SGT_det: Sparse Graph Tracker for detection

MOT17-01


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:

January 11, 2022 (2 years ago)

Published:

November 14, 2021 at 16:03:40 CET

Submissions:

2

Project page / code:

Open source:

Yes

Hardware:

V100

Runtime:

20.8 Hz

Benchmark performance:

Sequence AP MODA MODP FAF TP FP FN Rcll Prcn F1
MOT17Det0.9086.682.41.3106,8497,6887,71593.393.393.3

Detailed performance:

Sequence AP MODA MODP FAF TP FP FN Rcll Prcn F1
MOT17-010.7372.481.20.53,25723990978.293.285.0
MOT17-030.9195.084.92.067,7473,03737599.495.797.5
MOT17-060.8176.381.51.07,8111,13693889.387.388.3
MOT17-070.9087.379.00.98,54145471992.295.093.6
MOT17-080.9185.078.51.05,51162523495.989.892.8
MOT17-120.8161.678.21.44,6051,28178985.478.281.6
MOT17-140.7164.573.31.29,3779163,75171.491.180.1

Raw data: