Challenge and Dataset on Large-scale Human-centric Video Analysis in Complex Events (HiEve) |
i just use one frame to recognize action
30
1
Benchmark
performance:
F_w_mAP | F_w_mAP_50 | F_w_mAP_60 | F_w_mAP_75 | F_mAP | F_mAP_50 | F_mAP_60 | F_mAP_75 |
---|---|---|---|---|---|---|---|
0.0340 | 0.0501 | 0.0381 | 0.0139 | 0.0523 | 0.0736 | 0.0593 | 0.0240 |
Detailed
performance:
Video ID | F_w_mAP | F_w_mAP_50 | F_w_mAP_60 | F_w_mAP_75 | F_mAP | F_mAP_50 | F_mAP_60 | F_mAP_75 |
---|---|---|---|---|---|---|---|---|
20 | 0.0119 | 0.0147 | 0.0139 | 0.0071 | 0.0099 | 0.0117 | 0.0116 | 0.0065 |
21 | 0.0124 | 0.0286 | 0.0080 | 0.0005 | 0.0129 | 0.0295 | 0.0083 | 0.0008 |
22 | 0.0467 | 0.0707 | 0.0580 | 0.0114 | 0.0525 | 0.0778 | 0.0641 | 0.0156 |
23 | 0.1700 | 0.2359 | 0.1993 | 0.0748 | 0.1956 | 0.2641 | 0.2315 | 0.0914 |
24 | 0.0343 | 0.0511 | 0.0415 | 0.0103 | 0.0400 | 0.0578 | 0.0473 | 0.0150 |
25 | 0.0004 | 0.0007 | 0.0005 | 0.0000 | 0.0004 | 0.0007 | 0.0005 | 0.0000 |
26 | 0.1125 | 0.1274 | 0.1236 | 0.0863 | 0.1193 | 0.1282 | 0.1268 | 0.1029 |
27 | 0.1400 | 0.1757 | 0.1580 | 0.0861 | 0.1676 | 0.2053 | 0.1895 | 0.1081 |
28 | 0.0282 | 0.0409 | 0.0331 | 0.0107 | 0.0485 | 0.0587 | 0.0543 | 0.0326 |
29 | 0.1170 | 0.1583 | 0.1153 | 0.0774 | 0.1247 | 0.1677 | 0.1246 | 0.0817 |
30 | 0.0589 | 0.0909 | 0.0656 | 0.0202 | 0.0606 | 0.0900 | 0.0702 | 0.0217 |
31 | 0.1531 | 0.2222 | 0.1713 | 0.0659 | 0.1652 | 0.2290 | 0.1836 | 0.0831 |
32 | 0.0069 | 0.0104 | 0.0089 | 0.0016 | 0.0082 | 0.0113 | 0.0099 | 0.0035 |