Fangyin Wei

fwei@princeton.edu

I am a second-year Ph.D. student in the Computer Science department at Princeton University. Now at Princeton, I feel super lucky to be co-advised by professor Szymon Rusinkiewicz and professor Thomas Funkhouser. Prior to joining Princeton, I got my Bachelor's Degree in Intelligence Science and Technology from Peking University in 2018. I am currently interested in visual and 3D understanding of the world through learning. I was a research intern at Google, Sensetime Group Limited, Stanford University (advised by Prof. Leonidas Guibas), and Microsoft Research Asia.


Publications

RSA ADA-Tucker: Compressing deep neural networks via adaptive dimension adjustment tucker decomposition
Zhisheng Zhong, Fangyin Wei, Zhouchen Lin, Chao Zhang
Neural Networks 110: 104-115, 2019  
paper / bibtex 
@article{DBLP:journals/nn/ZhongWLZ19,
  author    = {Zhisheng Zhong and
               Fangyin Wei and
               Zhouchen Lin and
               Chao Zhang},
  title     = {ADA-Tucker: Compressing deep neural networks via adaptive dimension
               adjustment tucker decomposition},
  journal   = {Neural Networks},
  volume    = {110},
  pages     = {104--115},
  year      = {2019},
  url       = {https://doi.org/10.1016/j.neunet.2018.10.016},
}
integral regression Integral Human Pose Regression
Xiao Sun, Bin Xiao, Fangyin Wei, Shuang Liang, Yichen Wei
European Conference of Computer Vision (ECCV), 2018  
paper / code / bibtex 
@InProceedings{sun2017integral,
  author    = {Xiao Sun and
               Bin Xiao and
	       Fangyin Wei and
               Shuang Liang and
               Yichen Wei},
  title     = {Integral Human Pose Regression},
  booktitle = {ECCV},
  year      = {2018}
  }
D^2AE Exploring Disentangled Feature Representation Beyond Face Identification
Yu Liu*, Fangyin Wei*, Jing Shao*, Lu Sheng, Junjie Yan, Xiaogang Wang
Computer Vision and Pattern Recognition (CVPR), 2018  
paper/ page / poster / bibtex 
@InProceedings{liu2018exploring,
  title={Exploring Disentangled Feature Representation Beyond Face Identification},
  author={Liu, Yu and Wei, Fangyin and Shao, Jing and Sheng, Lu and Yan, Junjie and Wang, Xiaogang},
  booktitle={CVPR},
  year={2018}
}
RSA Recurrent Scale Approximation for Object Detection in CNN
Yu Liu, Hongyang Li , Junjie Yan, Fangyin Wei, Xiaogang Wang, Xiaoou Tang
International Conference of Computer Vision (ICCV), 2017  
paper / code / bibtex 
@InProceedings{liu2018rsa,
  title={Recurrent Scale Approximation for Object Detection in {CNN}},
  author={Yu Liu and
          Hongyang Li and
          Junjie Yan and
          Fangyin Wei and
          Xiaogang Wang and
          Xiaoou Tang},
  booktitle={ICCV},
  year={2017}
}