| InternVideo2: Scaling Foundation Models for Multimodal Video Understanding | ✓ Link | 33.8 | 55.9 | 62.2 | | | 30.1 | 47.7 | 54.8 | InternVideo2-6B | 2024-03-22 |
| InternVideo2: Scaling Foundation Models for Multimodal Video Understanding | ✓ Link | 32.0 | 52.4 | 59.4 | | | 27.3 | 44.2 | 51.6 | InternVideo2-1B | 2024-03-22 |
| HowToCaption: Prompting LLMs to Transform Video Annotations at Scale | ✓ Link | 27.7 | 46.5 | 54.6 | 7 | | | | | VAST, HowToCaption-finetuned | 2023-10-07 |
| Unmasked Teacher: Towards Training-Efficient Video Foundation Models | ✓ Link | 25.2 | 43.0 | 50.5 | | | 23.2 | 37.7 | 44.2 | UMT-L (ViT-L/16) | 2023-03-28 |
| mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video | ✓ Link | 24.1 | 43.8 | 52.0 | | | | | | mPLUG-2 | 2023-02-01 |
| BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning | ✓ Link | 19.5 | 35.9 | 45.0 | | | | | | BT-Adapter | 2023-09-27 |
| HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training | | 18.3 | 36.7 | 44.2 | | | | | | HiTeA-17M | 2022-12-30 |
| InternVideo: General Video Foundation Models via Generative and Discriminative Learning | ✓ Link | 17.6 | 32.4 | 40.2 | | | 13.2 | 27.8 | 34.9 | InternVideo | 2022-12-06 |
| HowToCaption: Prompting LLMs to Transform Video Annotations at Scale | ✓ Link | 17.3 | 31.7 | 38.6 | 29 | | | | | HowToCaption | 2023-10-07 |
| Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning | ✓ Link | 17.2 | 32.4 | 39.1 | | | | | | Yatai Ji et. al. | 2022-11-24 |
| HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training | | 15.5 | 31.1 | 39.8 | | | | | | HiTeA-5M | 2022-12-30 |
| CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval | ✓ Link | 15.1 | 28.5 | 36.4 | 28 | 117 | | | | CLIP4Clip | 2021-04-18 |
| Clover: Towards A Unified Video-Language Alignment and Fusion Model | ✓ Link | 14.7 | 29.2 | 38.2 | 24 | | | | | Clover | 2022-07-16 |
| Bridging Video-text Retrieval with Multiple Choice Questions | ✓ Link | 12.2 | 25.9 | 32.2 | 42.0 | | | | | Y. Ge et. al. | 2022-01-13 |
| MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval | ✓ Link | 11.1 | 24.7 | 30.6 | 50.7 | | | | | MILES | 2022-04-26 |
| Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning | ✓ Link | 4.2 | 11.6 | 17.1 | | | | | | SSML | 2020-03-06 |