AI RESEARCH
EAR: Enhancing Uni-Modal Representations for Weakly Supervised Audio-Visual Video Parsing
arXiv CS.CV
•
ArXi:2605.08723v1 Announce Type: new Weakly supervised Audio-Visual Video Parsing (AVVP) aims to recognize and temporally localize audio, visual, and audio-visual events in videos using only coarse-grained labels. Faced with the challenging task settings, existing research advances along two main paths: pre-