Recurrent Autoregressive Networks for Online Multi-Object Tracking

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

Short name:

RAR16pub

Benchmark:

Description:

Recurrent autoregressive networks tracking framework with public detections

Hardware:

Titan X, 1.5GHZ, 1Core

Detector:

Public

Processing:

Online

Last submitted:

March 24, 2017 (1 year ago)

Published:

July 23, 2018 at 09:33:19 CET

Submissions:

1

Open source:

No

Project page / code:

Reference:

K. Fang, Y. Xiang, X. Li, S. Savarese. Recurrent Autoregressive Networks for Online Multi-Object Tracking. In The IEEE Winter Conference on Applications of Computer Vision (WACV), 2018.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
45.974.81.213.2 % 41.9 % 6,87191,1736481,992Titan X, 1.5GHZ, 1CorePublic
IDF1ID PrecisionID Recall
48.869.737.5

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
MOT16-0126.333.673.00.1238.7 % 56.5 % 414,6631249
MOT16-0354.652.874.92.314823.0 % 14.9 % 3,49243,6793011,072
MOT16-0645.253.972.80.322114.0 % 48.4 % 4145,82186205
MOT16-0739.945.973.61.35411.1 % 35.2 % 6599,07473188
MOT16-0829.835.177.81.6639.5 % 38.1 % 97110,68889166
MOT16-1239.048.375.30.78614.0 % 46.5 % 6344,38043131
MOT16-1426.639.174.50.91645.5 % 56.7 % 66012,86844181

Raw data:


RAR16pub