| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Joint Video-Audio Generation | Landscape (test) | FVD86.79 | 9 | |
| Image Generation | Landscape | FID6.08 | 9 | |
| Video Synthesis | Landscape | LPIPS0.23 | 5 | |
| Scene-to-Image Generation | Landscape | Votes Count197 | 4 | |
| Image Synthesis | Landscape | FID6.92 | 4 | |
| Video-to-audio generation (V2A) | Landscape (test) | FAD0.78 | 2 | |
| Audio-Video reconstruction | Landscape (test) | FAD0.76 | 1 |