Metric: video-to-text R@1 (higher is better)
| # | Model↕ | video-to-text R@1▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | InternVideo2-6B | 56.5 | Yes | InternVideo2: Scaling Foundation Models for Mult... | 2024-03-22 | Code |
| 2 | InternVideo2-1B | 54.8 | Yes | InternVideo2: Scaling Foundation Models for Mult... | 2024-03-22 | Code |
| 3 | GRAM | 50.9 | Yes | Gramian Multimodal Representation Learning and A... | 2024-12-16 | Code |
| 4 | vid-TLDR (UMT-L) | 41.2 | Yes | vid-TLDR: Training Free Token merging for Light-... | 2024-03-20 | Code |
| 5 | UMT-L (ViT-L/16) | 40.7 | Yes | Unmasked Teacher: Towards Training-Efficient Vid... | 2023-03-28 | Code |
| 6 | LanguageBind(ViT-H/14) | 39.1 | Yes | LanguageBind: Extending Video-Language Pretraini... | 2023-10-03 | Code |
| 7 | LanguageBind(ViT-L/14) | 35.7 | Yes | LanguageBind: Extending Video-Language Pretraini... | 2023-10-03 | Code |
| 8 | VideoCoCa | 33 | Yes | VideoCoCa: Video-Text Modeling with Zero-Shot Tr... | 2022-12-09 | - |
| 9 | InternVideo | 31.4 | Yes | InternVideo: General Video Foundation Models via... | 2022-12-06 | Code |