Fair: A simple baseline for multi-object tracking
Video not available.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Short name:
Fair
Detector:
Private
Description:
n/a
Reference:
Y. Zhang, C. Wang, X. Wang, W. Zeng, W. Liu. FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking. In arXiv preprint arXiv:2004.01888, 2020.
Last submitted:
August 02, 2020 (3 years ago)
Published:
May 16, 2020 at 05:52:27 CET
Submissions:
3
Project page / code:
Open source:
Yes
Hardware:
RTX2080ti
Runtime:
30.5 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | HOTA | MT | ML | FP | FN | Rcll | Prcn | AssA | DetA | AssRe | AssPr | DetRe | DetPr | LocA | FAF | ID Sw. | Frag |
| MOT15 | 60.6 | 64.7 | 49.3 | 343 (47.6) | 79 (11.0) | 7,854 | 15,785 | 74.3 | 85.3 | 48.1 | 50.9 | 54.3 | 72.3 | 59.0 | 67.7 | 79.9 | 1.4 | 591 (8.0) | 1,731 (23.3) |
Detailed performance:
| Sequence | MOTA | IDF1 | HOTA | MT | ML | FP | FN | Rcll | Prcn | AssA | DetA | AssRe | AssPr | DetRe | DetPr | LocA | FAF | ID Sw. | Frag |
| ADL-Rundle-1 | 41.3 | 56.5 | 43.9 | 11 | 3 | 2,271 | 3,131 | 66.4 | 73.1 | 47.6 | 41.1 | 51.6 | 71.3 | 51.8 | 57.1 | 77.8 | 4.5 | 57 | 221 |
| ADL-Rundle-3 | 53.7 | 56.4 | 44.7 | 18 | 3 | 1,152 | 3,483 | 65.7 | 85.3 | 42.3 | 47.5 | 47.1 | 71.5 | 54.0 | 70.1 | 82.0 | 1.8 | 71 | 172 |
| AVG-TownCentre | 58.9 | 73.0 | 49.1 | 110 | 22 | 1,163 | 1,680 | 76.5 | 82.5 | 50.4 | 48.3 | 59.4 | 66.1 | 56.9 | 61.4 | 75.5 | 2.6 | 98 | 312 |
| ETH-Crossing | 76.7 | 76.0 | 59.1 | 10 | 2 | 31 | 197 | 80.4 | 96.3 | 55.7 | 62.9 | 62.8 | 76.3 | 67.3 | 80.5 | 84.1 | 0.1 | 6 | 23 |
| ETH-Jelmoli | 68.7 | 77.5 | 60.0 | 34 | 1 | 456 | 325 | 87.2 | 82.9 | 60.3 | 59.8 | 67.8 | 77.0 | 72.7 | 69.1 | 83.7 | 1.0 | 12 | 59 |
| ETH-Linthescher | 70.7 | 71.8 | 56.6 | 74 | 39 | 525 | 1,986 | 77.8 | 93.0 | 54.1 | 59.4 | 60.8 | 75.8 | 64.9 | 77.6 | 83.4 | 0.4 | 109 | 196 |
| KITTI-16 | 54.7 | 68.4 | 49.3 | 7 | 1 | 314 | 432 | 74.6 | 80.2 | 48.8 | 50.1 | 57.2 | 64.6 | 59.2 | 63.6 | 77.2 | 1.5 | 25 | 56 |
| KITTI-19 | 55.9 | 70.2 | 48.5 | 31 | 2 | 1,062 | 1,238 | 76.8 | 79.4 | 48.7 | 48.7 | 57.4 | 65.7 | 59.0 | 61.0 | 76.6 | 1.0 | 58 | 202 |
| PETS09-S2L2 | 77.1 | 58.0 | 45.3 | 27 | 1 | 500 | 1,582 | 83.6 | 94.2 | 34.7 | 59.3 | 39.2 | 70.5 | 64.8 | 72.9 | 79.1 | 1.1 | 121 | 392 |
| TUD-Crossing | 88.8 | 82.5 | 61.0 | 13 | 0 | 50 | 64 | 94.2 | 95.4 | 54.8 | 68.0 | 63.4 | 66.5 | 74.0 | 74.9 | 80.3 | 0.2 | 9 | 21 |
| Venice-1 | 55.7 | 64.0 | 50.9 | 8 | 5 | 330 | 1,667 | 63.5 | 89.8 | 56.4 | 46.2 | 60.1 | 80.4 | 51.2 | 72.4 | 81.7 | 0.7 | 25 | 77 |
Raw data:
