| Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition | | 79.5 | AdaFocus (MViT-Breakfast-Pretrain-feature, GHRM) | 2023-11-28 |
| Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition | | 79.2 | AdaFocus (MViT-Breakfast-Pretrain-feature, Timeception) | 2023-11-28 |
| Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition | | 70.4 | AdaFocus (I3D-Breakfast-Pretrain-feature, Timeception) | 2023-11-28 |
| Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition | | 69.6 | AdaFocus (I3D-Breakfast-Pretrain-feature, GHRM) | 2023-11-28 |
| Graph-Based High-Order Relation Modeling for Long-Term Action Recognition | | 65.86 | GHRM (I3D-K400-Pretrain-feature) | 2021-06-19 |
| VideoGraph: Recognizing Minutes-Long Human Activities in Videos | | 63.14 | VideoGraph (I3D-K400-Pretrain-feature) | 2019-05-13 |
| Timeception for Complex Action Recognition | ✓ Link | 61.82 | Timeception (I3D-K400-Pretrain-feature) | 2018-12-04 |
| ActionVLAD: Learning spatio-temporal aggregation for action classification | | 60.20 | ActionVlad (I3D-K400-Pretrain-feature) | 2017-04-10 |