SGT_det: Sparse Graph Tracker for detection

MOT20-04


Benchmark:

Short name:

SGT_det

Description:

Reference:

J. Hyun, M. Kang, D. Wee, D. Yeung. Detection recovery in online multi-object tracking with sparse graph tracker. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023.

Last submitted:

October 28, 2021 (2 years ago)

Published:

November 14, 2021 at 16:04:23 CET

Submissions:

1

Project page / code:

Open source:

Yes

Hardware:

1 V100, 12 CPUs

Runtime:

14.3 Hz

Benchmark performance:

Sequence AP MODA MODP FAF TP FP FN Rcll Prcn F1
MOT20Det0.9084.380.65.0311,92022,18331,60490.893.492.1

Detailed performance:

Sequence AP MODA MODP FAF TP FP FN Rcll Prcn F1
MOT20-040.9189.180.36.1218,30412,72012,42594.694.594.6
MOT20-060.7272.281.24.250,2824,18513,60778.792.385.0
MOT20-070.9185.483.73.315,8401,91745897.289.293.0
MOT20-080.8174.080.14.227,4943,3615,11484.389.186.6

Raw data: