A sound localization model trained with MLLM-generated foreground and background captions and two new losses better distinguishes sounding objects from visually similar silent ones.
Vggsound: A large-scale audio-visual dataset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Object-aware Sound Source Localization via Audio-Visual Scene Understanding
A sound localization model trained with MLLM-generated foreground and background captions and two new losses better distinguishes sounding objects from visually similar silent ones.