Selective convergence in contrastive audio-visual learning is exploited in a two-stage framework to localize dual sound sources without labels, with a new segmentation-mask evaluation benchmark.
In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
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
-
Whence the Voice? Self-supervised Dual-source Audio-Visual Localisation via Selective Convergence
Selective convergence in contrastive audio-visual learning is exploited in a two-stage framework to localize dual sound sources without labels, with a new segmentation-mask evaluation benchmark.