On a multilingual Indian speech dataset, dense token-level audio-visual matching beats global pooling by 59% relative Recall@1 and yields sharper zero-shot localization heatmaps.
Vo, Patrick Labatut, and Piotr Bojanowski
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
background 1representative citing papers
citing papers explorer
-
VeS: Teaching Pixels to Listen Without Supervision
On a multilingual Indian speech dataset, dense token-level audio-visual matching beats global pooling by 59% relative Recall@1 and yields sharper zero-shot localization heatmaps.