Audio-Visual Person Verification based on Recursive Fusion of Joint Cross-Attention

arXiv:2403.04654v1 Announce Type: new
Abstract: Person or identity verification has been recently gaining a lot of attention using audio-visual fusion as faces and voices share close associations with each other. Conventional approaches based on audio-visual fusion rely on score-level or early feature-level fusion techniques. Though existing approaches showed improvement over unimodal systems, the potential of audio-visual fusion for person verification is not fully exploited. In this paper, we have investigated the prospect of effectively capturing both the intra- and inter-modal …

abstract arxiv attention audio cs.cv cs.sd eess.as feature fusion identity identity verification improvement person recursive type verification visual voices