| DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos | ✓ Link | 47.55 | 68.79 | 72.96 | 91.53 | DeCafNet | 2025-05-22 |
| Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition | | 38.6 | 62.4 | 66.4 | 89.4 | AdaFocus (Full, MViT-Charades-Pretrain-feature, MMN model) | 2023-11-28 |
| Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition | | 35.6 | 56.7 | 65.0 | 87.9 | AdaFocus (Full, I3D-Charades-Pretrain-feature, MMN model) | 2023-11-28 |
| Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding | ✓ Link | 32.2 | 55.2 | 62.7 | 88.3 | MMN (Full, MViT-K400-Pretrain-feature, evaluated by AdaFocus) | 2021-09-10 |
| Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding | ✓ Link | 29.8 | 49.4 | 60.5 | 85.8 | MMN (Full, I3D-K400-Pretrain-feature, evaluated by AdaFocus) | 2021-09-10 |
| Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition | | 23.2 | 51.7 | 52.6 | 85.2 | AdaFocus (Weak, MViT-Charades-Pretrain-feature, CPL model) | 2023-11-28 |
| Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition | | 22.4 | 49.1 | 51.8 | 84.2 | AdaFocus (Weak, I3D-Charades-Pretrain-feature, CPL model) | 2023-11-28 |
| Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition | | 21.8 | 50.1 | 54.6 | 86.1 | AdaFocus (Semi-weak, MViT-Charades-Pretrain-feature, D3G model) | 2023-11-28 |
| Weakly Supervised Temporal Sentence Grounding With Gaussian-Based Contrastive Proposal Learning | ✓ Link | 21.8 | 47.8 | 50.4 | 84.6 | CPL (Weak, MViT-K400-Pretrain-feature, evaluated by AdaFocus) | 2022-01-01 |
| Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition | | 21.1 | 46.9 | 49.2 | 79.3 | AdaFocus (Semi-weak, I3D-Charades-Pretrain-feature, D3G model) | 2023-11-28 |
| D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation | ✓ Link | 20.2 | 46.0 | 50.2 | 83.1 | D3G (Semi-weak, MViT-K400-Pretrain-feature, evaluated by AdaFocus) | 2023-08-08 |
| D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation | ✓ Link | 18.8 | 41.7 | 48.0 | 78.2 | D3G (Semi-weak, I3D-K400-Pretrain-feature, evaluated by AdaFocus) | 2023-08-08 |
| Weakly Supervised Temporal Sentence Grounding With Gaussian-Based Contrastive Proposal Learning | ✓ Link | 18.6 | 39.6 | 49.2 | 81.4 | CPL (Weak, I3D-K400-Pretrain-feature, evaluated by AdaFocus) | 2022-01-01 |