GNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization
MOT20-04
Short name:
GNNMatch
Detector:
Public
Description:
Reference:
GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization. ARXIV 2020
Last submitted:
February 23, 2021 (12 days ago)
Published:
February 23, 2021 at 15:37:20 CET
Submissions:
4
Project page / code:
n/a
Open source:
No
Hardware:
TITAN RTX
Runtime:
0.1 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| MOT20 | 54.5 | 49.0 | 79.4 | 407 (32.8) | 317 (25.5) | 9,522 | 223,611 | 56.8 | 96.9 | 2.1 | 2,038 (35.9) | 2,456 (43.3) |
Detailed performance:
Raw data:
