Metric: mAP (higher is better)
| # | Model↕ | mAP▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | AdaFocus (MViT-Breakfast-Pretrain-feature, GHRM) | 79.5 | No | Towards Weakly Supervised End-to-end Learning fo... | 2023-11-28 | - |
| 2 | AdaFocus (MViT-Breakfast-Pretrain-feature, Timeception) | 79.2 | No | Towards Weakly Supervised End-to-end Learning fo... | 2023-11-28 | - |
| 3 | AdaFocus (I3D-Breakfast-Pretrain-feature, Timeception) | 70.4 | No | Towards Weakly Supervised End-to-end Learning fo... | 2023-11-28 | - |
| 4 | AdaFocus (I3D-Breakfast-Pretrain-feature, GHRM) | 69.6 | No | Towards Weakly Supervised End-to-end Learning fo... | 2023-11-28 | - |
| 5 | GHRM (I3D-K400-Pretrain-feature) | 65.86 | No | - | - | - |
| 6 | VideoGraph (I3D-K400-Pretrain-feature) | 63.14 | No | VideoGraph: Recognizing Minutes-Long Human Activ... | 2019-05-13 | - |
| 7 | Timeception (I3D-K400-Pretrain-feature) | 61.82 | No | Timeception for Complex Action Recognition | 2018-12-04 | Code |
| 8 | ActionVlad (I3D-K400-Pretrain-feature) | 60.2 | No | ActionVLAD: Learning spatio-temporal aggregation... | 2017-04-10 | - |