AI Paper Atlas

Research map / Video / Video generation

Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity

Santiago Pascual, Chunghsin YEH, Ioannis Tsiamas, Joan Serrà

ECCV 2024 · Video › Video generation · approach: Video-to-audio synthesis · 28 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add S3D alignment features (SparseSync-pretrained) to CLIP conditioning via AdaLN (ablation)MaskVAT AdaLN · VGGSound-TestSparseSync offset: 0.60 -> 0.43Improved
add S3D alignment features to CLIP conditioning via AdaLN (ablation)MaskVAT AdaLN · VGGSound-TestNovelty score: 0.05 -> 0.16Improved
add S3D features to CLIP conditioning (ablation)MaskVAT AdaLN · VGGSound-TestFAD: 3.83 -> 3.39Improved
use seq2seq cross-attention with BEATs distillation losses instead of AdaLN (ablation)MaskVAT · VGGSound-TestWaveCLIP: 0.50 -> 0.55Improved
use seq2seq instead of AdaLN with S3D (ablation)MaskVAT · VGGSound-TestSparseSync offset: 0.43 -> 0.63Hurt
use full-band DAC codec instead of baselines' lossy low-band pipelinesMaskVAT · VGGSound-TestFAD: 1.51 vs 0.84Hurt
apply bandwidth extension to baselinesSpecVQGAN · VGGSound-TestFDD: 0.26 -> 0.42Hurt
use MaskVAT Hybrid instead of V2A-Mapper in human evaluationV2A-Mapper · VGGSound-sparse subjective testAlignment MOS: 2.12 -> 3.81Improved
use MaskVAT Hybrid instead of V2A-MapperV2A-Mapper · VGGSound subjective testFidelity MOS: 3.00 -> 2.76No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy