Masked Image Modeling
Masked Image Modeling is a self-supervised learning framework that belongs to the class of pretext tasks in computer vision, distinguished by its strategy of reconstructing randomly masked image patches from the visible portions of an input image to learn expressive visual representations.
119
Publications
8.1K
Citations
554
Authors
138
Institutions
Publications per year
2017–2026
114
Parents
119
BEiT: BERT Pre-Training of Image Transformers
Hangbo Bao, Dong Li · arXiv (Cornell University) · 2021 · 927 citations · Full text
iBOT: Image BERT Pre-Training with Online Tokenizer
Jinghao Zhou, Huiyu Wang, Wei Shen et al. · arXiv (Cornell University) · 2021 · 210 citations · Full text
1–5 of 119
554
7
h-index
6
h-index
4
h-index
4
h-index
4
h-index
1–5 of 554
138

Chinese Academy of Sciences
Beijing, China
6 h-index
36 publications
4.5K citations
Microsoft Research Asia (China)
Beijing, China
6 h-index
28 publications
7.8K citations
University of Chinese Academy of Sciences
Beijing, China
5 h-index
21 publications
2.9K citations
Tsinghua University
Beijing, China
5 h-index
13 publications
3.3K citations

Hong Kong University of Science and Technology
Hong Kong, Hong Kong
4 h-index
6 publications
576 citations
Shanghai Artificial Intelligence Laboratory
Shanghai, China
4 h-index
14 publications
676 citations
Beijing Academy of Artificial Intelligence
Beijing, China
4 h-index
10 publications
770 citations
Chinese University of Hong Kong
Hong Kong, Hong Kong
4 h-index
8 publications
373 citations
1–8 of 138
Repository · 34 publications · 2K citations
17
h-index
11 publications · 1K citations
10
h-index
Conference · 4 publications · 149 citations
4
h-index
3 publications · 48 citations
3
h-index
Conference · 3 publications · 1.5K citations
3
h-index
1–5