A new video-level benchmark and a temporally aware model show that tracking sound sources over time is necessary for robust audio-visual localization.
Soundnet: Learning sound representations from unlabeled video
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
What's Making That Sound Right Now? Video-centric Audio-Visual Localization
A new video-level benchmark and a temporally aware model show that tracking sound sources over time is necessary for robust audio-visual localization.