Challenge and Dataset on Large-scale Human-centric Video Analysis in Complex Events (HiEve) |
ablation for sqga
2400
1
Benchmark
performance:
MOTA | w_MOTA | IDF1 | MT | ML | FP | FN | ID_Sw | ID_Sw_DT | Frag | MOTP |
---|---|---|---|---|---|---|---|---|---|---|
28.7348 | 24.1397 | 35.2481 | 14.5855 | 48.6884 | 9017 | 39096 | 1541 | 80 | 2033 | 74.1055 |
Detailed
performance:
Video ID | MOTA | w_MOTA | IDF1 | MT | ML | FP | FN | ID_Sw | ID_Sw_DT | Frag | MOTP |
---|---|---|---|---|---|---|---|---|---|---|---|
20 | 31.0729 | 30.7374 | 47.5224 | 40.8163 | 32.6531 | 3897 | 4206 | 120 | 1 | 209 | 77.4335 |
21 | 4.8853 | 0.8853 | 19.7665 | 0.0000 | 70.0000 | 104 | 825 | 25 | 1 | 43 | 65.2609 |
22 | 17.5028 | 11.3281 | 17.7778 | 3.8835 | 45.6311 | 384 | 7198 | 426 | 15 | 497 | 69.3240 |
23 | 54.8394 | 49.4787 | 31.3247 | 57.1429 | 14.2857 | 792 | 1147 | 86 | 6 | 127 | 73.3657 |
24 | 7.7880 | -1.4519 | 14.8322 | 0.6079 | 71.1246 | 353 | 11870 | 162 | 31 | 212 | 70.3122 |
25 | 4.4631 | -0.8027 | 24.3436 | 0.0000 | 59.7701 | 731 | 5029 | 41 | 8 | 131 | 70.6441 |
26 | 48.5484 | 46.3984 | 40.6359 | 29.4118 | 23.5294 | 220 | 1621 | 73 | 2 | 101 | 73.7496 |
27 | 69.6516 | 64.1398 | 45.9184 | 66.1290 | 6.4516 | 267 | 1021 | 254 | 7 | 231 | 77.4301 |
28 | 0.3948 | -10.6593 | 24.3024 | 10.0000 | 50.0000 | 955 | 1470 | 98 | 7 | 119 | 64.5371 |
29 | 41.8865 | 40.0823 | 45.7338 | 36.0000 | 20.0000 | 441 | 813 | 46 | 1 | 89 | 73.8143 |
30 | 40.5951 | 40.5951 | 47.8845 | 15.5556 | 4.4444 | 59 | 1047 | 72 | 0 | 85 | 75.4125 |
31 | 68.7840 | 68.7840 | 62.7414 | 77.7778 | 6.6667 | 235 | 397 | 56 | 0 | 41 | 76.7297 |
32 | 41.1531 | 40.3974 | 47.0885 | 15.0000 | 30.0000 | 579 | 2452 | 82 | 1 | 148 | 71.1931 |