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

Short Name: naive baseline
Complete name: naive baseline
Description:

naive baseline

Runtime:

na

Submissions:

5

Benchmark
performance:

MOTA w_MOTA IDF1 MT ML FP FN ID_Sw ID_Sw_DT Frag MOTP
44.3272 39.5024 47.7178 28.1217 30.6401 6582 30256 1952 84 2611 75.3840

Detailed
performance:

Video ID MOTA w_MOTA IDF1 MT ML FP FN ID_Sw ID_Sw_DT Frag MOTP
20 73.5960 71.9184 66.0948 71.4286 6.1224 1321 1751 78 5 197 78.4696
21 19.3420 15.3420 36.4796 0.0000 26.6667 163 601 45 1 58 65.8867
22 13.0215 7.2584 18.5270 7.7670 21.3592 1363 6290 790 14 769 68.0423
23 82.5379 78.0706 60.2740 64.2857 21.4286 110 610 63 5 115 80.6523
24 7.6837 -2.7485 18.3215 3.3435 61.3982 958 11162 279 35 338 68.2156
25 60.9025 55.6367 74.0372 50.0000 0.5747 884 1369 121 8 157 72.9933
26 43.9247 42.8497 37.3584 35.2941 23.5294 424 1595 67 1 144 75.3164
27 77.5044 71.2052 55.6164 70.9677 1.6129 231 716 196 8 280 77.6510
28 29.7276 21.8318 32.9938 25.0000 35.0000 566 1116 98 5 131 70.1770
29 55.0738 53.2696 54.3902 36.0000 20.0000 114 841 50 1 106 73.7571
30 36.3591 36.3591 50.0176 17.7778 40.0000 52 1183 27 0 53 77.1738
31 77.0871 77.0871 72.1432 77.7778 4.4444 65 395 45 0 97 77.7947
32 42.3251 41.5694 48.9619 27.5000 40.0000 331 2627 93 1 166 74.8959