MHT_bLSTM6: MHT with Neural Gating using Bilinear LSTM
MOT16-01
Benchmark:
MOT16 |
Short name:
MHT_bLSTM6
Detector:
Public
Description:
n/a
Reference:
C. Kim, F. Li, J. Rehg. Multi-object Tracking with Neural Gating Using Bilinear LSTM. In ECCV, 2018.
Last submitted:
July 26, 2018 (3 years ago)
Published:
July 26, 2018 at 09:04:30 CET
Submissions:
3
Project page / code:
n/a
Open source:
No
Hardware:
Titan X GPU, 3.6GHZ CPU
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 | 42.1 | 47.8 | 36.7 | 113 (14.9) | 337 (44.4) | 11,637 | 93,172 | 48.9 | 88.5 | 37.9 | 35.7 | 42.3 | 72.2 | 38.6 | 69.8 | 79.0 | 2.0 | 753 (15.4) | 1,156 (23.6) |
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 | 27.5 | 36.5 | 28.3 | 6 | 9 | 785 | 3,813 | 40.4 | 76.7 | 29.3 | 27.5 | 35.3 | 61.6 | 30.9 | 58.7 | 75.7 | 1.7 | 39 | 63 |
| MOT16-03 | 49.4 | 53.4 | 40.2 | 32 | 30 | 7,299 | 45,264 | 56.7 | 89.0 | 39.8 | 40.9 | 42.3 | 74.5 | 44.7 | 70.1 | 79.0 | 4.9 | 300 | 532 |
| MOT16-06 | 42.2 | 45.7 | 35.3 | 39 | 106 | 1,067 | 5,507 | 52.3 | 85.0 | 34.1 | 36.8 | 56.8 | 50.6 | 40.8 | 66.3 | 78.1 | 0.9 | 91 | 132 |
| MOT16-07 | 34.9 | 41.1 | 32.0 | 4 | 24 | 497 | 10,022 | 38.6 | 92.7 | 35.5 | 29.0 | 37.5 | 73.7 | 30.3 | 72.7 | 78.5 | 1.0 | 113 | 158 |
| MOT16-08 | 33.0 | 36.7 | 31.2 | 11 | 25 | 674 | 10,447 | 37.6 | 90.3 | 33.1 | 29.4 | 36.5 | 71.6 | 31.1 | 74.7 | 81.6 | 1.1 | 87 | 111 |
| MOT16-12 | 38.8 | 49.7 | 38.8 | 13 | 40 | 706 | 4,340 | 47.7 | 84.9 | 43.0 | 35.0 | 54.5 | 66.8 | 38.5 | 68.6 | 80.0 | 0.8 | 31 | 43 |
| MOT16-14 | 21.7 | 31.0 | 23.4 | 8 | 103 | 609 | 13,779 | 25.5 | 88.5 | 28.8 | 19.1 | 30.3 | 75.2 | 19.9 | 69.3 | 78.4 | 0.8 | 92 | 117 |
Raw data:
