Fangyin Wei

fwei@princeton.edu

I am a third-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 Uber ATG, Google, Microsoft Research Asia, Stanford University (advised by Prof. Leonidas Guibas), and Sensetime Group Limited.

/


Publications

semantic edit

Learning to Infer Semantic Parameters for 3D Shape Editing

Fangyin Wei, Elena Sizikova, Avneesh Sud, Szymon Rusinkiewicz, Thomas Funkhouser
International Conference on 3D Vision (3DV), 2020  
paper / supplement / webpage / bibtex
@article{Chen:NLOS:2020,
title = {Learned Feature Embeddings for Non-Line-of-Sight Imaging and Recognition},
author = {Wenzheng Chen and Fangyin Wei and Kiriakos N. Kutulakos and Szymon Rusinkiewicz and Felix Heide},
year = {2020},
issue_date = {December 2020}, 
publisher = {Association for Computing Machinery}, 
volume = {39}, 
number = {6}, 
journal = {ACM Transactions on Graphics (Proc. SIGGRAPH Asia)}, 
}
            

NLOS Imaging

Learned Feature Embeddings for Non-Line-of-Sight Imaging and Recognition

Wenzheng Chen*, Fangyin Wei*, Kyros Kutulakos, Szymon Rusinkiewicz, Felix Heide
ACM Transactions on Graphics (Proc. SIGGRAPH Asia), 2020  
paper / supplement / webpage / code (coming out soon) / bibtex
@article{Chen:NLOS:2020,
title = {Learned Feature Embeddings for Non-Line-of-Sight Imaging and Recognition},
author = {Wenzheng Chen and Fangyin Wei and Kiriakos N. Kutulakos and Szymon Rusinkiewicz and Felix Heide},
year = {2020},
issue_date = {December 2020}, 
publisher = {Association for Computing Machinery}, 
volume = {39}, 
number = {6}, 
journal = {ACM Transactions on Graphics (Proc. SIGGRAPH Asia)}, 
}
            

NLOS Detection and Tracking

Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radar

Nicolas Scheiner*, Florian Kraus*, Fangyin Wei*, Buu Phan, Fahim Mannan, Nils Appenrodt, Werner Ritter, Jürgen Dickmann, Klaus Dietmayer, Bernhard Sick, Felix Heide
Computer Vision and Pattern Recognition (CVPR), 2020  
paper / webpage / code / bibtex
@InProceedings{scheiner2019seeing,
author={Scheiner, Nicolas and Kraus, Florian and Wei, Fangyin and Phan, Buu and Mannan, Fahim and Appenrodt, Nils and Ritter, Werner and Dickmann, Jurgen and Dietmayer, Klaus and Sick, Bernhard and others},
title={Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radar},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}
            

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/ webpage / 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}
}
            



Teaching


Teaching Assistant, COS 302: Mathematics for Numerical Computing and Machine Learning, Fall 2020

Teaching Assistant, COS 302: Mathematics for Numerical Computing and Machine Learning, Spring 2020

Teaching Assistant, COS 429: Computer Vision, Fall 2019