Challenge and Dataset on Large-scale Human-centric Video Analysis in Complex Events (HiEve) |
n/a
0
1
Benchmark
performance:
MOTA | w_MOTA | IDF1 | MT | ML | FP | FN | ID_Sw | ID_Sw_DT | Frag | MOTP |
---|---|---|---|---|---|---|---|---|---|---|
34.0954 | 29.5003 | 40.8907 | 15.7398 | 36.0965 | 8519 | 35506 | 1894 | 80 | 2512 | 73.5456 |
Detailed
performance:
Video ID | MOTA | w_MOTA | IDF1 | MT | ML | FP | FN | ID_Sw | ID_Sw_DT | Frag | MOTP |
---|---|---|---|---|---|---|---|---|---|---|---|
20 | 51.0394 | 50.7039 | 60.4532 | 46.9388 | 18.3673 | 2415 | 3325 | 101 | 1 | 280 | 74.9533 |
21 | 0.1994 | 0.1994 | 11.3674 | 0.0000 | 70.0000 | 100 | 892 | 9 | 0 | 15 | 61.9613 |
22 | 24.6008 | 18.8377 | 25.4808 | 7.7670 | 45.6311 | 370 | 6629 | 320 | 14 | 493 | 70.4306 |
23 | 39.4960 | 34.1353 | 39.6369 | 50.0000 | 14.2857 | 1399 | 1224 | 90 | 6 | 140 | 71.8960 |
24 | 9.5376 | -0.8946 | 17.6010 | 1.8237 | 60.7903 | 695 | 11092 | 363 | 35 | 363 | 67.0567 |
25 | 13.7846 | 8.5188 | 41.0778 | 0.0000 | 16.6667 | 1107 | 4010 | 118 | 8 | 227 | 73.7484 |
26 | 36.4247 | 34.2747 | 31.4660 | 17.6471 | 35.2941 | 161 | 2103 | 101 | 2 | 184 | 75.6174 |
27 | 67.3686 | 62.6442 | 46.8445 | 72.5806 | 4.8387 | 510 | 848 | 300 | 6 | 229 | 78.8341 |
28 | 34.3861 | 28.0695 | 42.6925 | 15.0000 | 45.0000 | 440 | 1168 | 54 | 4 | 105 | 71.7165 |
29 | 31.4707 | 29.6665 | 33.3801 | 8.0000 | 28.0000 | 262 | 1171 | 100 | 1 | 140 | 74.5134 |
30 | 49.0671 | 49.0671 | 54.9875 | 15.5556 | 0.0000 | 92 | 850 | 68 | 0 | 81 | 76.9152 |
31 | 65.8802 | 65.8802 | 55.0582 | 82.2222 | 2.2222 | 337 | 277 | 138 | 0 | 57 | 75.6742 |
32 | 49.3384 | 47.0713 | 50.2044 | 22.5000 | 25.0000 | 631 | 1917 | 132 | 3 | 198 | 69.6047 |