Challenge and Dataset on Large-scale Human-centric Video Analysis in Complex Events (HiEve)


Short Name: JiaRen.AI
Complete name: JiaRen.AI
Description:

track1_public

Runtime:

na

Submissions:

7

Benchmark
performance:

MOTA w_MOTA IDF1 MT ML FP FN ID_Sw ID_Sw_DT Frag MOTP
47.4058 42.9256 53.4325 29.1710 29.6957 6341 29114 1190 78 1785 75.7554

Detailed
performance:


Video ID MOTA w_MOTA IDF1 MT ML FP FN ID_Sw ID_Sw_DT Frag MOTP
20 74.0989 72.4213 76.8262 73.4694 6.1224 1567 1456 67 5 96 78.5044
21 26.4207 22.4207 33.0568 3.3333 23.3333 128 567 43 1 54 65.7230
22 18.1931 12.8417 23.9082 4.8544 36.8932 804 6800 337 13 433 69.2758
23 83.7645 78.4038 58.9389 71.4286 14.2857 81 586 61 6 77 80.6441
24 9.9099 0.0738 18.0933 2.1277 61.0942 741 11177 182 33 271 68.2637
25 67.0290 61.7632 79.7881 51.1494 0.0000 565 1384 53 8 89 73.3085
26 43.0914 40.9414 38.0632 41.1765 23.5294 587 1480 50 2 102 75.4642
27 83.3694 79.4324 68.9774 77.4194 4.8387 236 502 107 5 123 77.7132
28 30.3987 25.6612 39.2707 40.0000 20.0000 798 873 92 3 118 72.0014
29 52.4810 50.6768 54.5499 44.0000 16.0000 319 683 61 1 93 74.4544
30 60.3631 60.3631 66.9770 31.1111 4.4444 107 636 43 0 74 76.8243
31 77.8584 77.8584 78.2458 75.5556 4.4444 48 420 20 0 92 78.3987
32 43.5917 42.8360 49.7259 20.0000 32.5000 360 2550 74 1 163 74.8441