Dynamic Cross Attention for Audio-Visual Person Verification

arXiv:2403.04661v1 Announce Type: cross
Abstract: Although person or identity verification has been predominantly explored using individual modalities such as face and voice, audio-visual fusion has recently shown immense potential to outperform unimodal approaches. Audio and visual modalities are often expected to pose strong complementary relationships, which plays a crucial role in effective audio-visual fusion. However, they may not always strongly complement each other, they may also exhibit weak complementary relationships, resulting in poor audio-visual feature representations. In this paper, we …

abstract arxiv attention audio cs.cv cs.lg cs.sd dynamic eess.as face fusion identity identity verification person relationships role type verification visual voice