MPNTrackSeg: Multi-Object Tracking and Segmentation via Neural Message Passing
MOTS20-12
Benchmark:
MOTS |
Short name:
MPNTrackSeg
Description:
Reference:
G. Bras'o, O. Cetintas, L. Leal-Taix'e. Multi-Object Tracking and Segmentation Via Neural Message Passing. In International Journal of Computer Vision, 2022.
Last submitted:
June 30, 2022 (2 years ago)
Published:
June 30, 2022 at 14:53:12 CET
Submissions:
1
Project page / code:
Open source:
No
Hardware:
RTX 8000
Runtime:
2.3 Hz
Benchmark performance:
| Sequence | sMOTSA | IDF1 | MOTSA | MOTSP | MODSA | MT | ML | TP | FP | FN | Rcll | Prcn | ID Sw. | Frag |
| MOTS | 58.6 | 68.8 | 73.7 | 80.6 | 74.3 | 207 (63.1) | 26 (7.9) | 25,036 | 1,059 | 7,233 | 77.6 | 95.9 | 202 (260.4) | 635 (818.5) |
Detailed performance:
| Sequence | sMOTSA | IDF1 | MOTSA | MOTSP | MODSA | MT | ML | TP | FP | FN | Rcll | Prcn | ID Sw. | Frag |
| MOTS20-01 | 60.6 | 75.9 | 79.3 | 77.6 | 79.7 | 8 | 0 | 2,591 | 116 | 515 | 83.4 | 95.7 | 12 | 64 |
| MOTS20-06 | 70.1 | 69.8 | 86.5 | 81.9 | 87.4 | 141 | 5 | 8,926 | 344 | 888 | 91.0 | 96.3 | 91 | 241 |
| MOTS20-07 | 46.5 | 60.4 | 60.3 | 77.7 | 60.7 | 14 | 17 | 7,966 | 144 | 4,912 | 61.9 | 98.2 | 59 | 235 |
| MOTS20-12 | 64.6 | 78.0 | 78.2 | 84.2 | 78.8 | 44 | 4 | 5,553 | 455 | 918 | 85.8 | 92.4 | 40 | 95 |
Raw data:
