Benchmark:
Short name:
ReMOTS
Description:
n/a
Reference:
F. Yang, X. Chang, C. Dang, Z. Zheng, S. Sakti, S. Nakamura, Y. Wu. ReMOTS: Self-Supervised Refining Multi-Object Tracking and Segmentation. In , 2020.
Last submitted:
May 30, 2020 (3 years ago)
Published:
May 18, 2020 at 15:22:38 CET
Submissions:
3
Project page / code:
n/a
Open source:
No
Hardware:
1080ti, 3Ghz
Runtime:
0.3 Hz
Benchmark performance:
| Sequence | sMOTSA | IDF1 | MOTSA | MOTSP | MODSA | MT | ML | TP | FP | FN | Rcll | Prcn | ID Sw. | Frag |
| CVPR 2020 MOTS Challenge | 69.9 | 75.0 | 83.9 | 84.0 | 85.1 | 248 (75.6) | 12 (3.7) | 28,270 | 819 | 3,999 | 87.6 | 97.2 | 388 (442.9) | 621 (708.8) |
Detailed performance:
| Sequence | sMOTSA | IDF1 | MOTSA | MOTSP | MODSA | MT | ML | TP | FP | FN | Rcll | Prcn | ID Sw. | Frag |
| MOTS20-01 | 68.5 | 81.9 | 83.9 | 82.5 | 84.8 | 8 | 0 | 2,723 | 88 | 383 | 87.7 | 96.9 | 30 | 56 |
| MOTS20-06 | 74.9 | 76.8 | 88.8 | 85.0 | 90.6 | 156 | 4 | 9,129 | 240 | 685 | 93.0 | 97.4 | 173 | 238 |
| MOTS20-07 | 65.4 | 68.3 | 80.6 | 81.9 | 81.6 | 36 | 4 | 10,798 | 294 | 2,080 | 83.8 | 97.3 | 127 | 236 |
| MOTS20-12 | 71.8 | 82.0 | 82.9 | 87.2 | 83.8 | 48 | 4 | 5,620 | 197 | 851 | 86.8 | 96.6 | 58 | 91 |
Raw data: