Chenliang Xu
Associate Professor of Computer Science | University of Rochester
Rochester, NY, UNITED STATES
Xu is an expert in artificial intelligence (AI) and machine learning and computer vision, and augmented and virtual reality
Areas of Expertise (5)
AI
Virtual Reality
Augmented Reality
Artificial Intelligence and Machine Learning
Artificial Intelligence and Computer Vision
Links (2)
Biography
Chenliang Xu joined the faculty at the University of Rochester's Hajim School of Engineering and Applied Sciences in 2016 after receiving his PhD from the University of Michigan. His research interests include computer vision, robot perception, and artificial intelligence, and tackles interdisciplinary topics, including video understanding, audio-visual learning, vision and language, and methods for trustworthy AI. His work has focused primarily on the problems in high-level video understanding, such as video segmentation, activity recognition, and vision and language.
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 (3)
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 (2)
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.
