AI Paper Atlas

Research map / Video / Video generation

Hear What Matters! Text-conditioned Selective Video-to-Audio Generation

Junwon Lee, Juhan Nam, Jiyoung Lee

CVPR 2026 · Video › Video generation · approach: Video-to-audio synthesis · 3 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 video encoder finetuning (text-conditioned) (ablation)SELVA · SelVA-Bench (inter-class)DeSync: 0.868 -> 0.721Improved
add video encoder finetuning (text-conditioned) (ablation)SELVA · SelVA-Bench (intra-class)DeSync: 0.734 -> 0.639Improved
add V2A generator finetuning with auto-mixed samples (ablation)SELVA · SelVA-Bench (inter-class)FAD: 56.6 -> 51.7Improved
add [SUP] supplementary tokens (ablation)SELVA · SelVA-Bench (inter-class)DeSync: 0.756 -> 0.721Improved
add [SUP] supplementary tokens (ablation)SELVA · SelVA-Bench (intra-class)DeSync: 0.676 -> 0.639Improved
add [SUP] supplementary tokens (ablation)SELVA · SelVA-Bench (inter-class)KAD: 0.637 -> 0.676Hurt
use two-stage training instead of joint training (ablation)SELVA · SelVA-Bench (inter-class)DeSync: 0.823 -> 0.721Improved
use two-stage training instead of joint training (ablation)SELVA · SelVA-Bench (intra-class)DeSync: 0.777 -> 0.639Improved
increase [SUP] tokens from 0/1/3/7 to 5 (ablation)SELVA · SelVA-Bench (inter-class)DeSync: 0.756 -> 0.721Improved
replace 5 tokens by 7 tokens (ablation)SELVA · SelVA-Bench (intra-class)DeSync: 0.639 -> 0.675Hurt
remove CLIP embedding (null) from MMAudio (ablation)MMAudio-S-16kHz · VGGSound testCLAP: 0.197 -> 0.235Improved
remove Synchformer embedding (null) from MMAudio (ablation)MMAudio-S-16kHz · VGGSound testDeSync: 0.492 -> 1.243Hurt

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