STAM16: Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism

MOT16-01


Benchmark:

MOT16 |

Short name:

STAM16

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:

August 04, 2017 (3 years ago)

Published:

August 13, 2017 at 15:26:38 CET

Submissions:

2

Project page / code:

n/a

Open source:

No

Hardware:

2.4 GHZ, 1 Core, TITAN X

Runtime:

0.2 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT1646.050.074.9111 (14.6)331 (43.6)6,89591,11750.093.01.2473 (9.5)1,422 (28.4)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT16-0135.740.472.0591593,92138.794.00.43081
MOT16-0353.853.674.736265,02843,01858.992.43.4210740
MOT16-0648.459.073.5351111475,76550.097.50.139131
MOT16-0738.045.474.25185499,49541.892.61.178194
MOT16-0832.336.879.292540710,85835.193.50.765111
MOT16-1242.354.077.114423544,41046.891.60.42337
MOT16-1424.636.574.6710025113,65026.195.10.328128

Raw data: