ResearchBenchmarksVideo-to-audio generation (V2A) on Landscape (test)Follow0.78FADAVDiT (MoNL)0.26723.72867.1910.6514May 22, 2024Evaluation ResultsMethodMethodLinksFADAV alignAVDiT (MoNL)2024.050.7851MM-Diffusion (MMD)2024.0513.650