Cheng Wang
Assistant Professor
We present a novel approach to identify ransomware campaigns derived fro...
The unstructured nature of point clouds demands that local aggregation b...
This study attempts to segment teeth and root-canals simultaneously from...
Image deraining is a challenging task that involves restoring degraded i...
Progress in artificial intelligence and machine learning over the past d...
Calibrating deep neural models plays an important role in building relia...
Federated learning (FL) has found numerous applications in healthcare,
f...
Magnetic resonance imaging (MRI) using hyperpolarized noble gases provid...
Exploring robust and efficient association methods has always been an
im...
This paper investigates the efficient solution of penalized quadratic
re...
In the realm of urban transportation, metro systems serve as crucial and...
Existing point cloud modeling datasets primarily express the modeling
pr...
Motion capture is a long-standing research problem. Although it has been...
Open-world instance segmentation has recently gained significant
popular...
Miscalibration-the mismatch between predicted probability and the true
c...
Driver models play a vital role in developing and verifying autonomous
v...
A finite difference numerical scheme is proposed and analyzed for the
Ca...
We present SLOPER4D, a novel scene-aware dataset collected in large urba...
Adenosine triphosphate (ATP) is a high-energy phosphate compound and the...
Although 3D point cloud classification neural network models have been w...
As the key technology of augmented reality (AR), 3D recognition and trac...
Recently, virtual/pseudo-point-based 3D object detection that seamlessly...
We present a novel framework to generate causal explanations for the
dec...
Spatio-temporal kriging is an important problem in web and social
applic...
Recurrent neural networks are a widely used class of neural architecture...
While federated learning has shown strong results in optimizing a machin...
3D object detection received increasing attention in autonomous driving
...
Coadded astronomical images are created by stacking multiple single-expo...
Reinforcement learning (RL) operating on attack graphs leveraging cyber
...
Task-oriented dialogue systems in industry settings need to have high
co...
We propose a novel normal estimation method called HSurf-Net, which can
...
Medical text learning has recently emerged as a promising area to improv...
In this paper, we study a second-order accurate and linear numerical sch...
The Landau-Lifshitz-Gilbert (LLG) equation is a widely used model for fa...
A second order accurate (in time) numerical scheme is proposed and analy...
The development of autonomous agents which can interact with other agent...
Inscrutable AI systems are difficult to trust, especially if they operat...
Relevant recommendation is a special recommendation scenario which provi...
Deep Learning neural networks are pervasive, but traditional computer
ar...
Existing motion capture datasets are largely short-range and cannot yet ...
We propose Human-centered 4D Scene Capture (HSC4D) to accurately and
eff...
In this paper, we propose and analyze a fully discrete finite element
pr...
Massive open online courses (MOOCs), which provide a large-scale interac...
The analysis of structure-preserving numerical methods for the
Poisson–N...
Learning the embeddings for urban regions from human mobility data can r...
Pawlak rough set and neighborhood rough set are the two most common roug...
Conversational recommender systems (CRS) aim to recommend suitable items...
Transformers are state-of-the-art in a wide range of NLP tasks and have ...
In this paper, we study the empirical spectral distribution of Spearman'...
Datasets containing both categorical and continuous variables are freque...