| Paper | Code | mean | Correctness of Information | Detail Orientation | Contextual Understanding | Temporal Understanding | Consistency | Dense Captioning | Spatial Understanding | Reasoning | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding | ✓ Link | 2.47 | 2.46 | 2.73 | 2.81 | 1.78 | 2.59 | 1.38 | 2.80 | 3.63 | VideoGPT+ | 2024-06-13 |
| Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding | ✓ Link | 2.29 | 2.29 | 2.56 | 2.66 | 1.56 | 2.36 | 1.33 | 2.36 | 3.59 | Chat-UniVi | 2023-11-14 |
| MVBench: A Comprehensive Multi-modal Video Understanding Benchmark | ✓ Link | 2.20 | 2.13 | 2.42 | 2.51 | 1.66 | 2.27 | 1.26 | 2.43 | 3.13 | VideoChat2 | 2023-11-28 |
| BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning | ✓ Link | 2.19 | 2.20 | 2.62 | 2.59 | 1.29 | 2.27 | 1.03 | 2.35 | 3.62 | BT-Adapter | 2023-09-27 |
| VTimeLLM: Empower LLM to Grasp Video Moments | ✓ Link | 2.17 | 2.16 | 2.41 | 2.48 | 1.46 | 2.35 | 1.13 | 2.29 | 3.45 | VTimeLLM | 2023-11-30 |
| Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models | ✓ Link | 2.08 | 2.07 | 2.42 | 2.46 | 1.39 | 2.06 | 0.89 | 2.25 | 3.60 | Video-ChatGPT | 2023-06-08 |