Federated learning (FL) enables resource-constrained node devices to learn a shared model while keeping the training data local. Since recent research has demonstrated multiple privacy leakage attacks in FL, e.g., gradient inference attacks and membership ...

The paper introduces AniTalker, an innovative framework designed to generate lifelike talking faces from a single portrait. Unlike existing models that primarily focus on verbal cues such as lip synchronization and fail to capture the complex dynamics of ...

Achieving a high-quality and fine-grained appearance representation is an important task in Multi-Object Tracking (MOT). Recent works learn responses of different locations or channels from the global feature map to enhance visible parts or weaken ...

In diffusion MRI (dMRI), a uniform single or multiple shell sampling scheme is typically required for data acquisition in $\mathbf{q}$-space, because uniform spherical sampling offers the advantage of capturing more information using fewer samples, leading ...

Natural neighbor (NaN) algorithm, as a parameter-free alternative to KNN, is widely used in various fields such as pattern recognition and machine learning. However, the original NaN algorithm only takes the Euclidean distance of the samples as ...

With the development of neural radiance fields and generative models, numerous methods have been proposed for learning 3D human generation from 2D images. These methods allow control over the pose of the generated 3D human and enable rendering ...${\mathrm{}}^{\mathrm{}}$${\mathrm{}}^{\mathrm{}}$

Existing parallel logging schemes are unsuitable for lower isolation levels due to tracking all dependencies of transactions. To overcome this problem, we present a high-performance parallel logging scheme (Poplar) in database management systems (...$\mathrm{}$$\mathrm{}$$\mathrm{}$$\mathrm{}$

Gradient leakage attack allow attackers to infer Privacy data, which raises concerns about data leakage. To solve this problem, a series of methods have been proposed, while previously proposed methods have two weaknesses. First, adding noise (...

The human brain is the most complex system in the human body, and understanding and treating brain-related diseases has always been a challenge for medical professionals. Recent research suggests that attention deficit hyperactivity disorder (ADHD)...

To enhance students’ self-management skills and improve the effectiveness of online learning, and to help teachers understand each student’s learning behavior, this paper proposes and designs an attention detection algorithm based on the temporal ...

The broadband hybrid spread spectrum system possesses the advantages of both direct spread spectrum and frequency hopping systems. All-digital receiving is the development trend of hybrid spread spectrum systems. In this paper, researchers propose a ...

Expanding tunneling has consistently been one of the approaches to enhance the on-state current (I o n) and performance of Tunnel Field-Effect Transistor (TFET). This paper proposes a novel structure for TFET called Step Tunneling Path TFET (STP ...

• By incorporating a pocket,the conventional point tunneling is enhanced to step tunneling.The on-state current of the TFETs is boosted.
• The partially depleted operation mechanism enables STP-TFETs to obtain larger currents at lower gate ...

The dynamic operational mechanisms of the brain in autism spectrum disorder (ASD) remain unclear. In this study, utilizing resting-state functional magnetic resonance imaging (fMRI) technology, we aimed to analyze the spatiotemporal ...

We introduce a novel neural network-based computational pipeline as a representation-agnostic slicer for multi-axis 3D printing. This advanced slicer can work on models with diverse representations and intricate topology. The approach involves employing ...

Oversampling-based methods achieve impressive performance for classifying imbalanced data. However, many existing oversampling algorithms are still very sensitive to noise. Besides, these algorithms also require one or more parameters, how to set ...

• This study proposes a model capable of identifying the phenological stages of wheat.
• The camera combined with unmanned aerial vehicle are employed for biomass estimation.
• The wheat biomass estimating accuracy is improved by ...

Conventional models for estimating crop biomass are influenced by the wheat fertility process and often result in large errors, limiting the accurate crop biomass monitoring throughout the reproductive period. In this study, we developed a ResNet-...

Image Signal Processor (ISP) is widely used in intelligent edge devices across various scenarios. The intricate and time-consuming tuning process demands substantial expertise. Current AI-based auto-tuning operates discretely offline, relying on ...

Total talus replacement is an alternative treatment to ankle fusion for talus fractures resulting from avascular necrosis and collapse. It involves the complete replacement of the human talus bone with an artificial implant that allows for maintaining ...

Utilizing musculoskeletal modeling through an inverse dynamics approach for gait assessment offers a non-invasive method to compute internal joint kinetics and ground reaction forces and moments solely from kinematic data, reducing reliance on cumbersome ...

At present, high-performance computing plays a crucial role in enhancing the national economy, advancing science and technology, and strengthening national defence. Sunway Bluelight II Supercomputer, as a leading example of high-performance computing, ...