Challenge and Dataset on Large-scale Human-centric Video Analysis in Complex Events (HiEve) |
n
10000
1
Benchmark
performance:
MOTA | w_MOTA | IDF1 | MT | ML | FP | FN | ID_Sw | ID_Sw_DT | Frag | MOTP |
---|---|---|---|---|---|---|---|---|---|---|
38.0610 | 33.0064 | 43.1004 | 18.0483 | 30.3253 | 10009 | 30947 | 2200 | 88 | 2797 | 72.1505 |
Detailed
performance:
Video ID | MOTA | w_MOTA | IDF1 | MT | ML | FP | FN | ID_Sw | ID_Sw_DT | Frag | MOTP |
---|---|---|---|---|---|---|---|---|---|---|---|
20 | 67.9966 | 66.6545 | 63.4990 | 57.1429 | 8.1633 | 1767 | 1929 | 122 | 4 | 195 | 75.1346 |
21 | -1.8943 | -5.8943 | 26.4108 | 0.0000 | 23.3333 | 365 | 599 | 58 | 1 | 71 | 63.8655 |
22 | 11.1363 | 4.9616 | 16.6970 | 2.9126 | 29.1262 | 1627 | 6188 | 811 | 15 | 822 | 64.9835 |
23 | 77.1632 | 71.8025 | 48.6109 | 57.1429 | 14.2857 | 137 | 790 | 97 | 6 | 130 | 73.3409 |
24 | 6.3286 | -4.6997 | 17.7530 | 2.4316 | 62.6140 | 1075 | 11230 | 276 | 37 | 335 | 63.5948 |
25 | 50.0659 | 44.8001 | 68.2424 | 14.9425 | 0.0000 | 1011 | 1901 | 120 | 8 | 143 | 76.2065 |
26 | 25.1613 | 23.0113 | 27.3040 | 29.4118 | 29.4118 | 979 | 1724 | 81 | 2 | 158 | 71.0296 |
27 | 74.0012 | 68.4894 | 53.0463 | 59.6774 | 3.2258 | 254 | 847 | 220 | 7 | 295 | 74.9993 |
28 | 0.5922 | -8.8827 | 30.9439 | 25.0000 | 30.0000 | 1497 | 927 | 94 | 6 | 107 | 70.5528 |
29 | 31.2919 | 29.4877 | 35.6445 | 20.0000 | 28.0000 | 540 | 918 | 79 | 1 | 119 | 71.5593 |
30 | 46.1422 | 46.1422 | 58.4606 | 20.0000 | 4.4444 | 216 | 778 | 74 | 0 | 127 | 69.1644 |
31 | 68.8748 | 68.8748 | 62.9864 | 66.6667 | 4.4444 | 172 | 468 | 46 | 0 | 81 | 73.0266 |
32 | 40.6616 | 39.9059 | 44.1393 | 20.0000 | 40.0000 | 369 | 2648 | 122 | 1 | 214 | 69.0613 |