Kan Wu

Rethinking and Improving Relative Position Encoding for Vision Transformer

Kan Wu, Houwen Peng, Minghao Chen et al. · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 2021 · 359 citations

Computing, Computer Science, Computer Vision +14

LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search

Bin Yan, Houwen Peng, Kan Wu et al. · 2021 · 239 citations

Computing, Computer Engineering, Computer Science +13

MiniViT: Compressing Vision Transformers with Weight Multiplexing

Jinnian Zhang, Houwen Peng, Kan Wu et al. · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 2022 · 116 citations

Computing, Computer Engineering, Computer Science +13

Tooth segmentation on dental meshes using morphologic skeleton

Kan Wu, Li Chen, Jing Li et al. · Computers & Graphics · 2013 · 83 citations

Dentistry, Oral Radiology, Oral Anatomy +7

Rethinking and Improving Relative Position Encoding for Vision Transformer

Kan Wu, Houwen Peng, Minghao Chen et al. · arXiv (Cornell University) · 2021 · 24 citations · Full text

Computing, Computer Science, Computer Vision +14