Deep Tracking Metric learning

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

Short name:

MDPNN16

Benchmark:

Description:

n/a

Hardware:

TITAN X 3GHZ 1 Core

Detector:

Public

Processing:

Online

Last submitted:

November 19, 2016 (3 months ago)

Published:

November 21, 2016 at 23:50:42 CET

Submissions:

2

Open source:

No

Project page / code:

Reference:

A. Sadeghian, A. Alahi, S. Savarese. Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies. In arXiv preprint arXiv:1701.01909, 2017.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
43.875.50.612.4 % 40.7 % 3,50198,1937232,036TITAN X 3GHZ 1 CorePublic

Detailed performance:

Sequence MOTA MOTP FAF GT MT ML FP FN ID Sw Frag
MOT16-0135.572.10.32317.4 % 39.1 % 1543,9442599
MOT16-0349.075.51.014816.2 % 20.9 % 1,54851,4293151,171
MOT16-0649.274.00.222114.0 % 43.9 % 2135,55594156
MOT16-0743.074.60.65411.1 % 35.2 % 3188,882102209
MOT16-0831.779.60.6639.5 % 39.7 % 39110,94194144
MOT16-1237.277.30.68616.3 % 43.0 % 5314,6473560
MOT16-1428.674.90.51645.5 % 55.5 % 34612,79558197

Raw data:


MDPNN16