activity
20172021
most citedOn Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework

6 citations · 11 across the 5 of their papers we have counts for

collaborators

9 papers

eess.AS20212 cited

Masks Fusion with Multi-Target Learning For Speech Enhancement

Liangchen Zhou, Wenbin Jiang, Jingyan Xu +2

Recently, deep neural network (DNN) based time-frequency (T-F) mask estimation has shown remarkable effectiveness for speech enhancement. Typically, a single T-F mask is first esti…

cs.IT20216 cited

On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework

Zeyu Yan, Fei Wen, Rendong Ying +2

Lossy compression algorithms are typically designed to achieve the lowest possible distortion at a given bit rate. However, recent studies show that pursuing high perceptual qualit…

eess.IV2020

AMP-Net: Denoising based Deep Unfolding for Compressive Image Sensing

Zhonghao Zhang, Yipeng Liu, Jiani Liu +2

Most compressive sensing (CS) reconstruction methods can be divided into two categories, i.e. model-based methods and classical deep network methods. By unfolding the iterative opt…

eess.IV2019

A Simple Local Minimal Intensity Prior and An Improved Algorithm for Blind Image Deblurring

Fei Wen, Rendong Ying, Yipeng Liu +2

Blind image deblurring is a long standing challenging problem in image processing and low-level vision. Recently, sophisticated priors such as dark channel prior, extreme channel p…

cs.LG20192 cited

Matrix Completion via Nonconvex Regularization: Convergence of the Proximal Gradient Algorithm

Fei Wen, Rendong Ying, Peilin Liu +1

Matrix completion has attracted much interest in the past decade in machine learning and computer vision. For low-rank promotion in matrix completion, the nuclear norm penalty is c…

cs.CR2018

StreamBox-TZ: Secure Stream Analytics at the Edge with TrustZone

Heejin Park, Shuang Zhai, Long Lu +1

While it is compelling to process large streams of IoT data on the cloud edge, doing so exposes the data to a sophisticated, vulnerable software stack on the edge and hence securit…