Benchmark:
MOT16 |
Short name:
DANetwork
Detector:
Public
Description:
Deep Association Network
Reference:
C. Ma, Y. Li, F. Yang, Z. Zhang, Y. Zhuang, H. Jia, X. Xie. Deep association: End-to-end graph-based learning for multiple object tracking with conv-graph neural network. In Proceedings of the 2019 on International Conference on Multimedia Retrieval, 2019.
Last submitted:
September 19, 2023 (1 year ago)
Published:
September 19, 2023 at 19:49:48 CET
Submissions:
1
Project page / code:
n/a
Open source:
No
Hardware:
Titian Tesla K40
Runtime:
3.0 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 | 48.6 | 49.3 | 37.7 | 100 (13.2) | 330 (43.5) | 5,853 | 87,260 | 52.1 | 94.2 | 37.0 | 38.8 | 41.8 | 68.0 | 41.0 | 74.0 | 79.6 | 1.0 | 596 (0.0) | 804 (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 | 46.0 | 60.0 | 43.1 | 5 | 9 | 37 | 3,411 | 46.7 | 98.8 | 54.7 | 34.0 | 57.0 | 76.0 | 35.0 | 74.1 | 77.5 | 0.1 | 5 | 11 |
| MOT16-03 | 57.3 | 51.8 | 39.8 | 41 | 26 | 2,610 | 41,754 | 60.1 | 96.0 | 35.8 | 44.7 | 40.2 | 66.2 | 47.2 | 75.4 | 80.0 | 1.7 | 244 | 247 |
| MOT16-06 | 31.8 | 38.4 | 29.9 | 17 | 121 | 1,222 | 6,590 | 42.9 | 80.2 | 29.9 | 30.5 | 51.4 | 44.6 | 33.4 | 62.5 | 74.9 | 1.0 | 60 | 166 |
| MOT16-07 | 45.3 | 49.9 | 36.2 | 9 | 15 | 633 | 8,222 | 49.6 | 92.8 | 36.6 | 36.2 | 39.3 | 72.8 | 38.2 | 71.4 | 77.6 | 1.3 | 75 | 147 |
| MOT16-08 | 37.0 | 41.9 | 34.3 | 9 | 24 | 226 | 10,240 | 38.8 | 96.6 | 37.7 | 31.4 | 40.6 | 78.6 | 32.4 | 80.6 | 83.5 | 0.4 | 70 | 70 |
| MOT16-12 | 39.7 | 55.1 | 42.4 | 15 | 43 | 521 | 4,462 | 46.2 | 88.0 | 52.0 | 34.8 | 54.4 | 79.4 | 37.6 | 71.6 | 80.8 | 0.6 | 22 | 33 |
| MOT16-14 | 28.0 | 39.1 | 28.0 | 4 | 92 | 604 | 12,581 | 31.9 | 90.7 | 33.5 | 23.5 | 36.4 | 67.4 | 24.6 | 69.8 | 77.3 | 0.8 | 120 | 130 |
Raw data: