Text-to-Video Generation on MSR-VTT 2016 (test)
0.3104CLIPSIMShow-1
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Show-1Evaluation Setting=Zero-shot2023.09 | 0.3104 | 12.97 | 536 | |
| Make-A-Video2023.09 | 0.3049 | 13.17 | — | |
| ModelScopeT2V2023.09 | 0.293 | 11.09 | 550 | |
| Video LDM2023.09 | 0.2929 | — | — | |
| CogVideoLanguage=English2023.09 | 0.2631 | 23.59 | 1,294 | |
| CogVideoLanguage=Chinese2023.09 | 0.2614 | 24.78 | — | |
| NUWA2023.09 | 0.2439 | 47.68 | — | |
| MagicVideo2023.09 | — | — | 1,290 |