Vision and Learning Lab @ U of A

	Dr. Li CHENG Associate Professor Email: lcheng5@ualberta.ca Lab Webpage: https://vision-and-learning-lab-ualberta.github.io/ Office phone: (780) 492-9305	ECE, University of Alberta 11-365 Donadeo Innovation Centre for Engineering 9211 - 116 Street NW Edmonton, AB, Canada T6G 1H9


What's new


[new!] an opening for Postdoc researcher in Computer Vision and Machine Learning.


Research Interests


I have been fascinated by many topics in computer vision and machine learning. My research interests in recent years have been more toward interpreting the visual behaviors of humans and animals from images and videos, biomedical image analysis, and geometric aspect of machine learning. Exemplar efforts can be found in the follow-up sections of Projects and Selected Publictions.






Brief Bio

I am an associate professor with the Department of Electrical and Computer Engineering, University of Alberta. I also hold an adjunct position with ASTAR, Singapore, where I have led a group in Machine Learning for Bioimage Analysis at the Bioinformatics Institute. Prior to joining University of Alberta in year 2018, I worked at ASTAR, Singapore, TTI-Chicago, USA, and NICTA, Australia. I received my BSc degree in Computer Science from Jilin University in 1996, M. Eng. degree from Nankai University in 1999, and PhD in Computing Science from the University of Alberta in 2004. My research expertise is mainly on computer vision and machine learning. I am a member of the Institute of Electrical and Electronics Engineers (IEEE), the Association for Computing Machinery (ACM), and the Association for the Advancement of Artificial Intelligence (AAAI). I have supervised or co-supervised a number of research students and postdocs. Many of them have taken scientist or engineer positions at the major tech companies (Google, Nvidia, Bosch, OmniVision, etc.) or hold faculty positions at prestigious universities (e.g. Southeast University of China, China University of Geosciences, University of Adelaide of Australia).



For Potential Graduate Students and Interns

I always look for self-motivated students with a strong computer science or computer engineering or mathematics/physics backgrounds who are interested to work on exciting computer vision and machine learning research topics to join my group. Potential PhD and MSc applicants may contact me directly. Students from China may also consider the China Scholarship Council (CSC) award. Short-term research internship is also possible through various funding sources. Please contact me regarding current opportunities.


Projects
Multivariate Regression with Gross Errors on Manifold-valued Data Transduction on Directed Graphs via Absorbing Random Walks Pose Estimation, Tracking, and Action Recognition of Articulated Object on Lie Groups Hand Pose Estimation from Single Depth Images, as well as In-house Hand Depth Image Dataset and Online Performance Evaluation Rodent Pose Estimation from Depth Images Action Recognition and Detection from Videos (e.g. hand actions and complex activities) Segmentation and Tracing of Filamentary Structured Objects (e.g. Neurites, Retinal Vessels), the Absorbing Markov Chain Foundation for our Tracing Algorithms, and Generating Filamentary Structured Images Learning to segment microscopic images Realtime Discriminative Background Subtraction ...


Selected Publications (full list)

Zhenguang Liu, Shuang Wu, Shuyuan Jin, Qi Liu, Shijian Lu, Roger Zimmermann, Li Cheng. Towards Natural and Accurate Future Pose Prediction for Humans and Animals. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. Details BibTeX Download: [pdf] Xiaowei Zhang, Xudong Shi, Yu Sun, Li Cheng. Multivariate Regression with Gross Errors on Manifold-valued Data. In IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI), 41(2):444-458, 2019. Project Webpage Details BibTeX Download: [pdf] Jaydeep De, Xiaowei Zhang, Feng Lin, Li Cheng. Transduction on Directed Graphs via Absorbing Random Walks. In IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI), 40(7):1770-1784, 2018. Project Webpage Details BibTeX Download: [pdf] Chi Xu, Lakshmi Narasimhan Govindarajan, Yu Zhang, Li Cheng. Lie-X: Depth Image Based Articulated Object Pose Estimation, Tracking, and Action Recognition on Lie Groups. In International Journal of Computer Vision (IJCV), 123(3):454-478, 2017. Project Webpage Details BibTeX Download: [pdf] GU Lin, Xiaowei Zhang, He Zhao, Huiqi Li, and Li Cheng. Segment 2D and 3D Filaments by Learning Structured and Contextual Features. In IEEE Trans. Medical Imaging (TMI),36(2):569-606, 2017. Project Webpage Details BibTeX Download: [pdf] Chi Xu, Lilian Zhang, Li Cheng, Reinhard Koch. Pose Estimation from Line Correspondences: A Complete Analysis and A Series of Solutions. In IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI),39(6):1209-22, 2017. Details BibTeX Download: [pdf] Adam Cliffe, David P. Doupe, HsinHo Sung, Isaac Lim Kok Hwee, Li Cheng, Kok Haur Ong, and Weimiao Yu. Quantitative 3D analysis of complex single border cell behaviors in coordinated collective cell migration. In Nature Communications, 14905:1-13, 2017. Details BibTeX Download: [pdf] Xiaowei Zhang, Li Cheng, Delin Chu, Li-Zhi Liao, Michael Ng, Roger C.E. Tan. Incremental Regularized Least Squares for Dimensionality Reduction of Large-Scale Data. In SIAM Journal on Scientific Computing, 38(3):414-39, 2016. Details BibTeX Download: [pdf] Li Liu, Li Cheng, Ye Liu, Yongpo Jia, David Rosenblum. Recognizing Complex Activities by a Probabilistic Interval-Based Model. In National Conference on Artificial Intelligence (AAAI), 2016. Details BibTeX Download: [pdf] Chi Xu, Ashwin Nanjappa, Xiaowei Zhang, Li Cheng. Estimate Hand Poses Efficiently from Single Depth Images. In International Journal of Computer Vision (IJCV), (116)1:21-45, 2016. Project Webpage, dataset and online performance Evaluation Details BibTeX Download: [pdf] Jaydeep De, Li Cheng, Xiaowei Zhang, Feng Lin, Huiqi Li, Kok Haur Ong, Weimiao Yu, Yuanhong Yu, Sohail Ahmed. A Graph-theoretical Approach for Tracing Filamentary Structures in Neuronal and Retinal Images. In IEEE Trans. Medical Imaging (TMI), (35)1:252-72, 2016. Project Webpage Details BibTeX Download: [pdf] Lin Gu, Li Cheng. Learning to Boost Filamentary Structure Segmentation. In International Conference on Computer Vision (ICCV), 2015. Project Webpage Details BibTeX Download: [pdf] Minglun Gong, Yiming Qian, Li Cheng. Integrated Foreground Segmentation and Boundary Matting for Live Videos. In IEEE Trans. Image Processing (TIP), 24(4):1356-70, 2015. Details BibTeX Download: [pdf] Li Cheng, Sinno Jialin Pan. Semi-supervised Domain Adaptation on Manifolds. In IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 25(12):2240-9, 2014. Details BibTeX Download: [pdf] Li Cheng, Jaydeep De, Xiaowei Zhang, Feng Lin, Huiqi Li. Tracing Retinal Blood Vessels by Matrix-Forest Theorem of Directed Graphs. In MICCAI, 2014. Project Webpage Details BibTeX Download: [pdf] Chi Xu, Li Cheng. Efficient Hand Pose Estimation from a Single Depth Image. In International Conference on Computer Vision (ICCV), 2013. Project Webpage Details BibTeX Download: [pdf] Li Cheng. Riemannian Similarity Learning. In International Conference on Machine Learning (ICML), 2013. Details BibTeX Download: [pdf] Li Cheng, Ning Ye, Weimiao Yu, Andre Cheah. Discriminative Cellular Segmentation for Microscopic Images. In Medical Image Computing and Computer Assisted Intervention (MICCAI), 2011. Details BibTeX Download: [pdf] Qinfeng Shi, Li Wang, Li Cheng, and Alex Smola. Discriminative Human Action Segmentation and Recognition using SMMs. In International Journal of Computer Vision (IJCV), 93(1):22-32, 2011. Code and Syn Data Details BibTeX Download: [pdf] Minglun Gong, Li Cheng. Foreground Segmentation of Live Videos using Locally Competing 1SVMs. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011. Details BibTeX Download: [pdf] Li Cheng, M. Gong, D. Schuurmans, and T. Caelli. Real-time Discriminative Background Subtraction. IEEE Trans. Image Processing, 20(5), 1401-1414, 2011. Project Webpage Details BibTeX Li Cheng, Minglun Gong. Realtime Background Subtraction from Dynamic Scenes. In IEEE International Conference on Computer Vision (ICCV), 2009. Details BibTeX Download: [pdf] Tiberio Caetano, Julian McAuley, Li Cheng, Quoc Le, and Alex Smola. Learning Graph Matching. IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI), 31(6):1048-1058, 2009. Details BibTeX Li Cheng, S.V.N. Vishwanathan, and Xinhua Zhang. Consistent image analogies using semi-supervised learning. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008. Details BibTeX Download: [pdf] Jun Zhou, Li Cheng, and Walter Bischof. Prediction and Change Detection In Sequential Data for Interactive Applications. In National Conference on Artificial Intelligence (AAAI), pp. 805--810, AAAI, 2008. Details BibTeX Download: [pdf] Li Cheng and S.V.N. Vishwanathan. Learning to compress images and videos. In Proceedings of the 24th international conference on Machine learning (ICML), pp. 161--168, ACM, New York, NY, USA, 2007. Details BibTeX Download: [pdf] Li Cheng, S.V.N. Vishwanathan, Dale Schuurmans, Shaojun Wang, and Terry Caelli. implicit Online Learning with Kernels. In B. Scholkopf, J. Platt, and T. Hoffman, editors, Advances in Neural Information Processing Systems (NIPS), pp. 249--256, MIT Press, Cambridge, MA, 2007. Details BibTeX Download: [pdf] Li Cheng and Terry Caelli. Bayesian stereo matching. Computer Vision and Image Understanding (CVIU), 106(1):85--96, 2007. Details BibTeX Download: [pdf] Jun Zhou, Li Cheng, and Walter Bischof. Online Learning with Novelty Detection in Human-guided Road Tracking. IEEE Transactions on Geoscience and Remote Sensing, 45(12):3967--3977, 2007. Details BibTeX Download: [HTML] Li Cheng, Terry Caelli, and A. Sanchez-Azofeifa. Component Optimization for Image Understanding: a Bayesian Approach. IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI), 28(5):684--693, 2006. Details BibTeX Download: [HTML] Li Cheng, Feng Jiao, Dale Schuurmans, and Shaojun Wang. Variational Bayesian image modelling. In Proceedings of the 22nd international conference on Machine learning (ICML), pp. 129--136, ACM, New York, NY, USA, 2005. Details BibTeX Download: [pdf] Shaojun Wang, Shaomin Wang, Russ Greiner, Dale Schuurmans, and Li Cheng. Exploiting syntactic, semantic and lexical regularities in language modeling via directed Markov random fields. In Proceedings of the 22nd international conference on Machine learning (ICML), pp. 948--955, ACM, New York, NY, USA, 2005. Details BibTeX Download: [pdf]