pith. sign in

arxiv: 2404.09509 · v1 · pith:Y4IMBEQW · submitted 2024-04-15 · cs.CV

Fuse after Align: Improving Face-Voice Association Learning via Multimodal Encoder

pith:Y4IMBEQWopen to challenge →

classification cs.CV
keywords learningmatchingcontrastiveretrievalassociationeffectiveembeddingsencoder
0
0 comments X
read the original abstract

Today, there have been many achievements in learning the association between voice and face. However, most previous work models rely on cosine similarity or L2 distance to evaluate the likeness of voices and faces following contrastive learning, subsequently applied to retrieval and matching tasks. This method only considers the embeddings as high-dimensional vectors, utilizing a minimal scope of available information. This paper introduces a novel framework within an unsupervised setting for learning voice-face associations. By employing a multimodal encoder after contrastive learning and addressing the problem through binary classification, we can learn the implicit information within the embeddings in a more effective and varied manner. Furthermore, by introducing an effective pair selection method, we enhance the learning outcomes of both contrastive learning and the matching task. Empirical evidence demonstrates that our framework achieves state-of-the-art results in voice-face matching, verification, and retrieval tasks, improving verification by approximately 3%, matching by about 2.5%, and retrieval by around 1.3%.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Missing-Token Prompted Reliability-Aware Fusion for Robust Polyglot Speaker Identification

    cs.SD 2026-06 unverdicted novelty 5.0

    MRAF framework uses missing-token prompting and reliability-aware cross-attention fusion to achieve 100% accuracy on some POLY-SIM 2026 tasks and competitive results on missing-face cases.