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.
(2022) T-V 33.3 66.7 34.0 68.7 31.9 72.0 - - OmniVL Wang et al
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 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.