RAR16pub: Recurrent Autoregressive Networks for Online Multi-Object Tracking


Video not available.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Benchmark:

MOT16 |

Short name:

RAR16pub

Detector:

Public

Description:

Recurrent autoregressive networks tracking framework with public detections

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.

Last submitted:

March 24, 2017 (5 years ago)

Published:

July 23, 2018 at 09:33:19 CET

Submissions:

1

Project page / code:

Open source:

No

Hardware:

Titan X, 1.5GHZ, 1Core

Runtime:

0.9 Hz

Benchmark performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT1645.948.836.5100 (13.2)318 (41.9)6,87191,17350.093.036.336.838.175.838.972.478.51.2648 (13.0)1,992 (39.8)

Detailed performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT16-0126.333.625.9213414,66327.197.733.719.935.175.620.473.577.50.11249
MOT16-0354.652.839.734223,49243,67958.294.636.843.038.676.045.473.778.62.33011,072
MOT16-0645.253.938.9311074145,82149.593.242.635.744.874.837.670.877.00.386205
MOT16-0739.945.932.86196599,07444.491.733.732.235.373.534.070.277.51.373188
MOT16-0829.835.128.162497110,68836.186.229.027.230.576.729.269.680.11.689166
MOT16-1239.048.337.012406344,38047.286.140.134.242.175.837.368.078.60.743131
MOT16-1426.639.127.499366012,86830.489.533.322.534.676.123.669.577.80.944181

Raw data: