Benchmark:
MOT15 |
Short name:
AM
Detector:
Public
Description:
n/a
Reference:
Q. Chu, W. Ouyang, H. Li, X. Wang, B. Liu, N. Yu. Online Multi-object Tracking Using CNN-Based Single Object Tracker with Spatial-Temporal Attention Mechanism. In 2017 IEEE International Conference on Computer Vision (ICCV), 2017.
Last submitted:
March 17, 2017 (7 years ago)
Published:
August 13, 2017 at 15:24:27 CET
Submissions:
2
Project page / code:
n/a
Open source:
No
Hardware:
2.4 GHZ, 1 Core, TITAN X
Runtime:
0.5 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | HOTA | MT | ML | FP | FN | Rcll | Prcn | AssA | DetA | AssRe | AssPr | DetRe | DetPr | LocA | FAF | ID Sw. | Frag |
| MOT15 | 34.3 | 48.3 | 34.5 | 82 (11.4) | 313 (43.4) | 5,154 | 34,848 | 43.3 | 83.8 | 39.5 | 30.4 | 43.2 | 69.0 | 32.9 | 63.6 | 74.8 | 0.9 | 348 (8.0) | 1,463 (33.8) |
Detailed performance:
| Sequence | MOTA | IDF1 | HOTA | MT | ML | FP | FN | Rcll | Prcn | AssA | DetA | AssRe | AssPr | DetRe | DetPr | LocA | FAF | ID Sw. | Frag |
| ADL-Rundle-1 | 27.8 | 45.4 | 34.5 | 6 | 15 | 1,000 | 5,697 | 38.8 | 78.3 | 44.6 | 27.0 | 48.5 | 72.5 | 29.9 | 60.4 | 75.6 | 2.0 | 26 | 181 |
| ADL-Rundle-3 | 39.3 | 52.4 | 35.7 | 5 | 13 | 720 | 5,418 | 46.7 | 86.8 | 39.3 | 32.7 | 42.5 | 69.3 | 35.3 | 65.6 | 75.9 | 1.2 | 36 | 109 |
| AVG-TownCentre | 37.5 | 53.9 | 37.9 | 32 | 69 | 645 | 3,742 | 47.6 | 84.1 | 43.1 | 33.6 | 48.2 | 66.2 | 36.0 | 63.5 | 73.1 | 1.4 | 79 | 332 |
| ETH-Crossing | 26.5 | 42.3 | 27.9 | 1 | 15 | 16 | 721 | 28.1 | 94.6 | 37.1 | 21.0 | 38.7 | 74.0 | 21.6 | 72.7 | 77.9 | 0.1 | 0 | 12 |
| ETH-Jelmoli | 43.1 | 59.8 | 40.8 | 9 | 17 | 277 | 1,155 | 54.5 | 83.3 | 44.8 | 37.3 | 50.3 | 71.3 | 42.0 | 64.2 | 77.3 | 0.6 | 11 | 43 |
| ETH-Linthescher | 21.1 | 32.4 | 25.1 | 7 | 149 | 163 | 6,872 | 23.0 | 92.7 | 36.3 | 17.4 | 38.8 | 73.3 | 17.8 | 71.7 | 77.5 | 0.1 | 15 | 54 |
| KITTI-16 | 40.6 | 60.6 | 39.5 | 1 | 3 | 186 | 805 | 52.7 | 82.8 | 43.3 | 36.1 | 46.5 | 67.7 | 39.9 | 62.8 | 74.6 | 0.9 | 19 | 57 |
| KITTI-19 | 24.3 | 50.1 | 35.2 | 5 | 15 | 1,098 | 2,909 | 45.6 | 68.9 | 39.9 | 31.4 | 44.5 | 63.3 | 35.9 | 54.3 | 71.4 | 1.0 | 37 | 239 |
| PETS09-S2L2 | 47.7 | 44.3 | 31.0 | 7 | 6 | 718 | 4,206 | 56.4 | 88.3 | 25.0 | 38.7 | 27.9 | 63.6 | 41.6 | 65.2 | 73.8 | 1.6 | 115 | 356 |
| TUD-Crossing | 68.6 | 81.7 | 56.3 | 6 | 2 | 25 | 315 | 71.4 | 96.9 | 61.0 | 52.0 | 64.2 | 75.7 | 54.7 | 74.3 | 78.2 | 0.1 | 6 | 22 |
| Venice-1 | 27.3 | 47.8 | 34.7 | 3 | 9 | 306 | 3,008 | 34.1 | 83.6 | 50.4 | 23.9 | 53.4 | 72.3 | 25.7 | 63.1 | 76.0 | 0.7 | 4 | 58 |
Raw data: