AM: Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism


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.

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:

MOT15 |

Short name:

AM

Detector:

Public

Description:

n/a

Reference:

Q. Chu, W. Ouyang, H. Li, X. Wang, B. Liu, N. Yu. Online Multi-object Tracking Using CNN-Based Single Object Tracker with Spatial-Temporal Attention Mechanism. In 2017 IEEE International Conference on Computer Vision (ICCV), 2017.

Last submitted:

March 17, 2017 (5 years ago)

Published:

August 13, 2017 at 15:24:27 CET

Submissions:

2

Project page / code:

n/a

Open source:

No

Hardware:

2.4 GHZ, 1 Core, TITAN X

Runtime:

0.5 Hz

Benchmark performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT1534.348.334.582 (11.4)313 (43.4)5,15434,84843.383.839.530.443.269.032.963.674.80.9348 (8.0)1,463 (33.8)

Detailed performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
ADL-Rundle-127.845.434.56151,0005,69738.878.344.627.048.572.529.960.475.62.026181
ADL-Rundle-339.352.435.75137205,41846.786.839.332.742.569.335.365.675.91.236109
AVG-TownCentre37.553.937.932696453,74247.684.143.133.648.266.236.063.573.11.479332
ETH-Crossing26.542.327.91151672128.194.637.121.038.774.021.672.777.90.1012
ETH-Jelmoli43.159.840.89172771,15554.583.344.837.350.371.342.064.277.30.61143
ETH-Linthescher21.132.425.171491636,87223.092.736.317.438.873.317.871.777.50.11554
KITTI-1640.660.639.51318680552.782.843.336.146.567.739.962.874.60.91957
KITTI-1924.350.135.25151,0982,90945.668.939.931.444.563.335.954.371.41.037239
PETS09-S2L247.744.331.0767184,20656.488.325.038.727.963.641.665.273.81.6115356
TUD-Crossing68.681.756.3622531571.496.961.052.064.275.754.774.378.20.1622
Venice-127.347.834.7393063,00834.183.650.423.953.472.325.763.176.00.7458

Raw data: