
Root and community inference on the latent growth process of a network using noisy attachment models
We introduce the PAPER (Preferential Attachment Plus Erdős–Rényi) model ...
read it

An Efficient Multitask Neural Network for Face Alignment, Head Pose Estimation and Face Tracking
While convolutional neural networks (CNNs) have significantly boosted th...
read it

Enhancing Transformationbased Defenses against Adversarial Examples with FirstOrder Perturbations
Studies show that neural networks are susceptible to adversarial attacks...
read it

Selfsupervised Pretraining of Visual Features in the Wild
Recently, selfsupervised learning methods like MoCo, SimCLR, BYOL and S...
read it

DataDriven Characterization and Detection of COVID19 Themed Malicious Websites
COVID19 has hit hard on the global community, and organizations are wor...
read it

Characterizing the Landscape of COVID19 Themed Cyberattacks and Defenses
COVID19 (Coronavirus) hit the global society and economy with a big sur...
read it

Active Learning to Classify Macromolecular Structures in situ for Less Supervision in CryoElectron Tomography
Motivation: CryoElectron Tomography (cryoET) is a 3D bioimaging tool t...
read it

SSFG: Stochastically Scaling Features and Gradients for Regularizing Graph Convolution Networks
Graph convolutional networks have been successfully applied in various g...
read it

A Visual Analytics Approach to Facilitate the Proctoring of Online Exams
Online exams have become widely used to evaluate students' performance i...
read it

Free Lunch for Fewshot Learning: Distribution Calibration
Learning from a limited number of samples is challenging since the learn...
read it

Towards Robust Medical Image Segmentation on SmallScale Data with Incomplete Labels
The datadriven nature of deep learning models for semantic segmentation...
read it

Weight Encode Reconstruction Network for Computed Tomography in a SemiCaseWise and LearningBased Way
Classic algebraic reconstruction technology (ART) for computed tomograph...
read it

Improving Lesion Segmentation for Diabetic Retinopathy using Adversarial Learning
Diabetic Retinopathy (DR) is a leading cause of blindness in working age...
read it

Inference on the History of a Randomly Growing Tree
The spread of infectious disease in a human community or the proliferati...
read it

SiamSNN: Spikebased Siamese Network for EnergyEfficient and Realtime Object Tracking
Although deep neural networks (DNNs) have achieved fantastic success in ...
read it

Meta3D: SingleView 3D Object Reconstruction from Shape Priors in Memory
3D shape reconstruction from a singleview RGB image is an illposed pro...
read it

AITom: Opensource AI platform for cryoelectron Tomography data analysis
Cryoelectron tomography (cryoET) is an emerging technology for the 3D ...
read it

A Deep Learning System That Generates Quantitative CT Reports for Diagnosing Pulmonary Tuberculosis
We developed a deep learning modelbased system to automatically generat...
read it

Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection
Recent saliency models extensively explore to incorporate multiscale co...
read it

Visual Analytics of Student Learning Behaviors on K12 Mathematics Elearning Platforms
With increasing popularity in online learning, a surge of Elearning pla...
read it

MURS: Practical and Robust Privacy Amplification with MultiParty Differential Privacy
When collecting information, local differential privacy (LDP) alleviates...
read it

Practical and Robust Privacy Amplification with MultiParty Differential Privacy
When collecting information, local differential privacy (LDP) alleviates...
read it

Deep LearningBased Strategy for Macromolecules Classification with Imbalanced Data from Cellular Electron Cryotomography
Deep learning model trained by imbalanced data may not work satisfactori...
read it

Highdimensional nonparametric density estimation via symmetry and shape constraints
We tackle the problem of highdimensional nonparametric density estimati...
read it

Dual Pattern Learning Networks by Empirical Dual Prediction Risk Minimization
Motivated by the observation that humans can learn patterns from two giv...
read it

RespondCAM: Analyzing Deep Models for 3D Imaging Data by Visualizations
The convolutional neural network (CNN) has become a powerful tool for va...
read it

Multitask Learning for Macromolecule Classification, Segmentation and Coarse Structural Recovery in CryoTomography
Cellular Electron CryoTomography (CECT) is a powerful 3D imaging tool f...
read it

Imagederived generative modeling of pseudomacromolecular structures  towards the statistical assessment of Electron CryoTomography template matching
Cellular Electron CryoTomography (CECT) is a 3D imaging technique that c...
read it

An integration of fast alignment and maximumlikelihood methods for electron subtomogram averaging and classification
Motivation: Cellular Electron CryoTomography (CECT) is an emerging 3D im...
read it

A Telecom Perspective on the Internet of Drones: From LTEAdvanced to 5G
Drones are driving numerous and evolving use cases, and creating transfo...
read it

AAANE: Attentionbased Adversarial Autoencoder for Multiscale Network Embedding
Network embedding represents nodes in a continuous vector space and pres...
read it

Deep learning based supervised semantic segmentation of Electron CryoSubtomograms
Cellular Electron CryoTomography (CECT) is a powerful imaging technique...
read it

Model compression for faster structural separation of macromolecules captured by Cellular Electron CryoTomography
Electron CryoTomography (ECT) enables 3D visualization of macromolecule...
read it

Feature Decomposition Based Saliency Detection in Electron CryoTomograms
Electron CryoTomography (ECT) allows 3D visualization of subcellular st...
read it

Performance Optimization and Parallelization of a Parabolic Equation Solver in Computational Ocean Acoustics on Modern Manycore Computer
As one of opensource codes widely used in computational ocean acoustics...
read it

A convolutional autoencoder approach for mining features in cellular electron cryotomograms and weakly supervised coarse segmentation
Cellular electron cryotomography enables the 3D visualization of cellul...
read it

Experience enrichment based task independent reward model
For most reinforcement learning approaches, the learning is performed by...
read it

Learning Multilevel Deep Representations for Image Emotion Classification
In this paper, we propose a new deep network that learns multilevel dee...
read it

Modelling Temporal Information Using Discrete Fourier Transform for Recognizing Emotions in Usergenerated Videos
With the widespread of usergenerated Internet videos, emotion recogniti...
read it

Integrative analysis of gene expression and phenotype data
The linking genotype to phenotype is the fundamental aim of modern genet...
read it

Global Gene Expression Analysis Using Machine Learning Methods
Microarray is a technology to quantitatively monitor the expression of l...
read it

Gene selection for cancer classification using a hybrid of univariate and multivariate feature selection methods
Various approaches to gene selection for cancer classification based on ...
read it

Automatic tracking of protein vesicles
With the advance of fluorescence imaging technologies, recently cell bio...
read it

Faithful Variable Screening for HighDimensional Convex Regression
We study the problem of variable selection in convex nonparametric regre...
read it

Efficient Hybrid Inline and Outofline Deduplication for Backup Storage
Backup storage systems often remove redundancy across backups via inline...
read it

Connectivitypreserving Geometry Images
We propose connectivitypreserving geometry images (CGIMs), which map a ...
read it

Conditional Sparse Coding and Grouped Multivariate Regression
We study the problem of multivariate regression where the data are natur...
read it

Efficient Active Algorithms for Hierarchical Clustering
Advances in sensing technologies and the growth of the internet have res...
read it

Highdimensional covariance estimation based on Gaussian graphical models
Undirected graphs are often used to describe high dimensional distributi...
read it

Forest Density Estimation
We study graph estimation and density estimation in high dimensions, usi...
read it
Min Xu
is this you? claim profile
Assistant Research Professor and Trainning Faculty at Carnegie Mellon University