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


Short Name: TestOnly
Complete name: SiamMOT (DLA-34 Public)
Description:

n/a

Runtime:

n /a

Submissions:

7

Benchmark
performance:

MOTA w_MOTA IDF1 MT ML FP FN ID_Sw ID_Sw_DT Frag MOTP
51.4546 46.2852 47.9070 25.8132 26.1280 3509 28667 1648 90 1866 77.7450

Detailed
performance:


Video ID MOTA w_MOTA IDF1 MT ML FP FN ID_Sw ID_Sw_DT Frag MOTP
20 76.5214 74.1728 62.3334 79.5918 4.0816 1117 1561 123 7 131 81.2285
21 30.6082 26.6082 42.9161 6.6667 36.6667 56 608 32 1 39 68.7719
22 24.7450 18.9819 22.6427 8.7379 33.0097 230 6748 327 14 437 72.8090
23 79.4603 74.0996 49.6008 78.5714 14.2857 63 765 93 6 74 81.0743
24 17.5936 6.2672 23.2113 5.7751 52.2796 422 10344 302 38 305 72.4295
25 56.9993 52.3918 70.4099 13.7931 1.7241 315 2236 60 7 141 72.2659
26 59.9462 57.7962 45.6825 58.8235 17.6471 223 1201 66 2 108 77.8335
27 72.4857 66.9739 42.0897 70.9677 4.8387 205 892 301 7 257 78.5878
28 48.6775 40.7817 46.5510 40.0000 20.0000 381 837 82 5 99 72.6810
29 50.7376 48.9334 45.1676 40.0000 12.0000 333 720 49 1 65 75.9661
30 61.5229 61.5229 62.3675 42.2222 2.2222 52 622 89 0 70 79.9656
31 83.4392 83.4392 70.3634 88.8889 4.4444 67 237 61 0 43 80.1950
32 62.1172 60.6058 60.7630 27.5000 22.5000 45 1896 63 2 97 79.7391