Metric: video-to-text R@10 (higher is better)
| # | Model↕ | video-to-text R@10▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | GRAM | 95.4 | Yes | Gramian Multimodal Representation Learning and A... | 2024-12-16 | Code |
| 2 | UMT-L (ViT-L/16) | 94.8 | Yes | Unmasked Teacher: Towards Training-Efficient Vid... | 2023-03-28 | Code |
| 3 | vid-TLDR (UMT-L) | 94.5 | Yes | vid-TLDR: Training Free Token merging for Light-... | 2024-03-20 | Code |
| 4 | HunYuan_tvr | 93.9 | Yes | Tencent Text-Video Retrieval: Hierarchical Cross... | 2022-04-07 | - |
| 5 | CenterCLIP (ViT-B/16) | 88 | Yes | CenterCLIP: Token Clustering for Efficient Text-... | 2022-05-02 | Code |
| 6 | DiffusionRet+QB-Norm | 86.7 | No | DiffusionRet: Generative Text-Video Retrieval wi... | 2023-03-17 | Code |
| 7 | DiffusionRet | 86.7 | No | DiffusionRet: Generative Text-Video Retrieval wi... | 2023-03-17 | Code |
| 8 | HBI | 86 | No | Video-Text as Game Players: Hierarchical Banzhaf... | 2023-03-25 | Code |