Image Patch Splitting
Image Patch Splitting is a computational method in computer vision that partitions an input image into non-overlapping local regions, or patches, to facilitate downstream tasks such as feature extraction, attention modeling, or sequence processing in transformer-based architectures.
16
Publications
1.7K
Citations
73
Authors
27
Institutions
Publications per year
2017–2026
12
Parents
16
EAPT: Efficient Attention Pyramid Transformer for Image Processing
Xiao Lin, Shuzhou Sun, Wei Huang et al. · IEEE Transactions on Multimedia · 2021 · 562 citations
DPT: Deformable Patch-based Transformer for Visual Recognition
Zhiyang Chen, Yousong Zhu, Chaoyang Zhao et al. · 2021 · 111 citations · Full text
1–5 of 16
73
2
h-index
2
h-index
2
h-index
1
h-index
1
h-index
1–5 of 73
27

Peking University
Beijing, China
2 h-index
4 publications
525 citations

The University of Sydney
Sydney, Australia
2 h-index
5 publications
1.1K citations

Shanghai Jiao Tong University
Shanghai, China
1 h-index
1 publications
562 citations
Xinjiang University
Ürümqi, China
1 h-index
4 publications
52 citations

Cornell University
Ithaca, United States
1 h-index
1 publications
17 citations
Nanyang Technological University
Singapore, Singapore
1 h-index
3 publications
198 citations
Tencent (China)
Shenzhen, China
1 h-index
4 publications
268 citations
Institute of Art
Warsaw, Poland
1 h-index
1 publications
67 citations
1–8 of 27
Repository · 4 publications · 113 citations
4
h-index
1 publications · 29 citations
1
h-index
1 publications · 30 citations
1
h-index
1 publications · 40 citations
1
h-index
1 publications · 562 citations
1
h-index
1–5