GNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization

TUD-Crossing


Benchmark:

Short name:

GNNMatch

Detector:

Public

Description:

Reference:

I. Papakis, A. Sarkar, A. Karpatne. GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization. In arXiv preprint arXiv:2010.00067, 2020.

Last submitted:

March 07, 2021 (6 months ago)

Published:

March 02, 2021 at 06:22:09 CET

Submissions:

4

Open source:

Yes

Hardware:

TITAN RTX

Runtime:

0.1 Hz

Benchmark performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT1546.743.235.4157 (21.8)203 (28.2)6,64325,31158.884.531.440.844.249.346.366.679.61.1820 (0.0)1,371 (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
ADL-Rundle-136.250.239.01132,5183,36863.870.239.638.745.463.449.854.877.65.048120
ADL-Rundle-348.747.739.71286464,51855.689.736.943.244.564.447.075.984.01.05461
AVG-TownCentre38.934.328.345441,1212,96858.578.922.137.240.631.543.859.076.02.5281495
ETH-Crossing46.446.939.05107445854.388.035.642.851.552.246.875.984.60.3611
ETH-Jelmoli59.647.842.0171232868373.185.034.651.066.439.259.769.482.50.71437
ETH-Linthescher49.640.337.136983824,08154.392.732.942.056.841.744.876.582.50.34288
KITTI-1650.458.937.43116265861.386.635.339.645.151.044.262.474.40.82444
KITTI-1947.447.634.09193892,36955.788.430.837.944.544.241.666.076.40.451142
PETS09-S2L248.131.524.0545004,24356.091.514.540.119.633.643.270.778.41.1263333
TUD-Crossing78.544.835.9803018683.196.822.557.738.632.261.972.277.60.12118
Venice-149.946.136.9644931,77961.085.033.840.641.656.646.564.778.91.11622

Raw data: