AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Seeking the Shape of Sound: An Adaptive Framework for Learning Voice-Face Association

Peisong Wen, Qianqian Xu, Yangbangyan Jiang, Zhiyong Yang, Yuan He, Qingming Huang

CVPR 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 35 citations (OpenAlex)

Check 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 the full two-level alignment and adaptive identity reweighting frameworkvoice-face association learning · 1:2 matching, verification and retrievalaccuracy, AUC, and mAPImproved
Add explicit modality alignment (ablation)voice-face association model · 1:2 matching and verification, especially gender-restricted queriesaccuracy and AUCImproved
Add implicit modality alignment (ablation)voice-face association model · 1:2 matchingaccuracyImproved
Add identity reweighting (ablation)voice-face association model · 1:2 matching and verificationaccuracy and AUC: +1%Improved
Add identity reweighting (ablation)voice-face association model · retrievalmAPHurt
Replace identity reweighting with focal loss (ablation)voice-face association model · 1:2 matching, verification and retrievalperformanceNo clear effect
Weight difficult identities without excluding extremely hard identities (R_keep 1.0, reweighting enabled) (ablation)voice-face association model · 1:2 matching V-F (U)accuracy: 85.5 -> 86.7Improved
Weight difficult identities without excluding extremely hard identities (R_keep 1.0, reweighting enabled) (ablation)voice-face association model · 1:2 matching F-V (U)accuracy: 85.2 -> 86.8Improved
Filter identities to retain 0.9 of them (ablation)identity-reweighted voice-face model · 1:2 matching V-F (U)accuracy: 86.7 -> 87.2Improved
Filter identities to retain 0.9 of them (ablation)identity-reweighted voice-face model · 1:2 matching F-V (U)accuracy: 86.8 -> 87.2Improved
Reduce retained identity ratio from 0.9 to 0.6 (ablation)identity-reweighted voice-face model · 1:2 matchingaccuracy: 87.2 -> 85.9; 87.2 -> 85.3Hurt
Increase retained identity ratio from 0.9 to 1.0 (ablation)identity-reweighted voice-face model · 1:2 matchingaccuracy: 87.2 -> 86.7; 87.2 -> 86.8Mixed

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