Metric: video-to-text Median Rank (higher is better)
| # | Model↕ | video-to-text Median Rank▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | CLIP | 73 | No | A Straightforward Framework For Video Retrieval ... | 2021-02-24 | Code |
| 2 | X-Pool | 10 | Yes | X-Pool: Cross-Modal Language-Video Attention for... | 2022-03-28 | Code |
| 3 | DiffusionRet | 9 | No | DiffusionRet: Generative Text-Video Retrieval wi... | 2023-03-17 | Code |
| 4 | HunYuan_tvr | 7 | Yes | Tencent Text-Video Retrieval: Hierarchical Cross... | 2022-04-07 | - |
| 5 | CenterCLIP (ViT-B/16) | 7 | Yes | CenterCLIP: Token Clustering for Efficient Text-... | 2022-05-02 | Code |
| 6 | HunYuan_tvr (huge) | 2 | Yes | Tencent Text-Video Retrieval: Hierarchical Cross... | 2022-04-07 | - |