Paper · 2022 · Open access

Three Things Everyone Should Know About Vision Transformers

Hugo Touvron, Matthieu Cord, Alaaeldin El-Nouby, Jakob Jozef Verbeek, Hervé Jeǵou

Lecture notes in computer science, 13684, 497–515 · Published 6 November 2022 · DOI 10.1007/978-3-031-20053-3_29

Open PDFView at the publisherCite this paper

In brief

“Three Things Everyone Should Know About Vision Transformers” is a 2022 paper by Hugo Touvron and 4 co-authors, published in Lecture notes in computer science. OpenAlex counts 221 citations as of 22 November 2026, which puts it in the top 2% of works published in 2022 by citations. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
221
Most cited in
2025 (68)
Field-weighted impact
10.66
References
84
Authors
5

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Touvron, H., Cord, M., El-Nouby, A., Verbeek, J. J., & Jeǵou, H. (2022). Three Things Everyone Should Know About Vision Transformers. Lecture notes in computer science, 13684, 497–515. https://doi.org/10.1007/978-3-031-20053-3_29

MLA 9

Touvron, Hugo, et al. “Three Things Everyone Should Know About Vision Transformers.” Lecture notes in computer science, vol. 13684, 2022, pp. 497–515. https://doi.org/10.1007/978-3-031-20053-3_29.

Chicago

Touvron, Hugo, Matthieu Cord, Alaaeldin El-Nouby, Jakob Jozef Verbeek, and Hervé Jeǵou. 2022. “Three Things Everyone Should Know About Vision Transformers.” Lecture notes in computer science 13684: 497–515. https://doi.org/10.1007/978-3-031-20053-3_29.

Harvard

Touvron, H. et al. (2022) ‘Three Things Everyone Should Know About Vision Transformers’, Lecture notes in computer science, 13684, pp. 497–515. doi:10.1007/978-3-031-20053-3_29.

IEEE

H. Touvron, M. Cord, A. El-Nouby, J. J. Verbeek, and H. Jeǵou, “Three Things Everyone Should Know About Vision Transformers,” Lecture notes in computer science, vol. 13684, pp. 497–515, 2022, doi: 10.1007/978-3-031-20053-3_29.

BibTeX

@article{touvron2022three,
  title     = {{Three Things Everyone Should Know About Vision Transformers}},
  author    = {Touvron, Hugo and Cord, Matthieu and El-Nouby, Alaaeldin and Verbeek, Jakob Jozef and Jeǵou, Hervé},
  journal   = {Lecture notes in computer science},
  year      = {2022},
  volume    = {13684},
  pages     = {497--515},
  doi       = {10.1007/978-3-031-20053-3_29},
  url       = {https://doi.org/10.1007/978-3-031-20053-3_29}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202277
20234949
20245757
20256868
20264040

Its field-weighted citation impact is 10.66: it has been cited 10.66 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • vision transformer
  • self-supervised pre-training
  • ImageNet
  • memory efficiency
  • computational efficiency

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Touvron, H., Cord, M., El-Nouby, A., Verbeek, J. J., & Jeǵou, H. (2022). Three Things Everyone Should Know About Vision Transformers. Lecture notes in computer science, 13684, 497–515. https://doi.org/10.1007/978-3-031-20053-3_29

How many times has this paper been cited?

221 times, according to OpenAlex on 22 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Hugo Touvron, Matthieu Cord, Alaaeldin El-Nouby, Jakob Jozef Verbeek, Hervé Jeǵou.

What is the DOI of this paper?

10.1007/978-3-031-20053-3_29, permanently at https://doi.org/10.1007/978-3-031-20053-3_29. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 22 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.