HiGen

Reported on 3 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing3 results

Text-to-Video GenerationonMSR-VTT
FID· 2023-12-07
8.6
best: 8.19 (TF-T2V)
SOTA
Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation arXiv:2312.04483
Text-to-Video GenerationonMSR-VTT
CLIPSIM· 2023-12-07
0.2947
best: 0.3125 (PixelDance)
Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation arXiv:2312.04483
Text-to-Video GenerationonMSR-VTT
FVD· 2023-12-07
406
best: 998 (MagicVideo)
Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation arXiv:2312.04483