7 Result(s)
within
**aoran Duan
Computer Science
-
Article
Open AccessNode and edge dual-masked self-supervised graph representation
Self-supervised graph representation learning has been widely used in many intelligent applications since labeled information can hardly be found in these data environments. Currently, masking and reconstructi...
-
Article
Dynamic visual-guided selection for zero-shot learning
Zero-shot learning (ZSL) methods currently employed to identify seen or unseen classes rely on semantic attribute prototypes or class information. However, hand-annotated attributes are only for the category r...
-
Article
When Multi-Focus Image Fusion Networks Meet Traditional Edge-Preservation Technology
Generating the decision map with accurate boundaries is the key to fusing multi-focus images. In this paper, we introduce edge-preservation (EP) techniques into neural networks to improve the quality of decisi...
-
Chapter and Conference Paper
Contrast and Aggregation Network for Generalized Zero-shot Learning
Generalized zero-shot learning (GZSL) aims to classify both seen classes and unseen classes by training seen classes and the semantic information shared by seen and unseen classes. Some methods try to synthesi...
-
Chapter and Conference Paper
Channel Pruning for Accelerating Convolutional Neural Networks via Wasserstein Metric
Channel pruning is an effective way to accelerate deep convolutional neural networks. However, it is still a challenge to reduce the computational complexity while preserving the performance of deep models. In...
-
Article
Multifocus image fusion using convolutional neural networks in the discrete wavelet transform domain
In this paper, a novel multifocus image fusion algorithm based on the convolutional neural network (CNN) in the discrete wavelet transform (DWT) domain is proposed. The algorithm combines the advantages of spa...
-
Chapter and Conference Paper
An Authentication Approach for Multiple-User Location-Based Queries
With the increasing use of smart mobile devices, users can connect and coordinate with local people or events that match their interests through geosocial networking applications. This calls for techniques to ...
