Pith. sign in

Virtex: Learning visual representations from textual annotations, 2021

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

Learning Visual Composition through Improved Semantic Guidance

cs.CV · 2024-12-19 · conditional · novelty 6.0

Recaptioning training images with a multimodal model and replacing CLIP's text tower with a large language model makes a standard contrastive model state-of-the-art on composition and retrieval benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Learning Visual Composition through Improved Semantic Guidance cs.CV · 2024-12-19 · conditional · none · ref 7

    Recaptioning training images with a multimodal model and replacing CLIP's text tower with a large language model makes a standard contrastive model state-of-the-art on composition and retrieval benchmarks.