Zhouchen Lin

Latest

• Neural ePDOs: Spatially Adaptive Equivariant Partial Differential Operator Based Networks
• Restarted Nonconvex Accelerated Gradient Descent: No More Polylogarithmic Factor in the O(ε−7/4) Complexity
• On the Lower Bound of Minimizing Polyak-Łojasiewicz Functions
• Zeroth-order Optimization with Weak Dimension Dependency
• Optimization-induced Implicit Graph Diffusion
• Alternating Direction Method of Multipliers for Machine Learning
• Training Much Deeper Spiking Neural Networks with a Small Number of Time-Steps
• Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation
• Variance Reduced EXTRA and DIGing and Their Optimal Acceleration for Strongly Convex Decentralized Optimization
• Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State
• Reparameterized Sampling for Generative Adversarial Networks
• Demystifying Adversarial Training via A Unified Probabilistic Framework
• PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation
• Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search
• Efficient Equivariant Network
• Gauge Equivariant Transformer
• AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models
• Is Attention Better Than Matrix Decomposition?
• Learned Extragradient ISTA with Interpretable Residual Structures for Sparse Coding
• PDO-eS2CNNs: Partial Differential Operator Based Equivariant Spherical CNNs
• Training Neural Networks by Lifted Proximal Operator Machines
• ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding
• Decentralized Accelerated Gradient Methods With Increasing Penalty Parameters
• Improving Semantic Segmentation via Decoupled Body and Edge Supervision
• Invertible Image Rescaling
• Accelerated First-Order Optimization Algorithms for Machine Learning
• Boosted Histogram Transform for Regression
• Implicit Euler Skip Connections: Enhancing Adversarial Robustness via Numerical Stability
• Maximum-and-Concatenation Networks
• PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions
• Accelerated Optimization for Machine Learning: First-Order Algorithms
• On the Complexity Analysis of the Primal Solutions for the Accelerated Randomized Dual Coordinate Ascent
• Spatial Pyramid Based Graph Reasoning for Semantic Segmentation
• Unified Graph and Low-rank Tensor Learning for Multi-view Clustering
• Synthetic Depth Transfer for Monocular 3D Object Pose Estimation in the Wild
• Dynamical System Inspired Adaptive Time Stepping Controller for Residual Network Families
• Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labeled Nodes
• SOGNet: Scene Overlap Graph Network for Panoptic Segmentation
• Revisiting EXTRA for Smooth Distributed Optimization
• Accelerated Alternating Direction Method of Multipliers:An Optimal O(1/K) Nonergodic Analysis
• L1-Norm Heteroscedastic Discriminant Analysis under Mixture of Gaussian Distributions
• On the Convergence of Learning-based Iterative Methods for Nonconvex Inverse Problems
• Expectation Maximization Attention Networks for Semantic Segmentation
• ADA-Tucker: Compressing Deep Neural Networks via Adaptive Dimension Adjustment Tucker Decomposition
• Lifted Proximal Operator Machines
• Robust 3D Human Pose Estimation from a Single Image or a Video Sequence
• Self-Supervised Convolutional Subspace Clustering Network
• Subspace Clustering by Block Diagonal Representation
• Subspace Clustering under Complex Noise
• The Augmented Homogeneous Coordinates Matrix Based Projective Mismatch Removal for Partial-Duplicate Image Search
• Neural Multimodal Cooperative Learning Towards Micro-video Understanding
• R^2 Net Recurrent and Recursive Network for Sparse View CT Artifacts Removal
• Neural Ordinary Differential Equations with Envolutionary Weights
• Virtual Adversarial Training on Graph ConvolutionalNetworks in Node Classification
• Differentiable Linearized ADMM
• Accelerated Alternating Direction Method of Multipliers: an Optimal O(1/K) Nonergodic Analysis
• Two-weight and three-weight linear codes based on Weil sums
• Deep Comprehensive Correlation Mining for Image Clustering
• Sharp Analysis for Nonconvex SGD Escaping from Saddle Points
• Tensor Robust Principal Component Analysis with A New Tensor Nuclear Norm
• Recurrent Squeeze-and-Excitation Net for Single Image Deraining
• A Unified Alternating Direction Method of Multipliers by Majorization Minimization
• Alternating Multi-bit Quantization for Recurrent Neural Networks
