ApLift: Approximate Lifted Disjoint Paths Tracker

MOT16-01


Benchmark:

Short name:

ApLift

Detector:

Public

Description:

Reference:

A. Hornakova*, T. Kaiser*, M. Rolinek, B. Rosenhahn, P. Swoboda, R. Henschel. Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths. In International Conference on Computer Vision (ICCV), 2021.

Last submitted:

March 14, 2021 (7 months ago)

Published:

March 22, 2021 at 11:46:35 CET

Submissions:

1

Project page / code:

Open source:

No

Hardware:

5Ghz 8 Cores

Runtime:

0.6 Hz

Benchmark performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT1661.766.151.3260 (34.3)237 (31.2)9,16860,18067.093.053.249.859.273.153.874.680.71.5495 (0.0)802 (0.0)

Detailed performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT16-0148.854.343.9891223,14550.896.450.838.156.376.339.875.479.90.3821
MOT16-0373.773.356.584174,49722,92378.194.855.657.760.973.262.275.580.53.0118308
MOT16-0657.461.949.298751,2333,60568.886.549.549.267.760.455.770.280.91.07292
MOT16-0746.952.840.91191,0907,49954.189.041.540.744.974.244.072.480.02.279133
MOT16-0841.751.843.917244999,22044.993.853.736.056.381.837.979.184.00.84766
MOT16-1249.463.449.523325803,59756.689.057.043.164.975.547.274.282.90.62032
MOT16-1437.851.036.719711,14710,19144.987.841.132.946.268.235.669.779.21.5151150

Raw data:


ApLift