IFA_MOT: Integration framework and self-attention for online multiple object tracking

MOT16-01


Benchmark:

MOT16 | MOT17 |

Short name:

IFA_MOT

Detector:

Public

Description:

Reference:

Last submitted:

November 24, 2020 (2 months ago)

Published:

November 24, 2020 at 16:23:44 CET

Submissions:

1

Project page / code:

n/a

Open source:

No

Hardware:

Inter Core i3-8100 CPU @3.6Ghz, 1 Core; NVIDIA GeForce GTX 1660, 1 Core.

Runtime:

1.8 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT1659.848.078.3199 (26.2)144 (19.0)9,11861,61766.293.01.52,599 (39.3)4,490 (67.8)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT16-0153.845.180.3753052,60059.392.60.750109
MOT16-0368.149.778.653173,42329,10772.295.72.38491,952
MOT16-0656.253.779.271469083,84866.689.40.8301394
MOT16-0758.949.478.71841,4635,01969.388.52.9219437
MOT16-0838.631.880.46145989,38243.992.51.0297478
MOT16-1248.650.878.020179393,18561.684.51.0138283
MOT16-1442.145.673.624411,4828,47654.187.12.0745837

Raw data: