56 Result(s)
within
**-Tao Guo
Computer Science
-
Article
Open AccessRobust and privacy-preserving collaborative training: a comprehensive survey
Increasing numbers of artificial intelligence systems are employing collaborative machine learning techniques, such as federated learning, to build a shared powerful deep model among participants, while keepin...
-
Article
Collective Movement Simulation: Methods and Applications
Collective movement simulations are challenging and important in many areas, including life science, mathematics, physics, information science and public safety. In this survey, we provide a comprehensive revi...
-
Article
Open AccessTwo-dimensional materials for future information technology: status and prospects
Over the past 70 years, the semiconductor industry has undergone transformative changes, largely driven by the miniaturization of devices and the integration of innovative structures and materials. Two-dimensi...
-
Article
Robust Unpaired Image Dehazing via Density and Depth Decomposition
To overcome the overfitting issue of dehazing models trained on synthetic hazy-clean image pairs, recent methods attempt to boost the generalization ability by training on unpaired data. However, most of exist...
-
Article
SNCL: a supernode OpenCL implementation for hybrid computing arrays
Heterogeneous computing has been develo** continuously in the field of high-performance computing because of its high performance and energy efficiency. More and more accelerators have emerged, such as GPU, ...
-
Article
A reinforcement learning-based approach to testing GUI of moblie applications
With the popularity of mobile devices, the software market of mobile applications has been booming in recent years. Android applications occupy a vast market share. However, the applications inevitably contain...
-
Chapter and Conference Paper
Trend and Methods of IoT Sequential Data Outlier Detection
In recent years, the state has made great efforts to develop the transportation industry. With the continuous expansion of the transportation network and the large-scale increase of vehicles, traffic congestio...
-
Chapter and Conference Paper
Within- and Between-Class Sample Interpolation Based Supervised Metric Learning for Speaker Verification
Metric learning aims to pull together the samples belonging to the same class and push apart those from different classes in embedding space. Existing methods may suffer from inadequate and low-quality sample ...
-
Article
Underwater occluded object recognition with two-stage image reconstruction strategy
The complex underwater environment, such as foreign object occlusion and dim light, causes the feature of underwater objects to be seriously missing. And ripple causes deformation of objects, which greatly inc...
-
Article
An automatic methodology for full dentition maturity staging from OPG images using deep learning
Accurate maturity identification of permanent teeth for children and adolescents using orthopantomogram (OPG) images is crucial in pediatric dentistry.Although recent advancements in deep learning have shown p...
-
Article
Open AccessA universal programmable Gaussian boson sampler for drug discovery
Gaussian boson sampling (GBS) has the potential to solve complex graph problems, such as clique finding, which is relevant to drug discovery tasks. However, realizing the full benefits of quantum enhancements ...
-
Chapter and Conference Paper
A Deep Reinforcement Learning-Based Approach for Android GUI Testing
The mobile application market is booming, and Android applications occupy a vast market share. However, the applications may contain many errors. The task in the testing phase is to find these errors as soon a...
-
Chapter and Conference Paper
SG-Net: Semantic Guided Network for Image Dehazing
From traditional handcrafted priors to learning-based neural networks, image dehazing technique has gone through great development. In this paper, we propose an end-to-end Semantic Guided Network (SG-Net (Code...
-
Article
Open AccessAttention mechanisms in computer vision: A survey
Humans can naturally and effectively find salient regions in complex scenes. Motivated by this observation, attention mechanisms were introduced into computer vision with the aim of imitating this aspect of th...
-
Article
Energy-efficient speed tuning for real-time applications
Applications with several tasks consuming huge energy during they are executed on modern high performance computing systems has not gone unnoticed. Fortunately, researchers have provided many solutions to redu...
-
Chapter and Conference Paper
Multi-task Parallel: A Tumor Segmentation Approach of Specific Task Attention
It is of great significance to make full use of the complementary advantages of different modality imaging information for improving the accuracy of tumor segmentation and formulating precise radiotherapy plan...
-
Chapter and Conference Paper
AreaTransfer: A Cross-City Crowd Flow Prediction Framework Based on Transfer Learning
Urban transfer learning transfers knowledge from the data-rich city to the data-scarce city, effectively solving the cold-start crowd flow prediction problem. In urban transfer learning, the selection of sourc...
-
Chapter and Conference Paper
A Reliable Service Function Chain Orchestration Method Based on Federated Reinforcement Learning
The novel cloud-edge collaborative computing architecture can provide more efficient and intelligent services close to users. Reliable service function chain orchestration among datacenters is critical to ensu...
-
Chapter and Conference Paper
CCMT 2022 Translation Quality Estimation Task
This paper presents the method used by Huawei Translation Services Center (HW-TSC) in the quality estimation (QE) task: sentence-level post-editing effort estimation in the 18th China Conference on Machine Tra...
-
Chapter and Conference Paper
SMPG: Adaptive Soft Update for Masked MADDPG
In multi-agent systems, deep reinforcement learning policy gradient algorithms can converge excessively slowly or even fail to converge if the agent size as well as the state information quickly grows. We cons...
