Computer Science Faculty
Yuan Yuan
Assistant Professor
Yuan Yuan
Ph.D.
Contact
245 Beacon Street 528E
Telephone: 617-552-6157
Email: yuanyua@bc.edu
Education
- Ph.D., Hong Kong University of Science and Technology
- B.S., Huazhong University of Science and Technology
Research Interests
- Machine Learning
- Deep Learning
- Computer Vision
- AI for Healthcare
Department
Biography
Yuan聽Yuan聽is an Assistant Professor of Computer Science at Boston College. Previously, she was a postdoctoral research associate at MIT CSAIL. Before her time at MIT, she obtained her Ph.D. degree from the Hong Kong University of Science and Technology and was a visiting research scholar at the Robotics Institute of Carnegie Mellon University.
Her research primarily focuses on deep learning, computer vision, and the application of AI in healthcare and medicine. Her work has attracted widespread media attention, featuring in outlets such as Forbes, The Washington Post, B情色空间, TechCrunch, and Engadget, among others. Remarkably, her work on an AI-powered digital biomarker for the diagnosis and progression tracking of Parkinson's disease was recognized as one of the top ten notable advances in medicine of 2022.
SELECTED PUBLICATIONS
Continuous Invariance Learning.聽Yong Lin, Fan Zhou, Lu Tan, Lintao Ma, Jianmeng Liu, Yansu He,聽Yuan聽Yuan, Yu Liu, James Y. Zhang, Yujiu Yang, Hao Wang.聽International Conference on Learning Representations (ICLR), Vienna, Austria, 2024.
TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut.聽Yangtao Wang, Xi Shen,聽Yuan聽Yuan, Yuming Du, Maomao Li, Xu Hu, James Crowley and Dominique Vaufreydaz.聽IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023.
Artificial Intelligence Detects Parkinson鈥檚 Disease and Estimates Disease Severity and Progression from Nocturnal Breathing.聽聽Yuzhe Yang*,聽Yuan聽Yuan*, Guo Zhang, Hao Wang, Ying-Cong Chen, Yingcheng Liu, Christopher G. Tarolli, Daniel Crepeau, Jan Bukartyk, Mithri R. Junna, Aleksandar Videnovic, Terry D. Ellis, PT, Melissa C. Lipford, Ray Dorsey and Dina Katabi.聽(* corresponding authors)聽Nature Medicine, 2022.聽
Contactless Oxygen Monitoring with Radio Waves and Gated Transformer.聽聽Yuan聽Yuan*, Hao He*, Ying-Cong Chen*, Peng Cao and Dina Katabi. (* equal contribution)聽聽Machine Learning for Healthcare (MLHC), New York, USA, 2023.聽
Addressing Feature Suppression in Unsupervised Visual Representations.聽聽Tianhong Li*, Lijie Fan*,聽Yuan聽Yuan, Hao He, Yonglong Tian, Rogerio Feris, Piotr Indyk and Dina Katabi. (* equal contribution)聽Winter Conference on Applications of Computer Vision (WACV), Hawaii, USA, 2023
Targeted Supervised Contrastive Learning for Long-Tailed Recognition.聽聽Tianhong Li*, Peng Cao*,聽Yuan聽Yuan, Lijie Fan, Yuzhe Yang, Rogerio Feris, Piotr Indyk and Dina Katabi.聽Computer Vision and Pattern聽Recognition (CVPR), New Orleans, USA, 2022.聽
Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut.聽Yangtao Wang, Xi Shen, Xu Hu,聽Yuan聽Yuan, James Crowley and Dominique Vaufreydaz.聽Computer Vision and Pattern Recognition (CVPR), New Orleans, USA, 2022.
Unsupervised Learning for Human Sensing Using Radio Signals.聽Tianhong Li*, Lijie Fan*,聽Yuan聽Yuan*,聽and Dina Katabi. (* equal contribution)聽Winter Conference on Applications of Computer Vision (WACV), Hawaii, USA, 2022.
Subgroup-based Rank-1 Lattice Quasi-Monte Carlo.聽聽Yueming Lyu,聽Yuan聽Yuan聽and Ivor W. Tsang.聽Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), virtual, 2020.聽
In-Home Daily-Life Captioning Using Radio Signals.聽聽Lijie Fan*, Tianhong Li*,聽Yuan聽Yuan, and Dina Katabi.聽European Conference on Computer Vision (ECCV), virtual, 2020.聽(Oral)
Learning Longterm Representations for Person Re-Identification Using Radio Signals.聽Lijie Fan*, Tianhong Li*, Rongyao Fang*, Rumen Hristov,聽Yuan聽Yuan聽and Dina Katabi.聽Computer Vision and Pattern Recognition (CVPR), virtual, 2020.
Marginalized Average Attentional Network For Weakly-Supervised Learning.聽Yuan聽Yuan, Yueming Lyu, Xi Shen, Ivor W. Tsang and Dit-Yan Yeung.聽International Conference on Learning Representations (ICLR), New Orleans, USA, 2019.
Temporal Dynamic Graph LSTM for Action-driven Video Object Detection.聽聽Yuan聽Yuan, Xiaodan Liang, Xiaolong Wang, Dit-Yan Yeung and Abhinav Gupta.聽International Conference on Computer Vision (ICCV), Venice, Italy, 2017.聽