
Robust Structured Statistical Estimation via Conditional Gradient Type Methods
Structured statistical estimation problems are often solved by Condition...
read it

Robust compressed sensing of generative models
The goal of compressed sensing is to estimate a high dimensional vector ...
read it

Channel Attention based Iterative Residual Learning for Depth Map SuperResolution
Despite the remarkable progresses made in deeplearning based depth map ...
read it

Computation on Sparse Neural Networks: an Inspiration for Future Hardware
Neural network models are widely used in solving many challenging proble...
read it

Learning 2D3D Correspondences To Solve The Blind PerspectivenPoint Problem
Conventional absolute camera pose via a PerspectivenPoint (PnP) solver...
read it

Hodge and Podge: Hybrid Supervised Sound Event Detection with MultiHot MixMatch and Composition Consistence Training
In this paper, we propose a method called Hodge and Podge for sound even...
read it

Deep Image Harmonization via Domain Verification
Image composition is an important operation in image processing, but the...
read it

Error estimate of a bifidelity method for kinetic equations with random parameters and multiple scales
In this paper, we conduct uniform error estimates of the bifidelity met...
read it

Encoding Selection for Solving Hamiltonian Cycle Problems with ASP
It is common for search and optimization problems to have alternative eq...
read it

Quantum algorithm for finding the negative curvature direction in nonconvex optimization
We present an efficient quantum algorithm aiming to find the negative cu...
read it

NODE: Extreme Low Light Raw Image Denoising using a Noise Decomposition Network
Denoising extreme low light images is a challenging task due to the high...
read it

Image Harmonization Datasets: HCOCO, HAdobe5k, HFlickr, and Hday2night
Image composition is an important operation in image processing, but the...
read it

HODGEPODGE: Sound event detection based on ensemble of semisupervised learning methods
In this paper, we present a method called HODGEPODGE[1] for largescale ...
read it

Optimal Feature Transport for CrossView Image GeoLocalization
This paper addresses the problem of crossview image based localization,...
read it

Lending Orientation to Neural Networks for Crossview Geolocalization
This paper studies imagebased geolocalization (IBL) problem using grou...
read it

FurcaNeXt: Endtoend monaural speech separation with dynamic gated dilated temporal convolutional networks
Deep dilated temporal convolutional networks (TCN) have been proved to b...
read it

FurcaNet: An endtoend deep gated convolutional, long shortterm memory, deep neural networks for single channel speech separation
Deep gated convolutional networks have been proved to be very effective ...
read it

Is CQT more suitable for monaural speech separation than STFT? an empirical study
Shorttime Fourier transform (STFT) is used as the front end of many pop...
read it

High Dimensional Robust Estimation of Sparse Models via Trimmed Hard Thresholding
We study the problem of sparsity constrained Mestimation with arbitrary...
read it

Dynamic Sparse Graph for Efficient Deep Learning
We propose to execute deep neural networks (DNNs) with dynamic and spars...
read it

Stochastic Secondorder Methods for Nonconvex Optimization with Inexact Hessian and Gradient
Trust region and cubic regularization methods have demonstrated good per...
read it

Stochastically Controlled Stochastic Gradient for the Convex and Nonconvex Composition problem
In this paper, we consider the convex and nonconvex composition problem...
read it

Deep Stochastic Attraction and Repulsion Embedding for Image Based Localization
This paper tackles the problem of largescale imagebased localization w...
read it

Stochastic Zerothorder Optimization via Variance Reduction method
Derivativefree optimization has become an important technique used in m...
read it

High Dimensional Robust Sparse Regression
We provide a novel  and to the best of our knowledge, the first  alg...
read it

Approximate Newtonbased statistical inference using only stochastic gradients
We present a novel inference framework for convex empirical risk minimiz...
read it

Discriminative CrossView Binary Representation Learning
Learning compact representation is vital and challenging for large scale...
read it

L1Norm Batch Normalization for Efficient Training of Deep Neural Networks
Batch Normalization (BN) has been proven to be quite effective at accele...
read it

PIRT: A Runtime Framework to Enable EnergyEfficient RealTime Robotic Applications on Heterogeneous Architectures
Enabling full robotic workloads with diverse behaviors on mobile systems...
read it

Asymptotic Analysis for LowResolution Massive MIMO Systems with MMSE Receiver
The uplink achievable rate of massive multiple inputmultipleoutput (M...
read it

A Double Joint Bayesian Approach for JVector Based Textdependent Speaker Verification
Jvector has been proved to be very effective in textdependent speaker ...
read it

Variance Reduced methods for Nonconvex Composition Optimization
This paper explores the nonconvex composition optimization in the form ...
read it

Dualityfree Methods for Stochastic Composition Optimization
We consider the composition optimization with two expectedvalue functio...
read it

Person Reidentification Using Visual Attention
Despite recent attempts for solving the person reidentification problem...
read it

Addressing Ambiguity in Multitarget Tracking by Hierarchical Strategy
This paper presents a novel hierarchical approach for the simultaneous t...
read it

MultiView TaskDriven Recognition in Visual Sensor Networks
Nowadays, distributed smart cameras are deployed for a wide set of tasks...
read it

Statistical inference using SGD
We present a novel method for frequentist statistical inference in Mest...
read it

Endtoend Binary Representation Learning via Direct Binary Embedding
Learning binary representation is essential to largescale computer visi...
read it

Compressing Deep Convolutional Networks using Vector Quantization
Deep convolutional neural networks (CNN) has become the most promising m...
read it
Liu Liu
is this you? claim profile
Graduate Research Assistant at University of Tennessee, Knoxville and Sr. Machine Learning Engineer at Samsung Semiconductor, Inc