Profile image
Yandong Wen
Ph.D. Candidate
Dept. of Electrical and Computer Engineering
Carnegie Mellon University

About Me (CV)


I am a fourth-year Ph.D. candidate in Department of Electrical and Computer Engineering at Carnegie Mellon University (CMU), advised by Prof. Rita Singh and Prof. Bhiksha Raj.

Before coming to CMU, I was a visiting student in Multimedia Laboratory at Shenzhen Institute of Advanced Technology, advised by Zhifeng Li and Yu Qiao. I got my M.Eng degree from School of Electronic and Information Engineering, South China University of Technology in 2016, where I received the B.Eng degree in 2013. My advisor is Prof. Yuli Fu.

My research interests mainly focus on deep learning and its applications on computer vision and speech analysis. I am super fortunate to work closely with Weiyang Liu and Kaipeng Zhang.

Education


Ph.D. Candidate, Carnegie Mellon University
Electrical and Computer Engineering
Sep. 2016 - Present
Advisors: Prof. Rita Singh and Prof. Bhiksha Raj
B.Eng. & M.Eng., South China University of Technology
Electronic and Information Engineering
Sep. 2009 - July 2016
Advisor: Yuli Fu

Experience


Graduate Student Researcher
Machine Learning For Signal Processing Group
Carnegie Mellon University
Sept. 2016 - Present
Visiting Student
Multimedia Laboratory
Shenzhen Institutes of Advanced Technology
May 2015 - August 2016

Publications


Face Reconstruction from Voice using Generative Adversarial Networks
Yandong Wen, Rita Singh, and Bhiksha Raj
Conference on Neural Information Processing Systems (NeurIPS) 2019
Conference
Paper Code Poster Poster


Disjoint Mapping Network for Cross-modal Matching of Voices and Faces
Yandong Wen, Mahmoud Al Ismail, Weiyang Liu, Bhiksha Raj, and Rita Singh
International Conference on Learning Representations (ICLR) 2019
Conference
Paper Poster


A Comprehensive Study on Center Loss for Deep Face Recognition
Yandong Wen*, Kaipeng Zhang*, Zhifeng Li, and Yu Qiao
International Journal of Computer Vision
Journal
Paper Code


A Corrective Learning Approach for Text-Independent Speaker Verification
Yandong Wen, Tianyan Zhou, Bhiksha Raj, and Rita Singh
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2018
Conference
Paper Slices


SphereFace: Deep Hypersphere Embedding for Face Recognition
Weiyang Liu*, Yandong Wen*, Zhiding Yu, Ming Li, Bhiksha Raj and Le Song
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017
Conference
Paper Poster Code Demo


A Discriminative Deep Feature Learning Approach for Face Recognition
Yandong Wen, Kaipeng Zhang, Zhifeng Li and Yu Qiao
European Conference on Computer Vision (ECCV) 2016
Conference
Paper Poster Code


Large-Margin Softmax Loss for Convolutional Neural Networks
Weiyang Liu*, Yandong Wen*, Zhiding Yu and Meng Yang
International Conference on Machine Learning (ICML) 2016
Conference
Paper Poster Code


Latent Factor Guided Convolutional Neural Networks for Age-Invariant Face Recognition
Yandong Wen, Zhifeng Li and Yu Qiao
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016
Conference
Paper Poster

Academic Services


Journal Reviewer: T-NNLS, T-IP, T-MM, T-IFS

Conference Reviewer: CVPR 18, AAAI 17