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


Video not available.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

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 02, 2021 (3 years ago)

Published:

July 30, 2020 at 21:33:18 CET

Submissions:

3

Open source:

Yes

Hardware:

TITAN RTX

Runtime:

0.3 Hz

Benchmark performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT1657.255.044.6174 (22.9)258 (34.0)3,90573,49359.796.543.745.851.068.148.278.081.70.7559 (9.4)847 (14.2)

Detailed performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT16-0144.041.736.0611903,47445.797.037.434.844.464.636.276.980.70.21928
MOT16-0368.463.750.661192,09030,87270.597.247.953.753.472.956.778.381.61.4117230
MOT16-0654.733.432.060805524,56460.492.722.246.355.529.649.776.282.40.5107130
MOT16-0746.746.737.19142588,36348.896.937.337.342.361.539.077.481.30.571140
MOT16-0835.337.732.992424110,54037.096.335.730.540.970.531.581.884.50.45067
MOT16-1248.555.645.717391204,13450.297.252.140.358.772.242.081.484.00.12030
MOT16-1433.638.829.6127155411,54637.592.631.428.136.959.129.572.979.70.7175222

Raw data: