| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Motion Generation | Pexels (held-out) | Min MSE21.29 | 9 | |
| Video Frame Interpolation | Pexels 45 video-keyframe pairs | LPIPS0.1028 | 8 | |
| Dynamics Texture Generation | Pexels (test) | FG-DTFVD0.9 | 5 | |
| Reference-guided Video Stylization | Pexels 50 videos (RV2V) | CLIP-T Score0.8312 | 4 | |
| Text-to-Video Stylization | Pexels 50 videos (TV2V) | CLIP-T0.2585 | 4 | |
| Object motion generation | Pexels | FVD420.82 | 4 | |
| Poked Motion Generation | Pexels Dense | Min MSE30.4 | 3 | |
| Video Synthesis | Pexels-large (≥ 40) | FVD188.89 | 3 | |
| Video Synthesis | Pexels med. (<40) | FVD183.14 | 3 | |
| Video Synthesis | Pexels small (<20) | FVD220.65 | 3 | |
| Video Synthesis | Pexels random | FVD91.55 | 3 | |
| Poked Motion Generation | Pexels 8 Pokes | Min MSE34.8 | 2 | |
| Poked Motion Generation | Pexels 4 Pokes | Minimum MSE35.8 | 2 | |
| Poked Motion Generation | Pexels 2 Pokes | Min MSE40.9 | 2 | |
| Poked Motion Generation | Pexels 1 Poke | Minimum MSE41 | 2 |