• Bilinear Factor Matrix Norm Minimization for Robust PCA: Algorithms and Applications
• Binary Multidimensional Scaling for Hashing
• Construction of Incoherent Dictionaries via Direct Babel Function Minimization
• Convolutional Neural Networks with Alternately Updated Clique
• Demosaicking based on Channel-Correlation Adaptive Dictionary Learning
• Dictionary Learning with Structured Noise
• Exact Low Tubal Rank Tensor Recovery from Gaussian Measurements
• Joint Dictionary Learning and Semantic Constrained Latent Subspace Projection for Cross-Modal Retrieval
• Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolution
• Low Rank Matrix Recovery via Robust Outlier Estimation
• Nonconvex Sparse Spectral Clustering by Alternating Direction Method of Multipliers
• On the Applications of Robust PCA in Image and Video Processing
• Optimization Algorithm Inspired Deep Neural Network Structure Design
• Optimized Projections for Compressed Sensing via Direct Mutual Coherence Minimization
• Robust Matrix Factorization by Majorization-Minimization
• SPIDER Near-Optimal Non-Convex Optimization via Stochastic Path-Integrated Differential Estimator
• t-Schatten- p Norm for Low-Rank Tensor Recovery
• Tensor Factorization for Low-Rank Tensor Completion
• Closed-form Solutions of Some Low-Rank Subspace Recovery Models and Their Applications (in Chinese)
• A Unified Convex Surrogate for the Schatten-p Norm
• Automatic Design of High-Sensitivity Color Filter Arrays with Panchromatic Pixels
• Bilevel Model Based Discriminative Dictionary Learning for Recognition
• Completing Low-Rank Matrices with Corrupted Samples from Few Coefficients in General Basis
• Efficient Tree-structured SfM by RANSAC Generalized Procrustes Analysis
• Factorization for Projective and Metric Reconstruction via Truncated Nuclear Norm
• Fast Compressive Phase Retrieval under Bounded Noise
• Faster and Non-ergodic O(1/K) Stochastic Alternating Direction Method of Multipliers
• Feature Learning via Partial Differential Equation with Applications to Face Recognition
• Globally Variance-Constrained Sparse Representation and Its Application in Image Set Coding
• Globally Variance-Constrained Sparse Representation for Rate-Distortion Optimized Image Representation
• Joint Latent Space Learning and Regression for Cross Modal Retrieval
• Label Information Guided Graph Construction for Semi-Supervised Learning
• Locality-constrained Linear Coding Based Bi-layer Model for Multi-view Facial Expression Recognition
• Optimized Color Filter Arrays for Sparse Representation Based Demosaicking
• Parallel Asynchronous Stochastic Variance Reduction for Nonconvex Optimization
• Penrose High Dynamic Range Imaging
• ROUTE: Robust Outlier Estimation for Low Rank Matrix Recovery
• The Shape Interaction Matrix-Based Affine Invariant Mismatch Removal for Partial-Duplicate Image Search
• Transformation Invariant Subspace Clustering
• Provable Accelerated Gradient Method for Nonconvex Low Rank Optimization
• Convex Sparse Spectral Clustering: Single-view to Multi-view
• Fast Proximal Linearized Alternating Direction Method of Multiplier with Parallel Splitting
• Multi-view Common Space Learning for Emotion Recognition in the Wild
• Relaxed Majorization-Minimization for Non-smooth and Non-convex Optimization
• Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks
• Robust Kernel Estimation with Outliers Handling for Image Deblurring
• Subspace Clustering Based Tag Sharing for Inductive Tag Matrix Refinement with Complex Errors
• Tensor LRR and Sparse Coding Based Subspace Clustering
• Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization
• A Review on Low-Rank Models in Signal and Data Analysis
• Automatic Design of Color Filter Arrays in the Frequency Domain
• Learning to Diffuse: A New Perspective to Design PDEs for Visual Analysis
• Nonconvex Nonsmooth Low-Rank Minimization via Iteratively Reweighted Nuclear Norm
• Learning Semi-Supervised Representation Towards a Unified Optimization Framework for Semi-Supervised Learning
• Low-Rank Models in Signal and Data Processing: Theories, Algorithms, and Applications (in Chinese)
• Locality-Preserving Low-Rank Representation for Graph Construction from Nonlinear Manifolds
• Dual Graph Regularized Latent Low-rank Representation for Subspace Clustering
• A Fast Alternating Time-Splitting Approach for Learning Partial Differential Equations
• Fast Multidimensional Ellipsoid-Specific Fitting by Alternating Direction Method of Multipliers
• Laplacian Regularized Low-Rank Representation and Its Applications
• Accelerated Proximal Gradient Methods for Nonconvex Programming
• Image Tag Completion and Refinement by Subspace Clustering and Matrix Completion
• Multiple Models Fusion for Emotion Recognition in the Wild
• Determining Step Sizes in Geometric Optimization Algorithms
• Integrated Low Rank Based Discriminative Feature Learning for Recognition
• A Robust Hybrid Method for Text Detection in Natural Scenes by Learning-based Partial Differential Equations
• A New Retraction for Accelerating the Riemannian Three-Factor Low-Rank Matrix Completion Algorithm
• Adaptive Sharing for Image Classification
• Subspace Clustering by Mixture of Gaussian Regression
• Multi-Level Discriminative Dictionary Learning With Application to Large Scale Image Classification
• Relations among Some Low Rank Subspace Recovery Models
• Robust Nuclear Norm Regularized Regression for Face Recognition with Occlusion
• Multi-Level Discriminative Dictionary Learning With Application to Large Scale Image Classification
• Penrose Demosaicking
• Exact Recoverability of Robust PCA via Outlier Pursuit with Tight Recovery Bounds
• Generalized Singular Value Thresholding
• Smoothed Low Rank and Sparse Matrix Recovery by Iteratively Reweighted Least Squared Minimization
• Linearized Alternating Direction Method with Parallel Splitting and Adaptive Penalty for Separable Convex Programs in Machine Learning
• Low Rank Global Geometric Consistency for Partial-Duplicate Image Search
• Proximal Iteratively Reweighted Algorithm with Multiple Splitting for Nonconvex Sparsity Optimization
• Adaptive Partial Differential Equation Learning for Visual Saliency Detection
• Generalized Nonconvex Nonsmooth Low-Rank Minimization
• Robust Estimation of 3D Human Poses from Single Images
• Robust Low-Rank Regularized Regression for Face Recognition with Occlusion
• Smooth Representation Clustering
• Smooth Representation Clustering
• Learning Markov Random Walks for Robust Subspace Clustering and Estimation
• Tensor LRR Based Subspace Clustering
• Robust Latent Low Rank Representation for Subspace Clustering
• A Regularized Approach for Geodesic Based Semi-Supervised Multi-Manifold Learning
• Linear time Principal Component Pursuit and its extensions using l1 Filtering
• Correlation Adaptive Subspace Segmentation by Trace Lasso
• Correntropy Induced L2 Graph for Robust Subspace Clustering
• Linearized Alternating Direction Method with Parallel Splitting and Adaptive Penalty for Separable Convex Programs in Machine Learning
• Rank Minimization: Theories, Algorithms, and Applications (in Chinese)
• L1-Norm Kernel Discriminant Analysis Via Bayes Error Bound Optimization for Robust Feature Extraction
• A Counterexample for The Validaity of Using Nuclear Norm as A Comvex Surrogate of Rank
• Transform Invariant Text Extraction
• Rectification of Optical Characters as Transform Invariant Low-rank Textures
• Linearized Alternating Direction Method with Adaptive Penalty and Warm Starts for Fast Solving Transform Invariant Low-Rank Textures
• Regularized Semi-Supervised Latent Dirichlet Allocation for visual concept learning
• Robust Recovery of Subspace Structures by Low-Rank Representation
• Geodesic based semi-supervised multi-manifold feature extraction
• Perceptual Thumbnail Generation
• A comparison of typical ℓp minimization algorithms
• Bases sorting: Generalizing the concept of frequency for over-complete dictionaries
• Fixed-Rank Representation for Unsupervised Visual Learning
• Non-Negative Low Rank and Sparse Graph for Semi-Supervised Learning
• A new discriminant subspace analysis approach for multi-class problems
• Fast gradient vector flow computation based on augmented Lagrangian method
• Linearized Alternating Direction Method with Adaptive Penalty for Low-Rank Representation
• A Generalized Accelerated Proximal Gradient Approach for Total Variation-Based Image Restoration
• Toward designing intelligent PDEs for computer vision An optimal control approach
• Some Software Packages for Partial SVD Computation
• Analysis and Improvement of Low Rank Representation for Subspace segmentation
• Penrose Pixels for Super-Resolution
• Learning Semi-Riemannian Metrics for Semisupervised Feature Extraction
• A Geometric Method for Optimal Design of Color Filter Arrays
• The Frequency Structure Matrix: A Representation of Color Filter Arrays
• A Block Lanczos with Warm Start Technique for Accelerating Nuclear Norm Minimization Algorithms
• Feature Extraction by Learning Lorentzian Metric Tensor and Its Extensions
• Emotion Recognition from Arbitrary View Facial Images
• Learning PDEs for Image Restoration via Optimal Control
• Robust Subspace Segmentation by Low-Rank Representation
• Unsupervised Object Segmentation with a Hybrid Graph Model
• Aperiodic pixel layout for super-resolution (Invited Paper)
• A Rank-One Update Algorithm for Fast Solving Kernel Foley-Sammon Optimal Discriminant Vectors
• The Multiscale Competitive Code via Sparse Representation for Palmprint Verification
• Tree Structure Based Analyses on Compressive Sensing for Binary Sparse Sources
• Fast Algorithms for Recovering a Corrupted Low-Rank Matrix
• Fast, Automatic and Fine-Grained Tampered JPEG Images Detection via DCT Coefficient Analysis
• Multi-output regression on the output manifold
• The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrix
• Tensor linear Laplacian discrimination (TLLD) for feature extraction
• Designing Partial Differential Equations for Image Processing by Combining Differential Invariants
• Fast Convex Optimization Algorithms for Exact Recovery of a Corrupted Low-Rank Matrix
• Learning-Based Image Superresolution Algorithms (in Chinese)
• Signature Sample Synthesis
• Radon Representation-Based Feature Descriptor for Texture Classification
• Classification via Minimum Incremental Coding Length
• A Novel Approach to Expression Recognition from Non-frontal Face Images
• Analysis on Rate-distortion Performance of Compressive Sensing for Binary Sparse Source
• Lorentzian Discriminant Projection and Its Applications
• Optimizing Multi-class Spatio-Spectral Filters via Bayes Error Estimation for EEG Classification
• Refined Exponential Filter with Applications to Image Restoration and Interpolation
• Learning Partial Differential Equations for Computer Vision
• Perceptual Image Preview
• Limits of Learning-Based Superresolution Algorithms
• Color Filter Arrays: A Design Methodology
• Color Filter Arrays: Representation and Analysis
• Learning Partial Differential Equations for Computer Vision
• One-Shot Approximate Local Shading
• Modeling and Rendering of Heterogeneous Translucent Materials Using the Diffusion Equation
• Classification via Semi-Riemannian Spaces
• Real-Time Rendering of Realistic Rain
• Style-preserving English handwriting synthesis
• High Resolution Animated Scenes from Stills
• A Hybrid Graph Model for Unsupervised Object Segmentation
• Classification via Minimum Incremental Coding Length (MICL)
• Contextual Distance for Data Perception
• Laplacian PCA and Its Applications
• Limits of Learning-Based Superresolution Algorithms
• Linear Laplacian Discrimination for Feature Extraction
• Penrose Pixels: Super-Resolution in the Detector Layout Domain
• Table Detection in Online Ink Notes
• Real-Time Rendering of Realistic Rain
• Rule-based cleanup of on-line English ink notes
• Response to Comments on Fundamental Limits of Reconstruction-Based Superresolution Algorithms under Local Translation
• Detecting Doctored JPEG Images via DCT Coefficient Analysis
• First Order Approximation for Texture Filtering
• Real-Time Rendering of Realistic Rain
• Detecting Doctored Images Using Camera Response Normality and Consistency
• On-Line Signature Verification With Two-Stage Statistical Models
• Optimal Polynomial Filters
• Pre-filtering 2D Polygons without Clipping
• A Geometric Analysis of Light Field Rendering
• Fundamental Limits of Reconstruction-Based Superresolution Algorithms under Local Translation
• Correction and rectification of light fields
• Off-line Signature Verification Incorporating the Prior Model
• Signature verification using integrated classifiers
• Relighting with the Reflected Irradiance Field: Representation, Sampling and Reconstruction
• Correction and Rectification of Light Fields
• On the Fundamental Limits of Reconstruction-Based Super-resolution Algorithms
• Relighting with the Reflected Irradiance Field: Representation, Sampling and Reconstruction
• On the Number of Samples Needed in Light Field Rendering with Constant-depth Assumption
• An Anisotropic Diffusion PDE for Noise Reduction and Thin Edge Preservation
• Constrained Optimal Control of Continuous Casting
• Numerical Analysis of the Bulging of Continuously Cast Slabs