GRAM replaces cosine similarity with the Gramian volume of the parallelotope formed by multiple modality embeddings, and a volume-based contrastive loss improves multimodal retrieval and classification.
Learning audio-video modalities from image captions
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Gramian Multimodal Representation Learning and Alignment
GRAM replaces cosine similarity with the Gramian volume of the parallelotope formed by multiple modality embeddings, and a volume-based contrastive loss improves multimodal retrieval and classification.