Few-shot classification is a challenging problem as only very few training examples are
given for each new task. One of the effective research lines to address this challenge …

Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer
vision and pattern recognition, and underpins a diverse set of real-world applications. The …

Visual attention has become a popular and widely used component for image recognition.
Although various attention-based methods have been proposed and achieved relatively …

Precision farming aims to optimizing the crop production process and managing sustainable
supply chain practices as more efficient and reasonable as possible. Recently, various …

Orbital angular momentum (OAM)-based optical encryption transmission plays an important
role in optical communications. However, it remains challenging to encrypt the data with …

Skeleton-based human action recognition is becoming increasingly important in a variety of
fields. Most existing works train a CNN or GCN based backbone to extract spatial-temporal …

The saliency ranking task is recently proposed to study the visual behavior that humans
would typically shift their attention over different objects of a scene based on their degrees of …

In remote sensing scene classification (RSSC), features can be extracted with different
spatial frequencies where high-frequency features usually represent detailed information …

Graph neural networks have achieved great success in learning node representations for
graph tasks such as node classification and link prediction. Graph representation learning …

Visual representation based on covariance matrix has demonstrates its efficacy for image
classification by characterising the pairwise correlation of different channels in convolutional …