Learning Transferable Models for Computer Vision via Image–Text Pre-training

Radford, A., Kim, & Hallacy. (2021). Learning Transferable Models for Computer Vision via Image–Text Pre-training. Proceedings of the 38th International Conference on Machine Learning.

Type

Conference paper

Intellectual base

Primary research

Year

2021

Link

no authoritative link yet

Cited from

linguistics_semiotics

Cited by

2 citations across 2 artifacts.

Each citation links to the sentence it supports in the citing article.

Primes

• Icon–Index–Symbol Distinction
  • T6b — Multimodal AI and Peircean sign-types. Recent multimodal models (CLIP, LLaVA, GPT-4V) implement iconic (image-matching), indexical (correlation-detection), and symbolic (language-based) operations simultaneously.

    This sourceRadford CLIP multimodal vision-language iconic indexical symbolic AI.

• Iconicity
  • Multimodal AI and vision-language models: Radford et al. (2021, CLIP)

    This sourceRadford CLIP multimodal vision-language model implicit iconic alignment.

Verification

This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.

Registry ID ref:33b9e2f4abd8 · see in the full table