Online MOT with Dual Matching Attention Networks

MOT16-01 MOT16-03 MOT16-06 MOT16-07 MOT16-08 MOT16-12 MOT16-14

Short name:

DMMOT

Benchmark:

Description:

n/a

Hardware:

2.4 GHZ, 1 Core

Detector:

Public

Processing:

Online

Last submitted:

November 11, 2017 (1 year ago)

Published:

September 11, 2018 at 07:22:21 CET

Submissions:

2

Open source:

No

Project page / code:

n/a

Reference:

J. Zhu, H. Yang, N. Liu, M. Kim, W. Zhang, M. Yang. Online Multi-Object Tracking with Dual Matching Attention Networks. In ECCV, 2018.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
46.173.81.317.4 % 42.7 % 7,90989,8745321,6162.4 GHZ, 1 CorePublic
IDF1ID PrecisionID Recall
54.877.242.5

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
MOT16-0137.048.769.80.42321.7 % 43.5 % 1993,8141372
MOT16-0353.559.373.72.914825.0 % 20.3 % 4,38544,051192842
MOT16-0647.455.872.10.522118.6 % 45.7 % 5665,377130242
MOT16-0742.851.672.41.25416.7 % 33.3 % 5768,70959148
MOT16-0832.544.378.91.16322.2 % 38.1 % 70810,53956106
MOT16-1241.857.076.60.58619.8 % 51.2 % 4124,4001638
MOT16-1423.638.172.71.41645.5 % 59.1 % 1,06312,98466168

Raw data:


DMMOT