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

Short Name: SMOT1
Complete name: SMOT1
Description:

n/a

Runtime:

n/a

Submissions:

3

Benchmark
performance:

MOTA w_MOTA IDF1 MT ML FP FN ID_Sw ID_Sw_DT Frag MOTP
46.2835 41.6884 40.1667 17.4187 34.7324 1162 34469 1796 80 1636 77.6572

Detailed
performance:

Video ID MOTA w_MOTA IDF1 MT ML FP FN ID_Sw ID_Sw_DT Frag MOTP
20 73.4451 71.7675 60.0667 53.0612 14.2857 85 2965 118 5 119 80.4828
21 24.6261 20.6261 36.7223 3.3333 43.3333 18 706 32 1 22 70.6627
22 21.3866 15.6235 17.7164 8.7379 44.6602 148 7099 384 14 366 74.0723
23 71.4095 66.0488 37.7177 42.8571 14.2857 147 1018 117 6 112 75.6553
24 14.0868 5.1449 18.7758 3.3435 63.8298 100 11229 210 30 166 73.4570
25 49.7200 44.4542 60.9817 10.3448 6.8966 174 2784 95 8 116 74.5844
26 46.6398 44.4898 30.6469 17.6471 29.4118 50 1832 103 2 108 78.5422
27 65.5580 60.8336 34.8720 46.7742 8.0645 104 1319 327 6 268 77.9254
28 38.7683 29.2934 25.8972 10.0000 40.0000 255 1197 99 6 103 71.6916
29 45.8203 44.0161 36.5566 16.0000 36.0000 35 1117 60 1 56 77.8845
30 50.7312 50.7312 52.9087 20.0000 2.2222 14 903 60 0 50 81.6868
31 79.2196 79.2196 58.9220 82.2222 4.4444 12 357 89 0 62 80.3671
32 60.9641 60.2084 49.6015 27.5000 27.5000 20 1943 102 1 88 80.0665