AGT: Adapted Graph Tracking

MOT16-01


Benchmark:

MOT17 | MOT16 |

Short name:

AGT

Detector:

Public

Description:

graph tracking with self adapted weights.

Reference:

Last submitted:

July 24, 2020 (12 days ago)

Published:

July 24, 2020 at 12:51:25 CET

Submissions:

1

Project page / code:

n/a

Open source:

No

Hardware:

Tesla-V100 32 G, 2 Core

Runtime:

6.6 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT1657.051.676.9192 (25.3)203 (26.7)8,48866,08463.893.21.43,857 (60.5)5,523 (86.6)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT16-0137.535.873.7731,1202,67658.276.92.5202276
MOT16-0371.360.377.667141,57227,25473.998.01.01,1802,556
MOT16-0650.444.476.470657304,16263.991.00.6834336
MOT16-0744.438.175.41191,1237,56853.688.62.2382684
MOT16-0831.633.078.3102188610,03840.088.31.4532483
MOT16-1239.748.478.518339003,94752.482.91.0157191
MOT16-1428.836.072.29582,15710,43943.578.92.9570997

Raw data: