Pith. sign in

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 1

years

2024 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Gramian Multimodal Representation Learning and Alignment

cs.CV · 2024-12-16 · conditional · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Gramian Multimodal Representation Learning and Alignment cs.CV · 2024-12-16 · conditional · none · ref 5

    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.