OSL-loc-NetVLAD
OpenSportsLib localization models. main is the version catalog; load an explicit experiment revision using LocalizationModel.from_pretrained.
Trained model versions
Select a version below to read its recipe, data, measured metrics and usage instructions. Each weight/config pair belongs to the linked experiment and seed.
| Version / README | Dataset | Seed | Scope | Measured test scores | Artifacts |
|---|---|---|---|---|---|
| soccernet_netrvlad_baidu | SoccerNet-v2 | 1 | controlled feature/pooling extension; no matched paper target | loose average-mAP: 69.3119%; tight average-mAP: 6.1889% | weights 路 config |
| soccernet_netrvlad_resnet_pca512 | SoccerNet-v2 | 1 | controlled feature/pooling extension; no matched paper target | loose average-mAP: 46.8216%; tight average-mAP: 7.2654% | weights 路 config |
| soccernet_netvlad_baidu | SoccerNet-v2 | 1 | controlled feature/pooling extension; no matched paper target | loose average-mAP: 70.8112%; tight average-mAP: 6.6621% | weights 路 config |
| soccernet_netvlad_resnet_pca512 | SoccerNet-v2 | 1 | released-code PCA ablation | loose average-mAP: 48.3548%; tight average-mAP: 7.3769% | weights 路 config |
Per-seed measurements do not establish exact paper reproduction. Read each version's protocol and aggregation notes.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support