Concepedia

Vision Transformers

Vision Transformer is a deep learning model that adapts the transformer architecture, originally designed for natural language processing, to image classification by treating image patches as sequential tokens and leveraging self-attention mechanisms to capture global spatial dependencies.

2K

Publications

209.1K

Citations

6.2K

Authors

1.4K

Institutions

Publications per year

2017–2026

2K

Parents

Publications

2K

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

Ze Liu, Yutong Lin, Yue Cao et al. · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 2021 · 30.1K citations

, , +16

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov et al. · arXiv (Cornell University) · 2020 · 21.6K citations · Full text

, , +14

A ConvNet for the 2020s

Zhuang Liu, Hanzi Mao, Chao-Yuan Wu et al. · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 2022 · 7.1K citations

, , +12

Emerging Properties in Self-Supervised Vision Transformers

Mathilde Caron, Hugo Touvron, Ishan Misra et al. · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 2021 · 5K citations · Full text

, , +13

Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions

Wenhai Wang, Enze Xie, Xiang Li et al. · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 2021 · 4.7K citations

, , +12

1–5 of 2K

Authors

6.2K

  1. JF
    Jiashi Feng

    National University of Singapore, Singapore

    17 publications · 5K citations

    16

    h-index

  2. DT
    Dacheng Tao

    The University of Sydney, Australia

    18 publications · 1.8K citations

    15

    h-index

  3. LY
    Lu Yuan

    Microsoft Research (United Kingdom), United Kingdom

    13 publications · 2.1K citations

    13

    h-index

  4. XZ
    Xiaohua Zhai

    Google (United States), United States

    14 publications · 25.4K citations

    13

    h-index

  5. XW
    Xinggang Wang

    Huazhong University of Science and Technology, China

    10 publications · 1.1K citations

    12

    h-index

1–5 of 6.2K

Institutions

1.4K

  1. Tsinghua University

    Beijing, China

    36 h-index

    109 publications

    48.2K citations

  2. Chinese Academy of Sciences

    Beijing, China

    33 h-index

    139 publications

    13.4K citations

  3. University of Chinese Academy of Sciences

    Beijing, China

    31 h-index

    101 publications

    13K citations

  4. Google (United States)

    Mountain View, United States

    28 h-index

    131 publications

    235.7K citations

  5. Zhejiang University

    Hangzhou, China

    24 h-index

    81 publications

    7.5K citations

  6. National University of Singapore

    Singapore, Singapore

    22 h-index

    50 publications

    25.2K citations

  7. University of Science and Technology of China

    Hefei, China

    21 h-index

    55 publications

    37.8K citations

  8. The University of Sydney

    Sydney, Australia

    21 h-index

    55 publications

    9.2K citations

1–8 of 1.4K

Venues

  1. arXiv (Cornell University)

    Repository · 373 publications · 45.6K citations

    78

    h-index

  2. 60

    h-index

  3. IEEE Access

    48 publications · 2.6K citations

    35

    h-index

  4. 33

    h-index

  5. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 38 publications · 3K citations

    30

    h-index

1–5