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

AVG-TownCentre


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

Runtime:

0.5 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
2D MOT 201534.348.370.582 (11.4)313 (43.4)5,15434,84843.383.80.9348 (8.0)1,463 (33.8)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
ADL-Rundle-127.845.471.46151,0005,69738.878.32.026181
ADL-Rundle-339.352.472.05137205,41846.786.81.236109
AVG-TownCentre37.553.968.132696453,74247.684.11.479332
ETH-Crossing26.542.374.11151672128.194.60.1012
ETH-Jelmoli43.159.873.49172771,15554.583.30.61143
ETH-Linthescher21.132.473.671491636,87223.092.70.11554
KITTI-1640.660.670.61318680552.782.80.91957
KITTI-1924.350.166.35151,0982,90945.668.91.037239
PETS09-S2L247.744.369.2767184,20656.488.31.6115356
TUD-Crossing68.681.774.4622531571.496.90.1622
Venice-127.347.871.3393063,00834.183.60.7458

Raw data: