Avatar

Risheng Liu

rsliu AT dlut.edu.cn

Professor

Dalian University of Technology

Personal Site

Biography

I am currently a full professor with Digital Media Department at International School of Information Science and Engineering, Dalian University of Technology (DUT). I obtained my B.S. and Ph.D. degrees both from Dalian University of Technology, China, working with Prof.Zhouchen Lin. I was also doing joint PhD research in Carnegie Mellon University from September 2010 to January 2012.

Interests

  • Machine Learning and Deep Learning
  • Computer Vision
  • Optimization

Education

  • Ph.D in Computational Mathematics, 2007-2012

    Dalian University of Technology

  • BSc in Computational Mathematics, 2003-2007

    Dalian University of Technology

Curriculum Vitae

 
 
 
 
 

Full Professor

Dalian University of Technology

Nov 2019 – Present Dalian, CN
 
 
 
 
 

Hong Kong Scholar

The Hong Kong Polytechnic University

Jan 2016 – Jan 2018 Hong Kong, CN
 
 
 
 
 

Associate Professor

Dalian University of Technology

Dec 2015 – Oct 2019 Dalian, CN
 
 
 
 
 

Assistant Professor

Dalian University of Technology

Nov 2012 – Nov 2015 Dalian, CN

Publications @ZERO Lab

On the Convergence of Learning-based Iterative Methods for Nonconvex Inverse Problems. TPAMI, 2019.

Numerous tasks at the core of statistics, learning and vision areas are specific cases of ill-posed inverse problems. Recently, …
Risheng Liu , Shichao Cheng , Yi He , Xin Fan , Zhouchen Lin , Zhongxuan Luo
PDF

Learning to Diffuse: A New Perspective to Design PDEs for Visual Analysis. TPAMI, 2016.

We propose a new PDE framework, named learning to diffuse (LTD), to adaptively design the governing equation and the boundary condition …
Risheng Liu , Guangyu Zhong , Junjie Cao , Zhouchen Lin , Shiguang Shan , Zhongxuan Luo
PDF DOI

Linearized Alternating Direction Method with Parallel Splitting and Adaptive Penalty for Separable Convex Programs in Machine Learning. ML, 2014.

We propose LADM with parallel splitting and adaptive penalty (LADMPSAP) to solve multi-block separable convex programs efficiently. We …
PDF DOI

Adaptive Partial Differential Equation Learning for Visual Saliency Detection. CVPR, 2014.

This paper develops a PDE system for saliency detection. We define a Linear Elliptic System with Dirichlet boundary (LESD) to model the …
Risheng Liu , Junjie Cao , Zhouchen Lin , Shiguang Shan
PDF supp

Learning Markov Random Walks for Robust Subspace Clustering and Estimation. NN, 2014.

We introduce a regularized MRW learning model, using a low-rank penalty to constrain the global subspace structure, for subspace …
Risheng Liu , Zhouchen Lin , Zhixun Su
PDF DOI

Linear time Principal Component Pursuit and its extensions using l1 Filtering. Neurocomputing, 2014.

We propose a novel algorithm, called ℓ1 filtering, for exactly solving PCP with an complexity, where m×n is the size of data matrix …
Risheng Liu , Zhouchen Lin , Zhixun Su , Junbin Gao
PDF Code DOI

Linearized Alternating Direction Method with Parallel Splitting and Adaptive Penalty for Separable Convex Programs in Machine Learning. ACML, 2013.

We propose linearized alternating direction method with parallel splitting and adaptive penalty for efficiently solving linearly …
Risheng Liu , Zhouchen Lin , Zhixun Su
PDF supp

Fixed-Rank Representation for Unsupervised Visual Learning. CVPR, 2012.

This paper proposed a novel framework, named fixedrank representation (FRR), for robust unsupervised visual learning.
Risheng Liu , Zhouchen Lin , Fernando De la Torre , Zhixun Su
PDF supp

Linearized Alternating Direction Method with Adaptive Penalty for Low-Rank Representation. NIPS, 2011.

We propose a linearized alternating direction method with adaptive penalty for solving subproblems in ADM conveniently
Zhouchen Lin , Risheng Liu , Zhixun Su
PDF Code supp

Toward designing intelligent PDEs for computer vision An optimal control approach. IVC, 2011.

We introduce a PDE-based optimal control framework for PDEs design.
Risheng Liu , Zhouchen Lin , Wei Zhang , Kewei Tang , Zhixun Su
PDF Code DOI

Feature Extraction by Learning Lorentzian Metric Tensor and Its Extensions. PR, 2010.

We develop a supervised dimensionality reduction method, called Lorentzian discriminant projection(LDP), for feature extraction and …
Risheng Liu , Zhouchen Lin , Zhixun Su , Kewei Tang
PDF

Learning PDEs for Image Restoration via Optimal Control. ECCV, 2010.

We have presented a framework of learning PDEs from training data for image restoration.
Risheng Liu , Zhouchen Lin , Wei Zhang , Zhixun Su
PDF

Lorentzian Discriminant Projection and Its Applications. ACCV, 2009.

We develops a supervised dimensionality reduction method, Lorentzian Discriminant Projection (LDP), for discriminant analysis and …
Risheng Liu , Zhixun Su , Zhouchen Lin , Xiaoyu Hou
PDF

Awards

Outstanding Youth Science Foundation

National Natural Science Foundation of China 2019

Top Young Talents

Liaoning Province 2017

Hong Kong Scholar

Hong Kong 2016 – 2018

Academic Acativities

Reviewer to Journals

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
International Journal of Computer Vision (IJCV)
IEEE Transactions on Knowledge and Data Engineering (TKDE)
IEEE Transactions on Image Processing (TIP)
IEEE Transactions on Parallel and Distributed Systems (TPDS)
IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
IEEE Transactions on Biomedical Engineering (TBME)
IEEE Transactions on Industrial Electronics (TIE)
IEEE Transactions on Multimedia (TMM)

Program Committee to Conferences

AAAI Conference on Artificial Intelligence (AAAI)
International Joint Conference on Artificial Intelligence (IJCAI)
International Conference on Machine Learning (ICML)
Neural Information Processing Systems (NIPS)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
International Conference on Computer Visions (ICCV)
European Conference on Computer Vision(ECCV)
ACM Multimedia(ACM MM)