LightAVSeg decouples semantic filtering and spatial grounding to achieve linear-cost cross-modal interaction in audio-visual segmentation, reaching 50.4 mIoU on MS3 with 20.5M parameters as a new lightweight state-of-the-art.
Proceedings of the 32nd ACM International Conference on Multimedia , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
LightAVSeg: Lightweight Audio-Visual Segmentation
LightAVSeg decouples semantic filtering and spatial grounding to achieve linear-cost cross-modal interaction in audio-visual segmentation, reaching 50.4 mIoU on MS3 with 20.5M parameters as a new lightweight state-of-the-art.