# Radford 2021: Learning Transferable Visual Models From Natural Language Supervision

> Alec Radford, Jong Wook Kim, Chris Hallacy et al., 2021. 2 records on Mysteries Department cite it. The surveys propose CLIP-style embeddings for…

Source: https://mysteriesdept.com/sources/SRC0D8MSPAE61XH/learning-transferable-visual-models-from-natural-language  
Publisher: Mysteries Department  
Licence: CC BY 4.0 (credit Mysteries Department and link the page)  

---

[Sources](https://mysteriesdept.com/sources)[Voynich Manuscript](https://mysteriesdept.com/mysteries/voynich-manuscript)Radford 2021

**0**

# Learning Transferable Visual Models From Natural Language Supervision

Alec Radford, Jong Wook Kim, Chris Hallacy et al., 2021. _Proceedings of ICML 2021_.

Introduces CLIP, a model that learns to match images with text by training on a large collection of image-caption pairs.

**Voynich Manuscript** ArticleChecked against the original0

## What it's used for here

The surveys propose CLIP-style embeddings for clustering glyphs and as an alternative to hand-coding the herbal drawings when matching text to images.

## Cited by on this site 2 records

[2 methods surveys]

Mathematics, inductive methods

SRC

## Cite it

```
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning Transferable Visual Models From Natural Language Supervision. Proceedings of ICML 2021. https://arxiv.org/abs/2103.00020
```

[Read it free at arxiv.org](https://arxiv.org/abs/2103.00020)

Key

**SRC** 0D8MSPAE61XH

Kind

Journal article

Rights

arXiv-nonexclusive

Checked

Against the published article

Added by

[apollo](https://mysteriesdept.com/u/apollo)

The record

Bibliographic records are CC0. Take this one as CSL-JSON, BibTeX or RIS.

[CSL-JSON](https://mysteriesdept.com/sources/SRC0D8MSPAE61XH/learning-transferable-visual-models-from-natural-language/csl.json)