Metric: R5@0.7 (higher is better)
| # | Model↕ | R5@0.7▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | DeCafNet | 72.96 | No | DeCafNet: Delegate and Conquer for Efficient Tem... | 2025-05-22 | Code |
| 2 | AdaFocus (Full, MViT-Charades-Pretrain-feature, MMN model) | 66.4 | No | Towards Weakly Supervised End-to-end Learning fo... | 2023-11-28 | - |
| 3 | AdaFocus (Full, I3D-Charades-Pretrain-feature, MMN model) | 65 | No | Towards Weakly Supervised End-to-end Learning fo... | 2023-11-28 | - |
| 4 | MMN (Full, MViT-K400-Pretrain-feature, evaluated by AdaFocus) | 62.7 | No | Negative Sample Matters: A Renaissance of Metric... | 2021-09-10 | Code |
| 5 | MMN (Full, I3D-K400-Pretrain-feature, evaluated by AdaFocus) | 60.5 | No | Negative Sample Matters: A Renaissance of Metric... | 2021-09-10 | Code |
| 6 | AdaFocus (Semi-weak, MViT-Charades-Pretrain-feature, D3G model) | 54.6 | No | Towards Weakly Supervised End-to-end Learning fo... | 2023-11-28 | - |
| 7 | AdaFocus (Weak, MViT-Charades-Pretrain-feature, CPL model) | 52.6 | No | Towards Weakly Supervised End-to-end Learning fo... | 2023-11-28 | - |
| 8 | AdaFocus (Weak, I3D-Charades-Pretrain-feature, CPL model) | 51.8 | No | Towards Weakly Supervised End-to-end Learning fo... | 2023-11-28 | - |
| 9 | CPL (Weak, MViT-K400-Pretrain-feature, evaluated by AdaFocus) | 50.4 | No | - | - | Code |
| 10 | D3G (Semi-weak, MViT-K400-Pretrain-feature, evaluated by AdaFocus) | 50.2 | No | D3G: Exploring Gaussian Prior for Temporal Sente... | 2023-08-08 | Code |
| 11 | AdaFocus (Semi-weak, I3D-Charades-Pretrain-feature, D3G model) | 49.2 | No | Towards Weakly Supervised End-to-end Learning fo... | 2023-11-28 | - |
| 12 | CPL (Weak, I3D-K400-Pretrain-feature, evaluated by AdaFocus) | 49.2 | No | - | - | Code |
| 13 | D3G (Semi-weak, I3D-K400-Pretrain-feature, evaluated by AdaFocus) | 48 | No | D3G: Exploring Gaussian Prior for Temporal Sente... | 2023-08-08 | Code |