ITM: Individualized Tubelet Model
MOT16-12
Benchmark:
MOT20 | MOT17 | MOT16 | 2D MOT 2015 |
Short name:
ITM
Detector:
Public
Description:
Reference:
Pivot Correlation Network with Individualized Tubelets for Efficient Multi-object Tracking
Last submitted:
November 12, 2020 (2 months ago)
Published:
November 12, 2020 at 03:34:09 CET
Submissions:
1
Project page / code:
n/a
Open source:
No
Hardware:
2080Ti
Runtime:
1.1 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| MOT16 | 61.1 | 59.5 | 77.6 | 213 (28.1) | 194 (25.6) | 8,919 | 61,019 | 66.5 | 93.2 | 1.5 | 1,052 (15.8) | 1,933 (29.1) |
Detailed performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| MOT16-01 | 42.0 | 44.0 | 77.0 | 6 | 9 | 359 | 3,317 | 48.1 | 89.6 | 0.8 | 35 | 60 |
| MOT16-03 | 74.0 | 68.0 | 77.3 | 83 | 15 | 4,987 | 22,032 | 78.9 | 94.3 | 3.3 | 157 | 477 |
| MOT16-06 | 59.0 | 61.6 | 79.2 | 71 | 53 | 589 | 4,000 | 65.3 | 92.8 | 0.5 | 138 | 292 |
| MOT16-07 | 47.6 | 47.3 | 77.6 | 9 | 10 | 740 | 7,678 | 53.0 | 92.1 | 1.5 | 136 | 315 |
| MOT16-08 | 35.6 | 36.0 | 81.5 | 10 | 23 | 404 | 10,281 | 38.6 | 94.1 | 0.6 | 90 | 162 |
| MOT16-12 | 48.3 | 54.1 | 81.3 | 18 | 27 | 384 | 3,855 | 53.5 | 92.0 | 0.4 | 47 | 85 |
| MOT16-14 | 36.4 | 38.9 | 74.9 | 16 | 57 | 1,456 | 9,856 | 46.7 | 85.6 | 1.9 | 449 | 542 |
Raw data:
