AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Whence the Voice? Self-supervised Dual-source Audio-Visual Localisation via Selective Convergence

Han Hu, Dongheng Lin, Yuqi Hou, Haotian LI, Hyung Jin Chang, Jianbo Jiao

ECCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization · 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
Use learned spatial prior from Stage 1 instead of uniform mask (ablation)SCAV · VGGSound-Duet (BBox) ablationCIoU@0.3 (%): 28.94 -> 53.27Improved
Progressive two-stage training instead of joint training (ablation)SCAV · VGGSound-Duet (BBox) ablationCIoU@0.3 (%): 41.84 -> 53.27Improved
Exclude cross-sample negatives in Stage 2 (ablation)SCAV · VGGSound-Duet (BBox) ablationCIoU@0.3 (%): 26.69 -> 53.27Improved
Add dominant-source post-processing (ablation)SCAV · VGGSound-Duet (BBox) ablationCIoU@0.3 (%): 52.44 -> 53.27No clear effect
Progressive training on mask-based benchmark (ablation)SCAV · VGGSound-Duet Mask ablationCIoU@0.3 (%): 25.62 -> 33.59Improved
Stage 1 contrastive training on mixed audioStage 1 model · VGGSound-Duet, first-stage modelCIoU@0.3 (%): dominant 61.70 vs second 3.62Mixed
SCAV vs best self-supervised baseline on mask evaluationSCAV · VGGSound-Duet MaskCIoU@0.3 (%): 9.58 -> 33.59Improved
SCAV vs AVGN on MUSIC-Duet detectionSCAV · MUSIC-Duet (BBox)CAP (%): 50.6 -> 47.6Hurt
SCAV vs OA-SSL on VGGSound-Duet bboxSCAV · VGGSound-Duet (BBox, frame-wise)CIoU@0.3 (%): 55.2 -> 53.3Hurt

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