Joint distribution matters: Deep brownian distance covariance for few-shot classification
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 …
given for each new task. One of the effective research lines to address this challenge …
Fine-grained image analysis with deep learning: A survey
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 …
vision and pattern recognition, and underpins a diverse set of real-world applications. The …
Class attention network for image recognition
Visual attention has become a popular and widely used component for image recognition.
Although various attention-based methods have been proposed and achieved relatively …
Although various attention-based methods have been proposed and achieved relatively …
Multi-stream hybrid architecture based on cross-level fusion strategy for fine-grained crop species recognition in precision agriculture
Precision farming aims to optimizing the crop production process and managing sustainable
supply chain practices as more efficient and reasonable as possible. Recently, various …
supply chain practices as more efficient and reasonable as possible. Recently, various …
Deep learning-enabled orbital angular momentum-based information encryption transmission
Orbital angular momentum (OAM)-based optical encryption transmission plays an important
role in optical communications. However, it remains challenging to encrypt the data with …
role in optical communications. However, it remains challenging to encrypt the data with …
Neural koopman pooling: Control-inspired temporal dynamics encoding for skeleton-based action recognition
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 …
fields. Most existing works train a CNN or GCN based backbone to extract spatial-temporal …
Bi-directional object-context prioritization learning for saliency ranking
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 …
would typically shift their attention over different objects of a scene based on their degrees of …
Remote sensing image scene classification using multiscale feature fusion covariance network with octave convolution
L Bai, Q Liu, C Li, Z Ye, M Hui… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
In remote sensing scene classification (RSSC), features can be extracted with different
spatial frequencies where high-frequency features usually represent detailed information …
spatial frequencies where high-frequency features usually represent detailed information …
Second-order pooling for graph neural networks
Graph neural networks have achieved great success in learning node representations for
graph tasks such as node classification and link prediction. Graph representation learning …
graph tasks such as node classification and link prediction. Graph representation learning …
Learning partial correlation based deep visual representation for image classification
Visual representation based on covariance matrix has demonstrates its efficacy for image
classification by characterising the pairwise correlation of different channels in convolutional …
classification by characterising the pairwise correlation of different channels in convolutional …