Chao Feng

I am a second-year master's student at the University of Michigan (UMich) majoring in Electrical and Computer Engineering (ECE) of EECS Department, advised by Prof. Andrew Owens.

I got my Bachelor's degree in Electronic Information Engineering from University of Electronic Science and Technology of China (UESTC), where I was advised by Prof. Shuaicheng Liu.

Email: chfeng at umich dot edu

I am currently applying for Ph.D. positions for Fall 2023!

Email  /  CV  /  Google Scholar  /  Github

profile photo
Research

I'm interested in computer vision, self-supervised learning, representation learning, audio-visual learning, multimodal learning, and image forensics. I am also open to other areas!

b3do Self-Supervised Video Forensics by Audio-Visual Anomaly Detection
Chao Feng, Ziyang Chen, Andrew Owens,
Under Review
project page / arXiv / code

We learn several feature sets in a self-supervised manner by using audio-visual synchronization task and utilize autoregressive model to do anomaly detection on top of each feature set for video forensics detection.

b3do ACML: Augmented Competitive Metric Learning for Image Ordinal Classification
Chao Zhang*, Chao Feng*, Jianmei Cheng, Shuaicheng Liu, Ce Zhu,
Under Review
project page / arXiv / code

We design a novel loss to embed ordinal information into training procedure and use augmented way to learn discriminative representation for image ordinal classification (IOC) task .

b3do AVA-AVD: Audio-Visual Speaker Diarization in the Wild
Eric Zhongcong Xu, Zeyang Song, Satoshi Tsutsui, Chao Feng, Mang Ye, Mike Zheng Shou,
ACM Multimedia, 2022
project page / arXiv / code

We create the AVA Audio-Visual Diarization (AVA-AVD) dataset to develop diarization methods for in-the-wild videos.

Side Projects
b3do NeRF implementation
code

b3do Image Super-Resolution
EECS 598 project
code

b3do MTCSNN: Multi-task Clinical Siamese Neural Network for Diabetic Retinopathy Severity Prediction
EECS 545 final project
code

Education
University of Michigan, M.S. in Electrical and Computer Engineering
Academic performance and related courses GPA: 4.0/4.0
EECS 504: Foundations of Computer Vision (A) Instructor: Andrew Owens
EECS 545: Machine Learning (CSE) (A) Instructors: Honglak Lee and MichaƂ DereziƄski
EECS 598: Deep Learning for Computer Vision (A+) Instructor: Justin Johnson
EECS 551: Matrix Methods for Signal Processing, Data Analysis and Machine Learning (A) Instructor: Jeffrey Fessler
EECS 501: Probability and Random Processes (A) Instructor: Lei Ying
EECS 498: Principles of Machine Learning (A) Instructor: Qing Qu
...
University of Electronic Science and Technology of China, B.Eng. in Electronic Information Engineering
Academic performance GPA: 88.79/100 (3.86/4.0)

Credit