A new audio-visual instance segmentation architecture, using audio separation and an audio-modulated Mamba, reaches 48.54 mAP on AVISeg with a COCO-pretrained ResNet50.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MM 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hear to See: Discerning Stateful Listening for Audio-Visual Instance Segmentation
A new audio-visual instance segmentation architecture, using audio separation and an audio-modulated Mamba, reaches 48.54 mAP on AVISeg with a COCO-pretrained ResNet50.