Yin Li (李寅)

I am an Assistant Professor in the Department of Biostatistics and Medical Informatics and affiliate faculty in the Department of Computer Sciences at the University of Wisconsin-Madison. My primary research focus is computer vision. I am also interested in the applications of vision and learning for healthcare

Previously, I was a postdoc at Carnegie Mellon University working with Abhinav Gupta. I obtained my Ph.D. in Computer Science from Georgia Tech in 2017. My advisor was James Rehg. In 2015, I interned with Piotr Dollár and Manohar Paluri at Facebook AI Research. I received my M.S. in Pattern Recognition and Machine Intelligence from Shanghai Jiao Tong University and my B.S. in Information Science from Nanjing University of Posts and Telecommunications.

Contact info.:
Office address: 6730 MSC Building, UW-Madison
E-mail: yin_dot_li_at_wisc_dot_edu 



1 Research Interests

2 Education

3 Projects
4 Publications
Research Interests
Computer Vision, Mobile Health, Machine Learning, Wearable Computing 


          Aug. 2011 – Aug. 2017                                                 Ph.D. School of Interactive Computing, College of Computing
                                                                                                   Georgia Institute of Technology

Sep. 2008 – Mar. 2011                                                M.Sc. Institute of Image Processing and Pattern Recognition, School of SEIEE,
                                                                                         Shanghai Jiao Tong University (SJTU)                    
Sep. 2004– Jun. 2008                                                 B.Sc.  Department of Science, Nanjing University of Posts and Telecommunications(NUPT)
                                                                                         Major: Information and Science Computing             

Highlighted Projects


  • Yin Li, Miao Liu, James M. Rehg. In the Eye of Beholder: Joint Learning of Gaze and Actions in First Person Vision, accepted by European Conference on Computer Vision (ECCV) 2018
  • Keizo Kato, Yin Li, Abhinav Gupta. Compositional Learning of Human Object Interactions, accepted by European Conference on Computer Vision (ECCV) 2018
  • Adithyavairavan Murali, Yin Li, Dhiraj Gandhi, Abhinav Gupta. Learning to Grasp without Seeing, accepted by International Symposium on Experimental Robotics (ISER) 2018 [arXiv] [project page]
  • Yupei Wang, Xin Zhao, Yin Li, Xuecai Hu, Kaiqi Huang. Densely Cascaded Shadow Detection Network via Deeply Supervised Parallel Fusion, International Joint Conference on Artificial Intelligence (IJCAI) 2018 [pdf]
  • Abhijit Kundu, Yin Li, James M. Rehg. 3D-RCNN: Instance-level 3D Object Reconstruction via Render-and-Compare​, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018 (oralacceptance rate 2.1%) [pdf] [project page]
  • Liwei Wang, Yin Li, Jing Huang, Svetlana Lazebnik. Learning two-branch neural networks for image-text matching tasks, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2018 [arXiv]
  • Junchi Yan, Changsheng Li, Yin Li, Guitao Cao. Adaptive Discrete Hypergraph Matching, IEEE Transactions on Cybernetics (TCYB) 2018 [link]
  • Sarah R. Edmunds, Agata Rozga, Yin Li, Elizabeth A. Karp, Lisa V. Ibanez, James M. Rehg, Wendy L. Stone. Using a Point-of-View Camera to Measure Eye Gaze in Young Children with Autism Spectrum Disorder During Naturalistic Social Interactions: A Pilot Study, Journal of Autism and Developmental Disorders (JADD) 2017 [link]
  • Yun C. Zhang, Yin Li, James M. Rehg. First-person action decomposition and zero-shot learning, IEEE Winter Conference on Applications of Computer Vision (WACV) 2017
  • Yin Li, Manohar Paluri, James M. Rehg, Piotr Dollár. Unsupervised Learning of Edges, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016 (oralacceptance rate 3.9%) [arXiv] [project page]
  • Liwei Wang, Yin LiSvetlana Lazebnik. Learning Deep Structure-Preserving Image-Text EmbeddingsIEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016 [arXiv[code] [data splits]
  • Yin Li, Zhefan Ye, James M. Rehg. Delving into Egocentric Actions, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015 [pdf] [project page]
  • Jia Xu, Lopamudra Mukherjee, Yin Li, Jamieson Warner, James M. Rehg, Vikas Singh. Gaze-enabled Egocentric Video Summarization via Constrained Submodular MaximizationIEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015 [pdf] [project page]
  • Javier Hernandez, Yin Li, James M. Rehg, Rosalind W. Picard. Cardiac and Respiratory Parameter Estimation Using Head-mounted Motion-sensitive Sensors, EAI Endorsed Transactions on Pervasive Health and Technology,  Vol 15, Issue 1, 2015 [pdf]
  • Zhefan Ye, Yin Li, Yun Liu, Chanel Bridge, Agata Rozga, James M. Rehg. Detecting Bids for Eye Contact using a Wearable Camera, IEEE International Conference on Automatic Face and Gesture Recognition (FG) 2015 (oral) [pdf] [project pageBest Student Paper Award! (1/84)
  • Javier Hernandez, Yin Li, James M. Rehg, Rosalind W. Picard. BioGlass: Physiological Parameter Estimation Using a Head-mounted Wearable Device, International Conference on Wireless Mobile Communication and Healthcare (MobiHealth) 2014  [pdf] [Wired UK | New Scientist | MIT Tech Review] Best Student Paper Award! (1/120)
  • Junchi Yan, Yin Li, Wei Liu, Hongyuan Zha, Xiaokang Yang. Graduated Consistency-Regularized Optimization for Multi-Graph MatchingEuropean Conference on Computer Vision (ECCV) 2014 [pdf]
  • Abhijit Kundu, Yin Li, Frank Dellaert, Fuxin Li, James M. Rehg. Joint Semantic Segmentation and 3D Reconstruction from Monocular VideoEuropean Conference on Computer Vision (ECCV) 2014 [pdf] [project page]
  • Yin Li*, Xiaodi Hou*Christof Koch, James M. Rehg, Alan L. Yuille. The Secrets of Salient Object SegmentationIEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2014 [pdf[extended version] [project page] [codeNote: * indicates equal contribution.  
  • Yin Li, Alireza Fathi, James M. Rehg. Learning to Predict Gaze in Egocentric Video, International Conference on Computer Vision (ICCV) 2013 (oral, acceptance rate 2.5%) [pdf[project page]
  • James M. Rehg et al. Decoding Children's Social BehaviorIEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2013 [pdf] [dataset]
  • Alireza Fathi, Yin Li, James M. Rehg. Learning to Recognize Daily Actions using Gaze, European Conference on Computer Vision (ECCV) 2012 [pdf] [project page] [code]
  • Zhefan Ye, Yin Li, Alireza Fathi, Yi Han, Agata Rozga, Gregory D. Abowd, James M. Rehg. Detecting Eye Contact using Wearable Eye-Tracking Glasses, 2nd International Workshop on Pervasive Eye Tracking and Mobile Eye-Based Interaction (PETMEI) in conjunction with UbiComp 2012 [pdf] [media press] [SFARI] [award] [demo
  • Liwei Wang, Yin Li, Jiaya Jia, Jian Sun, David P. Wipf, James M. Rehg. Learning Sparse Covariance Patterns for Natural Scenes, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2012 [pdf] [code]
  • Yin Li, Junchi Yan, Yue Zhou and Jie Yang. Optimum Subspace Learning and Error Correction for Tensors, European Conference on Computer Vision (ECCV) 2010 [pdf] [code
  • Yin Li, Yue Zhou, Junchi Yan, Jie Yang and Xiangjian He. Tensor Error Correction for Corrupted Values in Visual Data, IEEE International Conference on Image Processing (ICIP) 2010 (invited) [pdf] [code
  • Yin Li, Yue Zhou, Lei Xu, Jie Yang and Xiaochao Yang. Incremental Sparse Saliency Detection, IEEE International Conference on Image Processing (ICIP) 2009 (oral) [pdf] [project page] [slides] [code]
  • Yin Li, Yue Zhou, Junchi Yan, Zhibin Liu and Jie Yang. Visual Saliency Based on Conditional Entropy, Asian Conference on Computer Vision (ACCV) 2009 (oral) [pdf] [project page] [slides] [code]
  • Lv Guo, Yin Li, Jie Yang and Li Lu. Exploration into Single Image Super-resolution via Self Similariy by Sparse Coding, IEICE Transactions on Information and Systems Vol.E93-D, No.11, Nov. 2010 [link
  • Junchi Yan, Yin Li, Enliang Zheng and Xuncai Liu. An Accelerated Human Motion Tracking System Based on Voxel Reconstruction under Complex Environments, Asian Conference on Computer Vision (ACCV) 2009 [pdf] [project page]
  • Yue Zhou, Yin Li, Zheng Wu and Meilin Ge. Robust Facial Feature Points Extraction In Color Images, Engineering Applications of Artificial Intelligence, Vol 24, Issue 1, Feb. 2011, Pages 195–200 [link]
  • Junchi Yan, Jian Liu, Yin Li, Zhibin Niu, Yuncai Liu. Visual Saliency Detection via Rank-Sparsity Decomposition. IEEE International Conference on Image Processing (ICIP) 2010 [link[code available upon request]