Metric: 2-Class Accuracy (higher is better)
| # | Model↕ | 2-Class Accuracy▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Video-LLAMA | 88.33 | Yes | Video-LLaMA: An Instruction-tuned Audio-Visual L... | 2023-06-05 | Code |
| 2 | Time-Chat | 76.67 | Yes | TimeChat: A Time-sensitive Multimodal Large Lang... | 2023-12-04 | Code |
| 3 | TACT | 64.4 | Yes | Test of Time: Instilling Video-Language Models w... | 2023-01-05 | Code |
| 4 | VideoPrompter | 60 | No | Videoprompter: an ensemble of foundational model... | 2023-10-23 | - |