
Chenliang Xu
Associate Professor of Computer Science University of Rochester
- Rochester NY
Xu is an expert in artificial intelligence (AI) and machine learning and computer vision, and augmented and virtual reality
Areas of Expertise
Biography
Xu is a recipient of the James P. Wilmot Distinguished Professorship (2021), the University of Rochester Research Award (2021), the "Best Paper Award" at the 17th ACM SIGGRAPH VRCAI Conference (2019), the "Best Paper Award" at the 14th Sound and Music Computing Conference (2017), and the University of Rochester AR/VR Pilot Award (2017). He has authored more than 100 peer-reviewed papers in computer vision, machine learning, multimedia, and AI venues. He served as an associate editor for IEEE Transactions on Multimedia and an area chair/reviewer for various international conferences.
At the University of Michigan, his dissertation advanced the uses of supervoxel hierarchies as a new type of generic video representation in video analysis. He built the first framework for streaming hierarchical segmentation of arbitrarily long videos with constant memory. He is currently working on a book project on video segmentation.
Education
University of Michigan, Ann Arbor
PhD
Computer Science
2016
University at Buffalo
MS
Computer Science
2012
Nanjing University of Aeronautics and Astronautics
BS
Information and Computing Science
2010
Selected Media Appearances
Are video deepfakes powerful enough to influence political discourse?
University of Rochester online
2024-10-22
Chenliang Xu, an expert in computer vision and deep learning at the University of Rochester, says that while generative artificial intelligence technology is rapidly advancing, deepfake video generation remains harder for bad actors to leverage due to its complex nature.

AI Analysis May Improve Vaping Cessation Efforts on Social Media
University of Rochester online
2024-09-01
University of Rochester Clinical and Translational Science Institute researchers are using natural language processing techniques and deep learning models to identify the key features of high-engagement social media posts related to e-cigarette products, collecting data from Twitter/X, Instagram, TikTok, and YouTube, where vaping and e-cigarette posts attract high user engagement.
