AV-SAM: 模型将任何物体分割与视听定位相结合（英文版）

英文标题：AV-SAM: Segment Anything Model Meets Audio-Visual Localization and Segmentation中文摘要：本文提出了基于 SAM 模型的简单而有效的音频 - 视觉定位和分割框架 AV-SAM，可以生成对应于音频的听觉对象掩模，实现像声音定位和分割等视听任务。英文摘要：Segment Anything Model (SAM) has recently shown its powerful effectiveness invisual segmentation tasks. However, there is less exploration concerning howSAM works on audio-visual tasks, such as visual sound localization andsegmentation. In this work, we propose a simple yet effective audio-visuallocalization and segmentation fr