Challenge and Dataset on Large-scale Human-centric Video Analysis in Complex Events (HiEve) |
fine training on HIE20
30
2
Benchmark
performance:
MOTA | w_MOTA | IDF1 | MT | ML | FP | FN | ID_Sw | ID_Sw_DT | Frag | MOTP |
---|---|---|---|---|---|---|---|---|---|---|
48.6559 | 44.1757 | 51.4561 | 20.4617 | 33.5782 | 2366 | 31933 | 1475 | 78 | 2341 | 76.7313 |
Detailed
performance:
Video ID | MOTA | w_MOTA | IDF1 | MT | ML | FP | FN | ID_Sw | ID_Sw_DT | Frag | MOTP |
---|---|---|---|---|---|---|---|---|---|---|---|
20 | 74.1241 | 72.7820 | 70.4672 | 55.1020 | 12.2449 | 698 | 2298 | 91 | 4 | 259 | 76.9992 |
21 | 7.4776 | 3.4776 | 18.3230 | 0.0000 | 56.6667 | 82 | 800 | 46 | 1 | 65 | 66.1770 |
22 | 20.3049 | 15.3651 | 22.6465 | 2.9126 | 51.4563 | 139 | 7348 | 249 | 12 | 406 | 74.8875 |
23 | 88.4255 | 83.0648 | 63.8047 | 71.4286 | 14.2857 | 65 | 391 | 63 | 6 | 82 | 79.3079 |
24 | 12.7094 | 3.4695 | 18.8009 | 1.2158 | 64.4377 | 195 | 11345 | 184 | 31 | 270 | 74.1095 |
25 | 48.3366 | 43.0708 | 57.6835 | 16.6667 | 0.0000 | 555 | 2235 | 347 | 8 | 419 | 70.9760 |
26 | 57.2043 | 55.0543 | 45.0082 | 41.1765 | 23.5294 | 79 | 1449 | 64 | 2 | 125 | 79.8417 |
27 | 80.4960 | 75.7716 | 73.4398 | 77.4194 | 4.8387 | 193 | 709 | 89 | 6 | 166 | 79.7858 |
28 | 51.4015 | 41.9266 | 49.9158 | 25.0000 | 20.0000 | 126 | 1033 | 72 | 6 | 124 | 72.1946 |
29 | 49.1283 | 47.3241 | 46.9452 | 32.0000 | 24.0000 | 67 | 1022 | 49 | 1 | 106 | 77.8527 |
30 | 52.3449 | 52.3449 | 60.1403 | 17.7778 | 2.2222 | 24 | 854 | 67 | 0 | 80 | 77.3932 |
31 | 82.3503 | 82.3503 | 86.1472 | 82.2222 | 2.2222 | 50 | 300 | 39 | 0 | 66 | 76.9669 |
32 | 55.4442 | 54.6885 | 50.3050 | 22.5000 | 27.5000 | 93 | 2149 | 115 | 1 | 173 | 78.2424 |