A5091320821- Face and Expression Recognition
- Advanced Image Fusion Techniques
- Anomaly Detection Techniques and Applications
- Image Enhancement Techniques
- Advanced Image and Video Retrieval Techniques
- Image Processing Techniques and Applications
- Video Surveillance and Tracking Methods
- Advanced Image Processing Techniques
- Digital Imaging for Blood Diseases
- Medical Image Segmentation Techniques
- Advanced Neural Network Applications
- Image Retrieval and Classification Techniques
- Environmental Quality and Pollution
- Traditional Chinese Medicine Studies
- AI in cancer detection
- Image and Signal Denoising Methods
- Evaluation Methods in Various Fields
- Image and Object Detection Techniques
- Domain Adaptation and Few-Shot Learning
- Sparse and Compressive Sensing Techniques
- Remote-Sensing Image Classification
- Visual Attention and Saliency Detection
- Retinal Imaging and Analysis
- Remote Sensing and Land Use
- Advanced Vision and Imaging
Minjiang University
2016-2025
Fujian University of Technology
2022-2024
Fujian Provincial Hospital
2023
Zhengzhou University
2023
First Affiliated Hospital of Gannan Medical University
2022
Chengdu University of Information Technology
2006-2020
Fujian University of Traditional Chinese Medicine
2019
Nanjing Institute of Technology
2014-2018
Nanjing University of Posts and Telecommunications
2018
University of North Carolina at Chapel Hill
2015
Anomaly detection on attributed networks aims at finding nodes whose patterns deviate significantly from the majority of reference nodes, which is pervasive in many applications such as network intrusion and social spammer detection. However, most existing methods neglect complex cross-modality interactions between structure node attribute. In this paper, we propose a deep joint representation learning framework for anomaly through dual autoencoder (AnomalyDAE), captures attribute...
Digital pathology and microscope image analysis is widely used in comprehensive studies of cell morphology. Identification leukocytes blood smear images, acquired from bright field microscope, are vital for diagnosing many diseases such as hepatitis, leukaemia immune deficiency syndrome (AIDS). The major challenge robust accurate identification segmentation leukocyte images lays the large variations appearance size, colour shape cells, adhesion between (white WBCs) erythrocytes (red RBCs),...
Link prediction aims at inferring missing links or predicting future ones based on the currently observed network. This topic is important for many applications such as social media, bioinformatics and recommendation systems. Most existing methods focus homogeneous settings consider only low-order pairwise relations while ignoring either heterogeneity high-order complex among different types of nodes, which tends to lead a sub-optimal embedding result. paper presents method named...
The resting-state functional magnetic resonance imaging (rs-fMRI) reflects activity of brain regions by blood-oxygen-level dependent (BOLD) signals. Up to now, many computer-aided diagnosis methods based on rs-fMRI have been developed for Autism Spectrum Disorder (ASD). These are mostly the binary classification approaches determine whether a subject is an ASD patient or not. However, disease often consists several sub-categories, which complex and thus still confusing automatic methods....
Abstract In order to solve the problem of human motion recognition in multimedia interaction scenarios virtual reality environment, a classification and algorithm based on linear decision support vector machine (SVM) is proposed. Firstly, kernel function introduced into discriminant analysis for nonlinear projection map training samples high-dimensional subspace obtain best feature vector, which effectively solves expands sample difference. The genetic used realize parameter search...
Networks are ubiquitous in the real world such as social networks and communication networks, anomaly detection on aims at finding nodes whose structural or attributed patterns deviate significantly from majority of reference nodes. However, most traditional methods neglect relation structure information among data points therefore cannot effectively generalize to graph data. In this paper, we propose an end-to-end model Deep Dual Support Vector Data description based Autoencoder...