The authors define a joint generalized cosine similarity from the Gram determinant and use it in a contrastive loss called GHA to align three or more modalities in one step.
Unified cross-modal attention: robust audio-visual speech recognition and beyond,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.AP 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning
The authors define a joint generalized cosine similarity from the Gram determinant and use it in a contrastive loss called GHA to align three or more modalities in one step.