AI RESEARCH
Multimodal Confidence Modeling in Audio-Visual Quality Assessment
arXiv CS.CV
•
ArXi:2605.01219v1 Announce Type: cross Audio-visual quality assessment (AVQA) is essential for streaming, teleconferencing, and immersive media. In realistic streaming scenarios, distortions are often asymmetric, where one modality may be severely degraded while the other remains clean. Still, most contemporary AVQA metrics treat audio and video as equally reliable, causing confidence-unaware fusion to emphasize unreliable signals.