
Doubly Robust OffPolicy Learning on LowDimensional Manifolds by Deep Neural Networks
Causal inference explores the causation between actions and the conseque...
read it

Interactive Reinforcement Learning for Feature Selection with Decision Tree in the Loop
We study the problem of balancing effectiveness and efficiency in automa...
read it

DARWIN: A Highly Flexible Platform for Imaging Research in Radiology
To conduct a radiomics or deep learning research experiment, the radiolo...
read it

Identifying and Tracking Solar Magnetic Flux Elements with Deep Learning
Deep learning has drawn a lot of interest in recent years due to its eff...
read it

AutoFS: Automated Feature Selection via Diversityaware Interactive Reinforcement Learning
In this paper, we study the problem of balancing effectiveness and effic...
read it

Transmitting Extra Bits by Rotating Signal Constellations
In this letter, we propose a novel LDPC coding scheme to transmit extra ...
read it

A Color Elastica Model for VectorValued Image Regularization
Models related to the Euler's Elastica energy have proven to be very use...
read it

On the Numerical Solution of Nonlinear Eigenvalue Problems for the MongeAmpère Operator
In this article, we report the results we obtained when investigating th...
read it

Hybrid DiscriminativeGenerative Training via Contrastive Learning
Contrastive learning and supervised learning have both seen significant ...
read it

Polestar: An Intelligent, Efficient and NationalWide Public Transportation Routing Engine
Public transportation plays a critical role in people's daily life. It h...
read it

Robust PDE Identification from Noisy Data
We propose robust methods to identify underlying Partial Differential Eq...
read it

PuzzleNet: Scene Text Detection by Segment Context Graph Learning
Recently, a series of decompositionbased scene text detection methods h...
read it

An Alternating Direction Explicit Method for Time Evolution Equations with Applications to Fractional Differential Equations
We derive and analyze the alternating direction explicit (ADE) method fo...
read it

Curvature Regularized Surface Reconstruction from Point Cloud
We propose a variational functional and fast algorithms to reconstruct i...
read it

Learning functions varying along an active subspace
Many functions of interest are in a highdimensional space but exhibit l...
read it

Deep Learning for 3D Point Clouds: A Survey
Point cloud learning has lately attracted increasing attention due to it...
read it

A Comprehensive Study and Comparison of Core Technologies for MPEG 3D Point Cloud Compression
Point cloud based 3D visual representation is becoming popular due to it...
read it

Towards OmniSupervised Face Alignment for Large Scale Unlabeled Videos
In this paper, we propose a spatialtemporal relational reasoning networ...
read it

SemiSupervised Hierarchical Recurrent Graph Neural Network for CityWide Parking Availability Prediction
The ability to predict citywide parking availability is crucial for the...
read it

Triply Robust OffPolicy Evaluation
We propose a robust regression approach to offpolicy evaluation (OPE) f...
read it

Fast Algorithms for Surface Reconstruction from Point Cloud
We consider constructing a surface from a given set of point cloud data....
read it

Dense Scale Network for Crowd Counting
Crowd counting has been widely studied by computer vision community in r...
read it

Predicting Solar Flares Using a Long ShortTerm Memory Network
We present a long shortterm memory (LSTM) network for predicting whethe...
read it

Estimating Individual Advertising Effect in ECommerce
Online advertising has been the major monetization approach for Internet...
read it

Competitive Experience Replay
Deep learning has achieved remarkable successes in solving challenging r...
read it

Sequencebased Person Attribute Recognition with Joint CTCAttention Model
Attribute recognition has become crucial because of its wide application...
read it

Variational Inference with Tailadaptive fDivergence
Variational inference with αdivergences has been widely used in modern ...
read it

Adaptive guaranteedperformance consensus design for highorder multiagent systems
The current paper addresses the distributed guaranteedperformance conse...
read it

CIATowards a Unified Marketing Optimization Framework for eCommerce Sponsored Search
As the largest ecommerce platform, Taobao helps advertisers reach billi...
read it

Largescale Bisample Learning on ID vs. Spot Face Recognition
In many face recognition applications, there is large amount of face dat...
read it

Dynamic Output Feedback GuaranteedCost Synchronization for Multiagent Networks with Given Cost Budgets
The current paper addresses the distributed guaranteedcost synchronizat...
read it

On Connecting Stochastic Gradient MCMC and Differential Privacy
Significant success has been realized recently on applying machine learn...
read it

Sampleefficient Policy Optimization with Stein Control Variate
Policy gradient methods have achieved remarkable successes in solving ch...
read it

Deep Learning for CaseBased Reasoning through Prototypes: A Neural Network that Explains Its Predictions
Deep neural networks are widely used for classification. These deep mode...
read it

Triangle Generative Adversarial Networks
A Triangle Generative Adversarial Network (ΔGAN) is developed for semi...
read it

ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching
We investigate the nonidentifiability issues associated with bidirectio...
read it

Neural Person Search Machines
We investigate the problem of person search in the wild in this work. In...
read it

Stochastic Sequential Neural Networks with Structured Inference
Unsupervised structure learning in highdimensional time series data has...
read it

MultiView Image Generation from a SingleView
This paper addresses a challenging problem  how to generate multiview...
read it

Learning Policies for Markov Decision Processes from Data
We consider the problem of learning a policy for a Markov decision proce...
read it

Videobased Person Reidentification with Accumulative Motion Context
Video based person reidentification plays a central role in realistic s...
read it

Recurrent Image Captioner: Describing Images with SpatialInvariant Transformation and Attention Filtering
Along with the prosperity of recurrent neural network in modelling seque...
read it

Panoptic Studio: A Massively Multiview System for Social Interaction Capture
We present an approach to capture the 3D motion of a group of people eng...
read it

City traffic forecasting using taxi GPS data: A coarsegrained cellular automata model
City traffic is a dynamic system of enormous complexity. Modeling and pr...
read it

EndtoEnd Comparative Attention Networks for Person Reidentification
Person reidentification across disjoint camera views has been widely ap...
read it

Uncovering the information core in recommender systems
With the rapid growth of the Internet and overwhelming amount of informa...
read it
Hao Liu
is this you? claim profile
Associate Professor / Master Instructor at Beihang University School of Astronautics