Junyu Chen   陈俊宇

Email  /  Google Scholar

I am a first-year Ph.D. student in the Computer Science Department at the University of Rochester (UR), where I am advised by Prof. Christopher Kanan. Previously, I completed my master’s in Data Science at UR and bachelor’s at Peking University. My general research area is computer vision and continual learning.

profile photo


How Art-like are AI-generated Images? An Exploratory Study
Junyu Chen, Jie An, Hanjia Lyu, Jiebo Luo
ACMMM Workshop, 2023

This paper presents ArtScore, a metric designed to evaluate the degree to which an image resembles authentic artworks by artists (or conversely photographs).

Predicting Adverse Neonatal Outcomes for Preterm Neonates with Multi-Task Learning
Jingyang Lin, Junyu Chen, Hanjia Lyu, Igor Khodak, Divya Chhabra, Colby L Day Richardson, Irina Prelipcean, Andrew M Dylag, Jiebo Luo
ICDH, 2023

We propose an MTL (multi-task learning) framework to jointly predict multiple adverse neonatal outcomes.

Improving Visual-textual Sentiment Analysis by Fusing Expert Features
Junyu Chen, Jie An, Hanjia Lyu, Jiebo Luo
arXiv, 2022

We propose a new method that improves visual-textual sentiment analysis by introducing powerful expert visual features.


  • TA CSC 477 End-to-End Deep Learning - Fall 2023
  • Instructor Python 101 for REU - Summer 2023
  • TA CSC 440 Data Mining - Fall 2022

Template borrowed from Jon Barron. Thanks!