 |
Challenge and Dataset on Large-scale Human-centric Video Analysis in Complex Events (HiEve) |
| |
Challenge and Dataset on Large-scale Human-centric Video Analysis in Complex Events (HiEve) |
Combining detection and tracking
16877
3
Benchmark
performance:
| MOTA | MOTP | Total_AP |
|---|---|---|
| 53.4193 | 51.3124 | 64.5252 |
Detailed
performance:
| Video ID | MOTA | MOTP | Total_AP |
|---|---|---|---|
| 20 | 68.6566 | 55.8622 | 81.7807 |
| 21 | 12.7004 | 23.3892 | 23.8064 |
| 22 | 0.2669 | 7.0948 | 31.1298 |
| 23 | 68.1313 | 61.6159 | 74.1394 |
| 24 | 24.2061 | 25.3523 | 47.1437 |
| 25 | 46.4963 | 67.5107 | 64.1648 |
| 26 | 47.2827 | 55.4503 | 53.9467 |
| 27 | 66.6173 | 56.0196 | 78.1348 |
| 28 | 51.1440 | 49.7192 | 57.8180 |
| 29 | 42.6900 | 51.5498 | 58.8012 |
| 30 | 53.6224 | 17.0272 | 57.1229 |
| 31 | 75.9679 | 70.7694 | 83.0574 |
| 32 | 54.0804 | 46.3417 | 55.8466 |