GNN_SDT: Joint Object Detection and Multi-Object Tracking with Graph Neural Networks

MOT20-04


Benchmark:

Short name:

GNN_SDT

Description:

Reference:

Y. Wang, X. Weng, K. Kitani. Joint Detection and Multi-Object Tracking with Graph Neural Networks. In arXiv, 2020.

Last submitted:

October 27, 2020 (1 month ago)

Published:

October 31, 2020 at 07:29:49 CET

Submissions:

1

Project page / code:

n/a

Open source:

No

Hardware:

Titan Xp

Runtime:

1.2 Hz

Benchmark performance:

Sequence AP MODA MODP FAF TP FP FN Recall Precision F1
MOT20Det0.8179.380.07.1304,23631,67739,28888.690.689.6

Detailed performance:

Sequence AP MODA MODP FAF TP FP FN Recall Precision F1
MOT20-040.9087.680.04.9212,16910,12818,56092.095.493.7
MOT20-060.7162.879.69.850,0049,86713,88578.383.580.8
MOT20-070.9084.182.03.115,4991,79579995.189.692.3
MOT20-080.7751.179.712.326,5649,8876,04481.572.976.9

Raw data: