DGST: Spatio-temporal graph attention based on decoupling representation

MOT16-01


Benchmark:

MOT17 | MOT16 | MOT20 |

Short name:

DGST

Detector:

Private

Description:

Reference:

Last submitted:

November 16, 2021 (2 months ago)

Published:

November 16, 2021 at 05:01:28 CET

Submissions:

1

Project page / code:

n/a

Open source:

No

Hardware:

RTX2080Ti

Runtime:

17.9 Hz

Benchmark performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT1673.875.960.7322 (42.4)124 (16.3)8,43538,52578.994.561.260.365.779.865.278.183.21.4899 (0.0)2,553 (0.0)

Detailed performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT16-0161.166.653.595522,41362.398.757.250.261.981.152.182.684.30.12596
MOT16-0388.186.169.513203,3058,95091.496.767.671.672.381.276.681.084.12.2183757
MOT16-0663.667.953.482445253,53469.493.854.452.559.278.456.776.882.70.4146264
MOT16-0763.362.949.12321,1994,64971.590.746.152.750.275.558.374.082.22.4142423
MOT16-0846.047.839.117126588,24050.892.839.639.242.573.841.776.382.41.1140390
MOT16-1255.668.852.829149762,68667.685.257.948.562.279.155.670.082.71.122152
MOT16-1445.856.440.030471,7208,05356.485.842.638.045.274.842.564.777.22.3241471

Raw data: