VideoPoet

Reported on 3 benchmarks across 1 task · 1 paper

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 GenerationonUCF-101
FVD16· 2023-12-21
355
best: 699 (MagicVideo (Zero-shot, 256x256))
VideoPoet: A Large Language Model for Zero-Shot Video Generation arXiv:2312.14125
Text-to-Video GenerationonMSR-VTT
CLIPSIM· 2023-12-21
0.3123
best: 0.3125 (PixelDance)
VideoPoet: A Large Language Model for Zero-Shot Video Generation arXiv:2312.14125
Text-to-Video GenerationonMSR-VTT
FVD· 2023-12-21
213
best: 998 (MagicVideo)
VideoPoet: A Large Language Model for Zero-Shot Video Generation arXiv:2312.14125