Short name:
AGT
Detector:
Public
Description:
graph tracking with self adapted weights.
Reference:
Alibaba DAMO Academy city-brain team
Last submitted:
August 17, 2020 (3 years ago)
Published:
July 24, 2020 at 12:51:25 CET
Submissions:
4
Project page / code:
n/a
Open source:
No
Hardware:
Tesla-V100 32 G, 2 Core
Runtime:
6.6 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 | 74.8 | 67.2 | 57.5 | 342 (45.1) | 112 (14.8) | 12,173 | 32,462 | 82.2 | 92.5 | 53.6 | 62.1 | 58.0 | 78.5 | 68.5 | 77.1 | 83.5 | 2.1 | 1,239 (15.1) | 2,647 (32.2) |
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 | 58.1 | 49.1 | 43.9 | 10 | 4 | 390 | 2,251 | 64.8 | 91.4 | 39.1 | 49.6 | 41.3 | 82.6 | 54.2 | 76.4 | 83.7 | 0.9 | 39 | 107 |
| MOT16-03 | 89.2 | 77.4 | 66.5 | 131 | 0 | 4,150 | 6,947 | 93.4 | 95.9 | 60.7 | 73.1 | 65.2 | 80.7 | 78.8 | 80.9 | 84.5 | 2.8 | 243 | 670 |
| MOT16-06 | 63.3 | 61.2 | 49.4 | 88 | 43 | 646 | 3,404 | 70.5 | 92.6 | 46.0 | 53.1 | 56.1 | 66.4 | 57.9 | 76.1 | 82.8 | 0.5 | 189 | 270 |
| MOT16-07 | 64.0 | 51.8 | 44.4 | 22 | 2 | 1,257 | 4,476 | 72.6 | 90.4 | 37.0 | 53.6 | 39.7 | 75.0 | 59.6 | 74.2 | 82.6 | 2.5 | 143 | 385 |
| MOT16-08 | 46.1 | 40.7 | 38.4 | 21 | 2 | 3,314 | 5,382 | 67.8 | 77.4 | 32.4 | 46.6 | 35.2 | 74.3 | 56.8 | 64.9 | 81.9 | 5.3 | 321 | 469 |
| MOT16-12 | 58.6 | 64.9 | 51.4 | 27 | 16 | 613 | 2,776 | 66.5 | 90.0 | 53.4 | 49.8 | 57.9 | 79.7 | 54.8 | 74.1 | 82.7 | 0.7 | 46 | 176 |
| MOT16-14 | 49.8 | 52.6 | 39.6 | 43 | 45 | 1,803 | 7,226 | 60.9 | 86.2 | 38.5 | 41.4 | 41.8 | 71.0 | 46.8 | 66.2 | 78.5 | 2.4 | 258 | 570 |
Raw data: