QuadMOT16: Multi-Object Tracking with Quadruplet Convolutional Neural Networks
MOT16-01
Benchmark:
MOT16 |
Short name:
QuadMOT16
Detector:
Public
Description:
n/a
Reference:
J. Son, M. Baek, M. Cho, B. Han. Multi-Object Tracking with Quadruplet Convolutional Neural Networks. In CVPR, 2017.
Last submitted:
November 22, 2016 (8 years ago)
Published:
November 23, 2016 at 04:26:44 CET
Submissions:
1
Project page / code:
n/a
Open source:
No
Hardware:
3 GHZ, 1 Core, TITAN X
Runtime:
1.8 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 | 44.1 | 38.3 | 30.9 | 111 (14.6) | 341 (44.9) | 6,388 | 94,775 | 48.0 | 93.2 | 26.7 | 35.8 | 27.9 | 77.4 | 37.9 | 73.5 | 79.8 | 1.1 | 745 (15.5) | 1,096 (22.8) |
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 | 30.8 | 31.3 | 26.5 | 4 | 11 | 119 | 4,278 | 33.1 | 94.7 | 28.8 | 24.5 | 30.3 | 72.7 | 25.4 | 72.7 | 78.7 | 0.3 | 26 | 43 |
| MOT16-03 | 51.0 | 37.1 | 30.1 | 27 | 33 | 3,125 | 47,704 | 54.4 | 94.8 | 22.5 | 40.4 | 23.3 | 77.5 | 42.7 | 74.5 | 79.9 | 2.1 | 397 | 561 |
| MOT16-06 | 49.2 | 57.2 | 43.8 | 44 | 116 | 260 | 5,549 | 51.9 | 95.8 | 49.1 | 39.2 | 51.9 | 78.0 | 41.0 | 75.8 | 80.0 | 0.2 | 51 | 82 |
| MOT16-07 | 41.9 | 38.1 | 30.9 | 7 | 16 | 768 | 8,626 | 47.2 | 90.9 | 27.0 | 35.6 | 28.3 | 77.1 | 37.9 | 73.1 | 80.1 | 1.5 | 84 | 108 |
| MOT16-08 | 29.9 | 34.7 | 28.5 | 7 | 26 | 582 | 11,072 | 33.8 | 90.7 | 30.8 | 26.5 | 32.2 | 80.2 | 27.8 | 74.5 | 81.6 | 0.9 | 74 | 84 |
| MOT16-12 | 38.0 | 47.7 | 36.9 | 13 | 48 | 516 | 4,599 | 44.6 | 87.7 | 42.4 | 32.2 | 44.3 | 77.1 | 34.9 | 68.7 | 79.3 | 0.6 | 28 | 32 |
| MOT16-14 | 24.0 | 33.5 | 25.3 | 9 | 91 | 1,018 | 12,947 | 29.9 | 84.5 | 29.5 | 21.8 | 30.9 | 73.5 | 23.2 | 65.5 | 77.1 | 1.4 | 85 | 186 |
Raw data:
