• Publications
  • Influence
Deep ADMM-Net for Compressive Sensing MRI
TLDR
We propose a novel deep architecture, dubbed ADMM-Net, inspired by the Alternating Direction Method of Multipliers (ADMM) algorithm for optimizing a general CS-MRI model. Expand
  • 447
  • 53
  • PDF
ADMM-CSNet: A Deep Learning Approach for Image Compressive Sensing
TLDR
Compressive sensing (CS) is an effective technique for reconstructing image from a small amount of sampled data. Expand
  • 67
  • 15
Towards 3D Face Recognition in the Real: A Registration-Free Approach Using Fine-Grained Matching of 3D Keypoint Descriptors
TLDR
In this paper, towards 3D face recognition for real-life biometric applications, we significantly extend the SIFT-like matching framework to mesh data and propose a novel approach using fine-grained matching of 3D keypoint descriptors. Expand
  • 108
  • 12
  • PDF
Expression-robust 3D face recognition via weighted sparse representation of multi-scale and multi-component local normal patterns
TLDR
In the theory of differential geometry, surface normal, as a first order surface differential quantity, determines the orientation of a surface at each point and contains informative local surface shape information. Expand
  • 52
  • 7
  • PDF
Multimodal 2D+3D Facial Expression Recognition With Deep Fusion Convolutional Neural Network
TLDR
This paper presents a novel and efficient deep fusion convolutional neural network (DF-CNN) for multimodal 2D+3D facial expression recognition (FER). Expand
  • 90
  • 6
Expression robust 3D face recognition via mesh-based histograms of multiple order surface differential quantities
TLDR
This paper presents a mesh-based approach for 3D face recognition using a novel local shape descriptor and a SIFT-like matching process. Expand
  • 33
  • 6
  • PDF
An efficient multimodal 2D + 3D feature-based approach to automatic facial expression recognition
TLDR
We present a fully automatic multimodal 2D + 3D feature-based facial expression recognition approach and demonstrate its performance on the BU-3DFE database. Expand
  • 64
  • 5
Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries in Wavelet Domain
  • Huibin Li, Feng Liu
  • Mathematics, Computer Science
  • Fifth International Conference on Image and…
  • 20 September 2009
TLDR
This paper proposes a novel hybrid image denoising method based on wavelet transform and sparse and redundant representations model which is called signal-scale wavelet K-SVD algorithm. Expand
  • 133
  • 4
  • PDF
3D Facial Expression Recognition Based on Histograms of Surface Differential Quantities
TLDR
In this paper, we present a novel mesh-based method for 3D facial expression recognition using two local shape descriptors. Expand
  • 33
  • 4
  • PDF
A graph-cut approach to image segmentation using an affinity graph based on ℓ0-sparse representation of features
TLDR
We propose a graph-cut based image segmentation method by constructing an affinity graph using ℓ0 sparse representation, which has interesting properties of long range and sparsity. Expand
  • 22
  • 4
  • PDF