Online Multiple Object Tracking Based on Open-Set Few-Shot Learning

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

Short name:

VOFNet

Benchmark:

Description:

n/a

Hardware:

Detector:

Public

Processing:

Online

Last submitted:

March 13, 2018 (1 month ago)

Published:

March 13, 2018 at 08:13:58 CET

Submissions:

1

Open source:

No

Project page / code:

n/a

Reference:

Anonymous submission

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
40.974.60.89.7 % 47.0 % 4,750102,2776844,310Public
IDF1ID PrecisionID Recall
46.773.634.2

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
MOT16-0129.939.871.60.3238.7 % 43.5 % 1204,34022174
MOT16-0346.849.874.62.014814.2 % 25.0 % 2,97352,2653392,585
MOT16-0644.151.973.20.122111.3 % 52.0 % 1646,21961249
MOT16-0738.044.973.20.7549.3 % 38.9 % 3349,70388516
MOT16-0830.736.778.50.4639.5 % 44.4 % 23011,29173245
MOT16-1240.254.176.30.48611.6 % 48.8 % 3854,55622149
MOT16-1421.432.673.90.71643.0 % 63.4 % 54413,90379392

Raw data:

n/a


FLT
VOFNet