| Paper | Code | text-to-video R@1 | text-to-video R@10 | text-to-video R@5 | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|
| Unmasked Teacher: Towards Training-Efficient Video Foundation Models | ✓ Link | 90.8 | 100.0 | 100.0 | UMT-L (ViT-L/16) | 2023-03-28 |
| vid-TLDR: Training Free Token merging for Light-weight Video Transformer | ✓ Link | 90.2 | 100.0 | 100.0 | vid-TLDR (UMT-L) | 2024-03-20 |
| HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training | 85.6 | 100 | 100 | HiTeA | 2022-12-30 | |
| VindLU: A Recipe for Effective Video-and-Language Pretraining | ✓ Link | 83.3 | 100 | 100 | VindLU | 2022-12-09 |
| Revealing Single Frame Bias for Video-and-Language Learning | ✓ Link | 77.6 | 98.9 | 96 | Singularity-temporal | 2022-06-07 |