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

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

Short name:

STAM16

Benchmark:

Description:

n/a

Hardware:

2.4 GHZ, 1 Core, TITAN X

Detector:

Public

Processing:

Online

Last submitted:

August 04, 2017 (11 months ago)

Published:

August 13, 2017 at 15:26:38 CET

Submissions:

2

Open source:

No

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.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
46.074.91.214.6 % 43.6 % 6,89591,1174731,4222.4 GHZ, 1 Core, TITAN XPublic
IDF1ID PrecisionID Recall
50.071.538.5

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
MOT16-0135.740.472.00.42321.7 % 39.1 % 1593,9213081
MOT16-0353.853.674.73.414824.3 % 17.6 % 5,02843,018210740
MOT16-0648.459.073.50.122115.8 % 50.2 % 1475,76539131
MOT16-0738.045.474.21.1549.3 % 33.3 % 5499,49578194
MOT16-0832.336.879.20.76314.3 % 39.7 % 40710,85865111
MOT16-1242.354.077.10.48616.3 % 48.8 % 3544,4102337
MOT16-1424.636.574.60.31644.3 % 61.0 % 25113,65028128

Raw data:


STAM16