DMAN_16: Online MOT with Dual Matching Attention Networks
MOT16-01
Benchmark:
MOT16 |
Short name:
DMAN_16
Detector:
Public
Description:
n/a
Reference:
J. Zhu, H. Yang, N. Liu, M. Kim, W. Zhang, M. Yang. Online Multi-Object Tracking with Dual Matching Attention Networks. In ECCV, 2018.
Last submitted:
November 11, 2017 (3 years ago)
Published:
September 11, 2018 at 07:22:21 CET
Submissions:
2
Project page / code:
Open source:
Yes
Hardware:
2.4 GHZ, 1 Core
Runtime:
0.3 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 | 46.1 | 54.8 | 40.3 | 132 (17.4) | 324 (42.7) | 7,909 | 89,874 | 50.7 | 92.1 | 44.3 | 36.9 | 47.6 | 71.9 | 39.1 | 71.1 | 77.5 | 1.3 | 532 (10.5) | 1,616 (31.9) |
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 | 37.0 | 48.7 | 33.8 | 5 | 10 | 199 | 3,814 | 40.4 | 92.8 | 40.6 | 28.2 | 48.6 | 61.9 | 29.5 | 67.8 | 75.0 | 0.4 | 13 | 72 |
| MOT16-03 | 53.5 | 59.3 | 43.3 | 37 | 30 | 4,385 | 44,051 | 57.9 | 93.2 | 44.8 | 42.1 | 47.6 | 72.3 | 44.6 | 71.9 | 77.5 | 2.9 | 192 | 842 |
| MOT16-06 | 47.4 | 55.8 | 40.9 | 41 | 101 | 566 | 5,377 | 53.4 | 91.6 | 44.6 | 37.9 | 50.9 | 66.2 | 40.4 | 69.3 | 76.4 | 0.5 | 130 | 242 |
| MOT16-07 | 42.8 | 51.6 | 37.1 | 9 | 18 | 576 | 8,709 | 46.6 | 93.0 | 41.5 | 33.4 | 44.0 | 73.5 | 35.1 | 70.0 | 76.5 | 1.2 | 59 | 148 |
| MOT16-08 | 32.5 | 44.3 | 36.3 | 14 | 24 | 708 | 10,539 | 37.0 | 89.7 | 45.6 | 29.0 | 49.5 | 73.0 | 30.6 | 74.1 | 81.0 | 1.1 | 56 | 106 |
| MOT16-12 | 41.8 | 57.0 | 42.1 | 17 | 44 | 412 | 4,400 | 47.0 | 90.4 | 51.0 | 34.7 | 54.8 | 74.0 | 37.1 | 71.5 | 79.6 | 0.5 | 16 | 38 |
| MOT16-14 | 23.6 | 38.1 | 27.5 | 9 | 97 | 1,063 | 12,984 | 29.8 | 83.8 | 35.2 | 21.6 | 37.5 | 69.9 | 23.0 | 64.7 | 76.4 | 1.4 | 66 | 168 |
Raw data:
