Generalizable Video Quality Assessment via Weak-to-Strong Learning 事件

Generalizable Video Quality Assessment via Weak-to-Strong Learning arXiv:2505.03631v5 Announce Type: replace Abstract: Video quality assessment (VQA) seeks to predict the perceptual quality of a video in alignment with human visual perception, serving as a fundamental tool for quantifying quality degradation across video processing workflows. The dominant VQA paradigm relies on supervised training with human-labeled datasets, which, despite substantial progress, still suffers from poor generali