 56.19% | 75.35% | 64.32% | 83 | 48 | 43 | 4293 | 135 | 551 | 2231 |
h&h_lab | 53.94% | 74.18% | 47.22% | 78 | 53 | 43 | 4051 | 106 | 459 | 2502 |
TA-VTT | 52.14% | 70.83% | 51.52% | 72 | 50 | 52 | 4015 | 40 | 543 | 2604 |
GOCR | 49.69% | 72.71% | 66.95% | 104 | 45 | 25 | 4872 | 146 | 1563 | 1641 |
Semantic-Aware Video Text Detection | 48.40% | 70.72% | 56.23% | 62 | 50 | 62 | 3678 | 34 | 455 | 2947 |
LOGO | 47.26% | 66.40% | 61.81% | 75 | 58 | 41 | 4126 | 94 | 979 | 2439 |
VideoTextSCM | 43.63% | 76.36% | 46.94% | 76 | 52 | 46 | 4011 | 39 | 1106 | 2609 |
TransDETR | 35.67% | 65.28% | 61.84% | 60 | 57 | 57 | 3659 | 6 | 1284 | 2994 |
SRC-B-TextProcessingLab | 34.15% | 73.30% | 39.13% | 31 | 60 | 83 | 2516 | 130 | 242 | 4013 |
TransVTSpotter | 27.81% | 64.77% | 43.14% | 38 | 70 | 66 | 2932 | 109 | 1080 | 3618 |
USTB_TexVideo | 25.98% | 76.87% | 35.89% | 20 | 77 | 77 | 2203 | 76 | 473 | 4380 |
Megvii-Image++ | 25.05% | 65.28% | 46.55% | 16 | 78 | 80 | 2640 | 24 | 972 | 3995 |
StradVision-1 | 23.26% | 74.73% | 40.33% | 21 | 55 | 98 | 2064 | 76 | 515 | 4519 |
AJOU | 23.13% | 73.60% | 41.89% | 29 | 49 | 96 | 2212 | 49 | 672 | 4398 |
USTB_TexVideo II-1 | 17.19% | 73.74% | 43.13% | 18 | 77 | 79 | 2382 | 45 | 1237 | 4232 |
USTB_TexVideo II-2 | 17.03% | 78.57% | 23.89% | 5 | 53 | 116 | 1259 | 76 | 125 | 5324 |
RTST Lucas-Kanade-2 (RealTimeSceneText_LucasKanade_v2) | -38.31% | 71.85% | 3.86% | 8 | 51 | 115 | 256 | 1199 | 2807 | 5204 |