Metric: video-to-text R@5 (higher is better)
| # | Model↕ | video-to-text R@5▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | UMT-L (ViT-L/16) | 89.1 | Yes | Unmasked Teacher: Towards Training-Efficient Vid... | 2023-03-28 | Code |
| 2 | vid-TLDR (UMT-L) | 88.7 | Yes | vid-TLDR: Training Free Token merging for Light-... | 2024-03-20 | Code |
| 3 | HunYuan_tvr | 85.7 | Yes | Tencent Text-Video Retrieval: Hierarchical Cross... | 2022-04-07 | - |
| 4 | EMCL-Net++ | 78.9 | No | Expectation-Maximization Contrastive Learning fo... | 2022-11-21 | Code |
| 5 | CenterCLIP (ViT-B/16) | 77.1 | Yes | CenterCLIP: Token Clustering for Efficient Text-... | 2022-05-02 | Code |
| 6 | DiffusionRet+QB-Norm | 76.3 | No | DiffusionRet: Generative Text-Video Retrieval wi... | 2023-03-17 | Code |
| 7 | X-CLIP | 75.9 | No | X-CLIP: End-to-End Multi-grained Contrastive Lea... | 2022-07-15 | Code |
| 8 | DiffusionRet | 75.3 | No | DiffusionRet: Generative Text-Video Retrieval wi... | 2023-03-17 | Code |
| 9 | EMCL-Net | 74 | No | Expectation-Maximization Contrastive Learning fo... | 2022-11-21 | Code |
| 10 | HBI | 73 | No | Video-Text as Game Players: Hierarchical Banzhaf... | 2023-03-25 | Code |
| 11 | Ours | 60 | No | Video and Text Matching with Conditioned Embeddi... | 2021-10-21 | Code |