Text-to-Video Generation on Multimodal VoxCeleb benchmark leaderboard · SOTA2 Research

Text-to-Video Generation on Multimodal VoxCeleb

0.197CLIP ScoreMMVID

Evaluation Results

Method	Links
MMVID2022.03		0.197	46.763	97.2	97.1
ART-V2022.03		0.193	60.342	95.3	96