Journal article · 2022 · Open access

Transformers in Vision: A Survey

Salman Hameed Khan, Muzammal Naseer, Munawar Hayat, Syed Waqas Zamir, Fahad Shahbaz Khan, Mubarak A. Shah

ACM Computing Surveys, 54(10s), 1–41 · Published 31 January 2022 · DOI 10.1145/3505244

Open PDFView at the publisherCite this paper

In brief

“Transformers in Vision: A Survey” is a 2022 journal article by Salman Hameed Khan and 5 co-authors, published in ACM Computing Surveys. OpenAlex counts 4,779 citations as of 22 November 2026. It is open access under a CC BY-SA licence: the full text is free to read at arXiv (Cornell University).

Citations
4,779
Most cited in
2025 (1,310)
Field-weighted impact
219.51
References
308
Authors
6

Abstract

Astounding results from Transformer models on natural language tasks have intrigued the vision community to study their application to computer vision problems. Among their salient benefits, Transformers enable modeling long dependencies between input sequence elements and support parallel processing of sequence as compared to recurrent networks, e.g., Long short-term memory. Different from convolutional networks, Transformers require minimal inductive biases for their design and are naturally suited as set-functions. Furthermore, the straightforward design of Transformers allows processing multiple modalities (e.g., images, videos, text, and speech) using similar processing blocks and demonstrates excellent scalability to very large capacity networks and huge datasets. These strengths have led to exciting progress on a number of vision tasks using Transformer networks. This survey aims to provide a comprehensive overview of the Transformer models in the computer vision discipline. We start with an introduction to fundamental concepts behind the success of Transformers, i.e., self-attention, large-scale pre-training, and bidirectional feature encoding. We then cover extensive applications of transformers in vision including popular recognition tasks (e.g., image classification, object detection, action recognition, and segmentation), generative modeling, multi-modal tasks (e.g., visual-question answering, visual reasoning, and visual grounding), video processing (e.g., activity recognition, video forecasting), low-level vision (e.g., image super-resolution, image enhancement, and colorization), and three-dimensional analysis (e.g., point cloud classification and segmentation). We compare the respective advantages and limitations of popular techniques both in terms of architectural design and their experimental value. Finally, we provide an analysis on open research directions and possible future works. We hope this effort will ignite further interest in the community to solve current challenges toward the application of transformer models in computer vision.

Cite this paper

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

APA 7

Khan, S. H., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. A. (2022). Transformers in Vision: A Survey. ACM Computing Surveys, 54(10s), 1–41. https://doi.org/10.1145/3505244

MLA 9

Khan, Salman Hameed, et al. “Transformers in Vision: A Survey.” ACM Computing Surveys, vol. 54, no. 10s, 2022, pp. 1–41. https://doi.org/10.1145/3505244.

Chicago

Khan, Salman Hameed, Muzammal Naseer, Munawar Hayat, Syed Waqas Zamir, Fahad Shahbaz Khan, and Mubarak A. Shah. 2022. “Transformers in Vision: A Survey.” ACM Computing Surveys 54 (10s): 1–41. https://doi.org/10.1145/3505244.

Harvard

Khan, S. H. et al. (2022) ‘Transformers in Vision: A Survey’, ACM Computing Surveys, 54(10s), pp. 1–41. doi:10.1145/3505244.

IEEE

S. H. Khan, M. Naseer, M. Hayat, S. W. Zamir, F. S. Khan, and M. A. Shah, “Transformers in Vision: A Survey,” ACM Computing Surveys, vol. 54, no. 10s, pp. 1–41, 2022, doi: 10.1145/3505244.

BibTeX

@article{khan2022transformers,
  title     = {{Transformers in Vision: A Survey}},
  author    = {Khan, Salman Hameed and Naseer, Muzammal and Hayat, Munawar and Zamir, Syed Waqas and Khan, Fahad Shahbaz and Shah, Mubarak A.},
  journal   = {ACM Computing Surveys},
  year      = {2022},
  volume    = {54},
  number    = {10s},
  pages     = {1--41},
  doi       = {10.1145/3505244},
  url       = {https://doi.org/10.1145/3505244}
}

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

Citations by year

YearCitationsShare of the best year
201911
2021139139
2022402402
2023783783
20241,0551055
20251,3101310
20261,0891089

Its field-weighted citation impact is 219.51: it has been cited 219.51 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-attention
  • pre-training
  • image classification
  • object detection
  • human action recognition
  • semantic segmentation
  • generative models

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?

Khan, S. H., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. A. (2022). Transformers in Vision: A Survey. ACM Computing Surveys, 54(10s), 1–41. https://doi.org/10.1145/3505244

How many times has this paper been cited?

4,779 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?

Salman Hameed Khan, Muzammal Naseer, Munawar Hayat, Syed Waqas Zamir, Fahad Shahbaz Khan, Mubarak A. Shah.

What is the DOI of this paper?

10.1145/3505244, permanently at https://doi.org/10.1145/3505244. 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.