Snap Video (512x288)

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
CLIP-FID· 2024-02-22
9.35
best: 8.48 (Snap Video (288×288))
SOTA
Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis arXiv:2402.14797
Text-to-Video GenerationonMSR-VTT
CLIPSIM· 2024-02-22
0.2793
best: 0.3125 (PixelDance)
Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis arXiv:2402.14797
Text-to-Video GenerationonMSR-VTT
FVD· 2024-02-22
104
best: 998 (MagicVideo)
Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis arXiv:2402.14797