QuadMOT16: Multi-Object Tracking with Quadruplet Convolutional Neural Networks

MOT16-01


Benchmark:

MOT16 |

Short name:

QuadMOT16

Detector:

Public

Description:

n/a

Project page / code:

n/a

Reference:

J. Son, M. Baek, M. Cho, B. Han. Multi-Object Tracking with Quadruplet Convolutional Neural Networks. In CVPR, 2017.

Processing:

Batch

Last submitted:

November 22, 2016 (3 years ago)

Published:

November 23, 2016 at 04:26:44 CET

Submissions:

1

Open source:

No

Hardware:

3 GHZ, 1 Core, TITAN X

Runtime:

1.8 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT1644.138.376.4111 (14.6)341 (44.9)6,38894,77548.093.21.1745 (15.5)1,096 (22.8)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT16-0130.831.374.84111194,27833.194.70.32643
MOT16-0351.037.176.327333,12547,70454.494.82.1397561
MOT16-0649.257.276.8441162605,54951.995.80.25182
MOT16-0741.938.177.27167688,62647.290.91.584108
MOT16-0829.934.779.472658211,07233.890.70.97484
MOT16-1238.047.776.213485164,59944.687.70.62832
MOT16-1424.033.573.89911,01812,94729.984.51.485186

Raw data: