Abstract | ||
---|---|---|
Within Convolutional Neural Network (CNN), the convolution operations are good at extracting local features but experience difficulty to capture global representations. Within visual transformer, the cascaded self-attention modules can capture long-distance feature dependencies but unfortunately deteriorate local feature details. In this paper, we propose a hybrid network structure, termed Conform... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICCV48922.2021.00042 | 2021 IEEE/CVF International Conference on Computer Vision (ICCV) |
Keywords | DocType | ISBN |
Couplings,Representation learning,Visualization,Fuses,Convolution,Object detection,Transformers | Conference | 978-1-6654-2812-5 |
Citations | PageRank | References |
2 | 0.45 | 0 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhiliang Peng | 1 | 2 | 0.79 |
Wei Huang | 2 | 2 | 0.45 |
Shanzhi Gu | 3 | 2 | 0.45 |
Ling-Xi Xie | 4 | 429 | 37.79 |
Yaowei Wang | 5 | 134 | 29.62 |
Jianbin Jiao | 6 | 367 | 32.61 |
Qixiang Ye | 7 | 913 | 64.51 |