| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Human Video Generation | HumanVid | SSIM69.1 | 5 | |
| Text-to-Video Generation | HumanVid 500 real-world videos (curated evaluation set) | LPIPS0.46 | 5 | |
| Human Video Generation | HumanVid Portrait | SSIM67.8 | 5 | |
| Human Video Generation | HumanVid Landscape | SSIM0.672 | 5 | |
| Image-to-Video Generation | HumanVid curated 500 real-world videos (evaluation set) | LPIPS0.42 | 2 |