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

MOT20-04


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:

February 23, 2021 (6 months ago)

Published:

February 23, 2021 at 15:37:20 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
MOT2054.549.040.2407 (32.8)317 (25.5)9,522223,61156.896.937.043.844.058.745.978.482.02.12,038 (35.9)2,456 (43.3)

Detailed performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT20-0474.761.949.5331543,72064,66276.498.341.659.149.063.462.179.982.41.88301,041
MOT20-0632.029.124.5311302,66686,99634.594.522.926.428.043.427.575.380.72.6676810
MOT20-0752.347.538.5312046015,16554.297.536.041.742.959.543.878.982.70.8159185
MOT20-0822.823.220.8141132,67656,78826.788.621.520.327.143.021.370.680.13.3373420

Raw data: