Deep Tracking Metric learning

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

Short name:

AMIR

Benchmark:

Description:

Hardware:

TITAN X 3GHZ 1 Core

Detector:

Public

Processing:

Online

Last submitted:

March 17, 2017 (1 year ago)

Published:

November 21, 2016 at 23:50:42 CET

Submissions:

3

Open source:

No

Project page / code:

Reference:

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
47.275.80.514.0 % 41.6 % 2,68192,8567741,675TITAN X 3GHZ 1 CorePublic
IDF1ID PrecisionID Recall
46.368.934.8

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
MOT16-0137.838.072.10.22313.0 % 39.1 % 863,8652477
MOT16-0353.847.575.90.814820.3 % 18.9 % 1,14246,803352900
MOT16-0649.256.774.40.122115.8 % 50.7 % 1525,66936108
MOT16-0745.546.874.80.45411.1 % 27.8 % 2228,573102206
MOT16-0832.540.179.70.4637.9 % 38.1 % 23211,0045697
MOT16-1240.452.877.60.58618.6 % 48.8 % 4684,4433635
MOT16-1429.435.674.80.51646.7 % 52.4 % 37912,499168252

Raw data:


AMIR