Skip to main content
Search

# Audio-Visual Segmentation

1 related articles

Subscribe to updates
  1. arXiv

    When identical objects share the frame, which one is sounding? Binaural cues lift instance mIoU by 35.19 points

    When several same-class objects appear in one view, existing audio-visual segmentation methods typically return sound-related regions or category masks and cannot say which instance is producing the sound. BiSID-AVS turns source-direction information in binaural audio into an image-plane spatial response and conditions mask formation at both the feature and decoder levels; on the multi-candidate subsets of the binaurally extended AVS-Synthetic and Habitat-AVS, instance-level mIoU improves by 35.19 and 41.21 percentage points, with markedly less false activation on non-sounding same-class regions.

You’re all caught up