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


Benchmark:

Short name:

AM

Detector:

Public

Description:

n/a

Project page / code:

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.

Processing:

Online

Last submitted:

March 17, 2017 (3 years ago)

Published:

August 13, 2017 at 15:24:27 CET

Submissions:

2

Open source:

No

Hardware:

2.4 GHZ, 1 Core, TITAN X

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
2D MOT 201534.348.370.582.0313.05,15434,848348

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
ADL-Rundle-127.845.471.46.015.01,0005,69726
ADL-Rundle-339.352.472.05.013.07205,41836
AVG-TownCentre37.553.968.132.069.06453,74279
ETH-Crossing26.542.374.11.015.0167210
ETH-Jelmoli43.159.873.49.017.02771,15511
ETH-Linthescher21.132.473.67.0149.01636,87215
KITTI-1640.660.670.61.03.018680519
KITTI-1924.350.166.35.015.01,0982,90937
PETS09-S2L247.744.369.27.06.07184,206115
TUD-Crossing68.681.774.46.02.0253156
Venice-127.347.871.33.09.03063,0084

Raw data:


AM