Benchmark:
MOTS |
Short name:
EMNT
Description:
S. Wang, H. Sheng, D. Yang, Y. Zhang, Y. Wu and S. Wang, "Extendable Multiple Nodes Recurrent Tracking Framework with RTU++," in IEEE Transactions on Image Processing, 2022, doi: 10.1109/TIP.2022.3192706.
Reference:
S. Wang, H. Sheng, D. Yang, Y. Zhang, Y. Wu and S. Wang, "Extendable Multiple Nodes Recurrent Tracking Framework with RTU++," in IEEE Transactions on Image Processing, 2022, doi: 10.1109/TIP.2022.3192706.
Last submitted:
May 19, 2022 (2 years ago)
Published:
June 06, 2022 at 10:26:12 CET
Submissions:
2
Project page / code:
Open source:
No
Hardware:
R9-5900X RTX3090
Runtime:
11.7 Hz
Benchmark performance:
Sequence | sMOTSA | IDF1 | MOTSA | MOTSP | MODSA | MT | ML | TP | FP | FN | Rcll | Prcn | ID Sw. | Frag |
MOTS | 70.0 | 77.0 | 83.7 | 84.1 | 84.5 | 234 (71.3) | 13 (4.0) | 27,943 | 666 | 4,326 | 86.6 | 97.7 | 261 (301.4) | 618 (713.7) |
Detailed performance:
Sequence | sMOTSA | IDF1 | MOTSA | MOTSP | MODSA | MT | ML | TP | FP | FN | Rcll | Prcn | ID Sw. | Frag |
MOTS20-01 | 69.5 | 85.1 | 84.5 | 82.6 | 84.7 | 8 | 0 | 2,683 | 51 | 423 | 86.4 | 98.1 | 7 | 55 |
MOTS20-06 | 74.9 | 72.0 | 88.5 | 85.2 | 89.8 | 147 | 5 | 9,013 | 197 | 801 | 91.8 | 97.9 | 130 | 239 |
MOTS20-07 | 65.4 | 76.3 | 80.4 | 82.0 | 81.1 | 35 | 4 | 10,692 | 253 | 2,186 | 83.0 | 97.7 | 87 | 229 |
MOTS20-12 | 71.9 | 82.3 | 82.7 | 87.4 | 83.3 | 44 | 4 | 5,555 | 165 | 916 | 85.8 | 97.1 | 37 | 95 |
Raw data: