Benchmark:
MOT16 |
Short name:
MOT_GM_
Detector:
Public
Description:
Reference:
Y. Yoo, S. Lee, S. Bae. Effective Multi-Object Tracking via Global Object Models and Object Constraint Learning. In , .
Last submitted:
November 04, 2021 (2 years ago)
Published:
November 05, 2021 at 02:01:03 CET
Submissions:
1
Project page / code:
n/a
Open source:
No
Hardware:
NVIDIA TITAN Xp GPU, an Intel i7-8700K CPU
Runtime:
7.9 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | HOTA | MT | ML | FP | FN | Rcll | Prcn | AssA | DetA | AssRe | AssPr | DetRe | DetPr | LocA | FAF | ID Sw. | Frag |
| MOT16 | 43.2 | 51.5 | 37.9 | 68 (9.0) | 414 (54.5) | 3,481 | 99,532 | 45.4 | 96.0 | 42.5 | 33.9 | 46.2 | 70.4 | 35.3 | 74.6 | 79.0 | 0.6 | 484 (0.0) | 1,461 (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 |
| MOT16-01 | 30.1 | 40.7 | 31.2 | 3 | 12 | 46 | 4,408 | 31.1 | 97.7 | 43.2 | 22.6 | 45.5 | 74.4 | 23.2 | 73.0 | 77.4 | 0.1 | 13 | 40 |
| MOT16-03 | 56.2 | 61.3 | 43.7 | 34 | 25 | 1,139 | 44,480 | 57.5 | 98.1 | 44.8 | 42.7 | 48.3 | 72.4 | 44.5 | 76.0 | 79.4 | 0.8 | 152 | 741 |
| MOT16-06 | 25.1 | 34.5 | 28.2 | 10 | 137 | 1,069 | 7,446 | 35.5 | 79.3 | 31.2 | 26.0 | 41.4 | 49.9 | 28.2 | 63.0 | 75.8 | 0.9 | 128 | 213 |
| MOT16-07 | 27.3 | 38.2 | 29.0 | 4 | 27 | 777 | 11,010 | 32.5 | 87.2 | 35.7 | 23.9 | 38.8 | 62.1 | 25.1 | 67.3 | 75.5 | 1.6 | 82 | 229 |
| MOT16-08 | 27.9 | 34.9 | 28.9 | 5 | 31 | 138 | 11,882 | 29.0 | 97.2 | 36.2 | 23.1 | 38.7 | 71.9 | 23.7 | 79.3 | 82.3 | 0.2 | 50 | 81 |
| MOT16-12 | 39.4 | 52.7 | 39.4 | 11 | 51 | 118 | 4,895 | 41.0 | 96.6 | 49.8 | 31.2 | 53.3 | 74.5 | 32.2 | 76.0 | 79.6 | 0.1 | 16 | 31 |
| MOT16-14 | 15.3 | 23.2 | 18.1 | 1 | 131 | 194 | 15,411 | 16.6 | 94.1 | 26.2 | 12.5 | 28.9 | 60.8 | 12.8 | 72.2 | 77.8 | 0.3 | 43 | 126 |
Raw data: