ApLift: Approximate Lifted Disjoint Paths Tracker
MOT20-04
Short name:
ApLift
Detector:
Public
Description:
Reference:
A. Hornakova*, T. Kaiser*, M. Rolinek, B. Rosenhahn, P. Swoboda, R. Henschel. Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths. In International Conference on Computer Vision (ICCV), 2021.
Last submitted:
March 17, 2021 (3 years ago)
Published:
March 22, 2021 at 11:46:14 CET
Submissions:
3
Project page / code:
Open source:
No
Hardware:
5 GHZ 8 Core
Runtime:
0.4 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | HOTA | MT | ML | FP | FN | Rcll | Prcn | AssA | DetA | AssRe | AssPr | DetRe | DetPr | LocA | FAF | ID Sw. | Frag |
| MOT20 | 58.9 | 56.5 | 46.6 | 513 (41.3) | 264 (21.3) | 17,739 | 192,736 | 62.8 | 94.8 | 45.2 | 48.2 | 48.1 | 76.8 | 51.3 | 77.5 | 82.2 | 4.0 | 2,241 (0.0) | 2,112 (0.0) |
Detailed performance:
| Sequence | MOTA | IDF1 | HOTA | MT | ML | FP | FN | Rcll | Prcn | AssA | DetA | AssRe | AssPr | DetRe | DetPr | LocA | FAF | ID Sw. | Frag |
| MOT20-04 | 79.3 | 68.8 | 56.6 | 412 | 40 | 8,315 | 47,364 | 82.7 | 96.5 | 50.5 | 63.7 | 53.7 | 78.8 | 67.9 | 79.2 | 82.7 | 4.0 | 968 | 840 |
| MOT20-06 | 36.1 | 36.8 | 30.1 | 41 | 111 | 4,786 | 79,313 | 40.3 | 91.8 | 29.6 | 30.8 | 31.5 | 71.4 | 32.5 | 74.1 | 80.6 | 4.7 | 740 | 744 |
| MOT20-07 | 56.9 | 54.7 | 44.0 | 40 | 15 | 936 | 13,135 | 60.3 | 95.5 | 42.2 | 46.4 | 45.3 | 75.9 | 49.2 | 78.0 | 82.2 | 1.6 | 194 | 195 |
| MOT20-08 | 26.5 | 33.8 | 27.6 | 20 | 98 | 3,702 | 52,924 | 31.7 | 86.9 | 31.8 | 24.1 | 34.3 | 70.0 | 25.5 | 70.0 | 80.1 | 4.6 | 339 | 333 |
Raw data:
