Video-Based Text Generation on Video-Based Text Generation
3.51Cr.CAMD
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| CAMDBackbone=Video-LLaMA22026.03 | 3.51 | 3.57 | 3.45 | 3.73 | 2.62 | |
| CAMDBackbone=VILA2026.03 | 3.3 | 3.65 | 2.95 | 3.72 | 2.85 | |
| FarSightBackbone=Video-LLaMA22026.03 | 3.26 | 3.32 | 3.21 | 3.5 | 2.47 | |
| FarSightBackbone=VILA2026.03 | 3.18 | 3.52 | 2.73 | 3.45 | 2.6 | |
| VILA2026.03 | 3.14 | 3.4 | 2.71 | 3.43 | 2.58 | |
| Video-LLaMA22026.03 | 3.13 | 3.23 | 2.7 | 3.42 | 2.45 | |
| CAMDBackbone=Chat-UniVi2026.03 | 3.05 | 3.1 | 2.72 | 3.35 | 2.6 | |
| FarSightBackbone=Chat-UniVi2026.03 | 2.86 | 2.94 | 2.56 | 3.19 | 2.48 | |
| Chat-UniVi2026.03 | 2.84 | 2.93 | 2.55 | 3.16 | 2.43 | |
| CAMDBackbone=Video-LLaVA2026.03 | 2.58 | 2.55 | 3.06 | 3.02 | 2.3 | |
| FarSightBackbone=Video-LLaVA2026.03 | 2.43 | 2.38 | 2.93 | 2.84 | 2.14 | |
| Video-LLaVA2026.03 | 2.32 | 2.34 | 2.65 | 2.75 | 2.09 |