AI Paper Atlas

Research map / Video / Video generation

Precise Video-to-Audio Generation with Cross-Modal Alignment in Latent Space

Thanh V. T. Tran, Ngoc-Son Nguyen, Luong Tran, Long-Khanh Pham, Paarth Neekhara, Shehzeen Hussain, Van Nguyen

ECCV 2026 · Video › Video generation · approach: Video-to-audio synthesis · 0 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 Progressive Soft-masked Cross-Attention (replace standard visual cross-attention) (ablation)Flowley · VGGSound testAlign Acc: 87.61 -> 89.37Improved
add layer-dependent progressive parameter beta (ablation)Flowley PSCA · VGGSound testAlign Acc: 88.62 -> 89.37Improved
add layer-dependent progressive parameter beta (ablation)Flowley PSCA · VGGSound testIS: 17.78 -> 18.25Improved
add text and visual cross-attention to single-stream block (vs vanilla DiT) (ablation)Flowley · VGGSound testIS: 16.99 -> 18.25Improved
add text cross-attention (ablation)Flowley · VGGSound testIB-Score: 28.51 -> 29.32Improved
widen PSCA window omega and delta (ablation)Flowley · VGGSound testAlign Acc: 89.37 -> 86.58Hurt
widen PSCA window omega and delta (ablation)Flowley · VGGSound testIS / IB-Score: IS 17.85-18.57, IB 28.84-29.48No clear effect
add SoundCap captionsFlowley · VGGSound testIS: 18.25 -> 19.68Improved
add SoundCap captionsMMAudio · VGGSound testKAD: 0.57 -> 0.39Improved
add SoundCap captions without noise-aware prompts (ablation)Flowley · VGGSound testIS: 18.25 -> 15.16Hurt
add noise-aware conditions to SoundCap prompts (ablation)Flowley + SoundCap · VGGSound testIS: 15.16 -> 19.68Improved
add SoundCap at inferenceFlowley · MovieGen Audio Bench (zero-shot)IS: 7.74 -> 8.18Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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