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

MOT17-01


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 07:29:42 CET

Submissions:

2

Project page / code:

n/a

Open source:

No

Hardware:

Titan Xp

Runtime:

5,919.0 Hz

Benchmark performance:

Sequence AP MODA MODP FAF TP FP FN Recall Precision F1
MOT17Det0.8978.181.32.4103,89514,39710,66990.787.889.2

Detailed performance:

Sequence AP MODA MODP FAF TP FP FN Recall Precision F1
MOT17-010.7263.982.80.93,0453851,12173.188.880.2
MOT17-030.9082.682.36.065,3269,0542,79695.987.891.7
MOT17-060.8175.879.60.67,3847531,36584.490.787.5
MOT17-070.9083.881.61.88,68092058093.790.492.0
MOT17-080.9077.482.21.75,4871,04125895.584.189.4
MOT17-120.7267.380.30.64,1775461,21777.488.482.6
MOT17-140.7161.774.72.39,7961,6983,33274.685.279.6

Raw data: