Search Results

Most ultrasound image segmentation methods employ a joint training strategy, where the model learns the edge and core regions indiscriminately and uniformly. However, they often overlook the distinct shapes of the edges and the sizes of the core regions. ...

Directed Graph convolutional networks (DGCNs) have been indeed gaining attention and being applied in skeleton-based action recognition tasks to capture the hierarchical relationships of skeleton via directed graph topology. However, they ...

Display Omitted

• Introducing VA-DGCN with average posture as anchor to boost spatial variation emphasis.
• Utilizing a channel-specific topology branch for diverse channel topologies.
• Designing MCTC module with contrastive learning for improved multi-...

With the end of the COVID-19 pandemic, the number of pedestrians in various public places has increased dramatically. Estimating the size and density distribution of crowds accurately from images is essential for public safety. At present, there ...

The neuron model as a computational unit not only determines the performance of widely used deep neural networks and emerging quantum neural networks, but in turn facilitates research on biological neurons. Current three generations of models, ...

Crowd counting has made great progress in recent years, however, problems such as sharp scale variation and background noise still seriously affect counting accuracy. To address the above two deep-rooted challenges, we purposefully propose a ...

Deep neural networks have demonstrated superior performance in artificial intelligence applications, but the opaqueness of their inner working mechanism is one major drawback in their application. The prevailing unit-based interpretation is a ...

As an indispensable component of intelligent monitoring systems, crowd counting plays a crucial role in many fields, particularly crowd management and control during the COVID-19 pandemic. Despite the promising achievements of many methods, crowd ...

Supervised human action recognition methods based on skeleton data have achieved impressive performance recently. However, many current works emphasize the design of different contrastive strategies to gain stronger supervised signals, ignoring the ...

Wearable health monitoring is a crucial technical tool that offers early warning for chronic diseases due to its superior portability and low power consumption. However, most wearable health data is distributed across different organizations, such ...

With the aid of graph convolution neural network and transformer model, human action recognition has achieved significant performance based on skeleton data. However, the majority of existing works rarely focus on identifying fine-grained motion ...

Skeleton-based action recognition is widely used in varied areas such as human–machine interaction and virtual reality. Benefit from the powerful expression ability to depict structural data, graph convolutional networks (GCNs) have been ...

• A multi-stream model Global–Local Motion Fusion Network is proposed.
• Grouping GCN aims to enforce the ability to aggregate local spatial information.
• Spatial Self-attention aims to extract spatial long-term motion relationships.

As an emerging computer vision task, crowd localization has received increasing attention due to its ability to produce more accurate spatially predictions. However, continuous scale variations in complex crowd scenes lead to tiny individuals at the edges,...

Most existing crowd evacuation methods focus on internal factors and do not consider the influence of the external environment factors, producing unrealistic global behavior occurs when individuals are moving through the crowded space. As an ...

Session-based recommendation (SBR) aims to predict the next item at a certain time point based on anonymous user behavior sequences. Existing methods typically model session representation based on simple item transition information. However, since ...

For pursuing accurate skeleton-based action recognition, most prior methods combine Graph Convolution Networks (GCNs) with attention-based methods in a serial way. However, they regard the human skeleton as a complete graph, resulting in less variations ...

• An adaptive multi level graph convolutional network (AML GCN) is proposed, which enables complementarity between the non sharing and dynamics of topological ...

Graph Convolutional Networks (GCNs) have been widely used in skeleton-based action recognition with remarkable achievements. Many recent studies model the human body as a topological graph and extract action features using GCNs, ...

Code summarization aims to generate high-quality functional summaries of code snippets to improve the efficiency of program development and maintenance. It is a pressing challenge for code summarization models to capture more ...

• Local-ADG: A code semantic structure to express API relationships of code snippets.

The purpose of crowd counting is to estimate the number of people in an image. Due to the unconstrained imaging conditions, the scale variation and background occlusion in the images make it still challenging to achieve counting accurately. To ...

Background: Code summarization automatically generates the corresponding natural language descriptions according to the input code to characterize the function implemented by source code. Comprehensiveness of code representation is critical to code ...

The goal of session-based recommendation (SBR) is to predict the next item at a certain point in time for anonymous users. Previous methods usually learn session representations based on the item prediction loss, and session-based data ...