Challenge and Dataset on Large-scale Human-centric Video Analysis in Complex Events (HiEve) |
JDE(baseline)
8000
1
Benchmark
performance:
MOTA | w_MOTA | IDF1 | MT | ML | FP | FN | ID_Sw | ID_Sw_DT | Frag | MOTP |
---|---|---|---|---|---|---|---|---|---|---|
33.1180 | 27.7762 | 36.0194 | 15.1102 | 24.1343 | 9526 | 33327 | 3747 | 93 | 3605 | 72.2680 |
Detailed
performance:
Video ID | MOTA | w_MOTA | IDF1 | MT | ML | FP | FN | ID_Sw | ID_Sw_DT | Frag | MOTP |
---|---|---|---|---|---|---|---|---|---|---|---|
20 | 55.7670 | 55.0960 | 51.4644 | 44.8980 | 14.2857 | 1920 | 2972 | 385 | 2 | 433 | 73.5555 |
21 | 12.0638 | 8.0638 | 26.2880 | 3.3333 | 40.0000 | 161 | 653 | 68 | 1 | 55 | 67.1577 |
22 | 10.9303 | 4.3439 | 18.9646 | 7.7670 | 20.3883 | 1633 | 6019 | 994 | 16 | 844 | 67.5036 |
23 | 67.7966 | 62.4359 | 35.0101 | 50.0000 | 14.2857 | 128 | 1184 | 132 | 6 | 159 | 76.2489 |
24 | 3.1196 | -9.3990 | 15.4358 | 3.0395 | 46.2006 | 1877 | 10405 | 730 | 42 | 568 | 66.5961 |
25 | 24.0613 | 18.7955 | 41.9511 | 0.0000 | 2.8736 | 911 | 3358 | 342 | 8 | 250 | 67.1288 |
26 | 47.6075 | 45.4575 | 41.0013 | 17.6471 | 23.5294 | 272 | 1600 | 77 | 2 | 135 | 74.8162 |
27 | 64.8101 | 60.0857 | 42.6268 | 56.4516 | 3.2258 | 361 | 1097 | 330 | 6 | 356 | 77.9453 |
28 | 18.0813 | 10.1855 | 28.6607 | 0.0000 | 30.0000 | 661 | 1247 | 167 | 5 | 154 | 66.1193 |
29 | 31.3813 | 29.5771 | 36.9936 | 32.0000 | 20.0000 | 442 | 991 | 102 | 1 | 124 | 73.0168 |
30 | 47.6551 | 47.6551 | 43.2863 | 22.2222 | 2.2222 | 86 | 790 | 162 | 0 | 145 | 73.8656 |
31 | 65.9710 | 65.9710 | 67.0515 | 71.1111 | 4.4444 | 212 | 462 | 76 | 0 | 108 | 75.7653 |
32 | 32.0794 | 29.0565 | 39.4243 | 20.0000 | 27.5000 | 862 | 2549 | 182 | 4 | 274 | 71.0839 |