#artificial intelligence
Oct 2025
Taming Modality Entanglement in Continual Audio-Visual Segmentation
A novel Continual Audio-Visual Segmentation (CAVS) task, aiming to continuously segment new classes guided by audio, and a Collision-based Multi-modal Rehearsal (CMR) framework, designed to address challenges of multi-modal semantic drift and co-occurrence confusion.
Yuyang Hong, Qi Yang, Tao Zhang et al.
· arXiv.org · 3 citations
· ⚡1