A5100418527- Advanced Graph Neural Networks
- Recommender Systems and Techniques
- Topic Modeling
- Multimodal Machine Learning Applications
- Advanced Neural Network Applications
- Caching and Content Delivery
- Human Pose and Action Recognition
- Generative Adversarial Networks and Image Synthesis
- Advanced MIMO Systems Optimization
- Bayesian Modeling and Causal Inference
- Emotion and Mood Recognition
- Numerical methods in inverse problems
- Advanced Image and Video Retrieval Techniques
- Sentiment Analysis and Opinion Mining
- Image Enhancement Techniques
- Video Analysis and Summarization
- Software-Defined Networks and 5G
- Remote-Sensing Image Classification
- Digital Imaging for Blood Diseases
- Energy Harvesting in Wireless Networks
- Rough Sets and Fuzzy Logic
- Stability and Controllability of Differential Equations
- Image and Object Detection Techniques
- Underwater Acoustics Research
- Simulation and Modeling Applications
Wuxi Taihu Hospital
2025
Xidian University
2021-2024
Xinjiang University
2024
Northwest University
2010
Deep learning (DL)-based object detection algorithms have gained impressive achievements in natural images and gradually matured recent years. However, compared with images, remote sensing are faced severe challenges due to the complex backgrounds difficult of small objects dense scenes. To address these problems, a novel one-stage model named MDCT is proposed based on multi-kernel dilated convolution (MDC) block transformer block. Firstly, new feature enhancement module, MDC block,...
Recently, Multimodal Sentiment Analysis (MSA) is a challenging research area given its complex nature, and humans express emotional cues across various modalities such as language, facial expressions, speech. Representation fusion of features are the most crucial tasks in multimodal sentiment analysis research. However, current research, methods ignore importance eliminating potential irrelevant original each modality cross-modal common feature. Moreover, extracted from all contain cluttered...
Image-text matching has become a challenging task in the multimedia analysis field. Many advanced methods have been used to explore local and global cross-modal correspondence matching. However, most ignore importance of eliminating potential irrelevant features original each modality common feature. Moreover, extracted from regions images words sentences contain cluttered background noise different occlusion noise, which negatively affects alignment. Different these methods, we propose...
The core idea of cross-domain recommendation is to alleviate the problem data scarcity. Previous methods have made brilliant successes. However, many them mainly focus on learning an ideal mapping function across-domains, ignoring user preferences within a specific domain, which leads suboptimal results. In this paper, we propose Cross-Domain Recommendation Variational AutoEncoder framework (CDRVAE), novel extension variational autoencoder recommendations for behaviour distribution modeling....
Data sparsity and cold start problems are common in recommender systems. Adding some side information, such as knowledge graph users' trust relationship, is an effective method to alleviate these problems. However, few work jointly explore the fine-grained implicit relationships between external heterogeneous graphs enhance recommendation accuracy. To address this issue, paper, we propose a new named Trust-aware Multi-task Knowledge Graph (TMKG), which uses multi-task learning integrate two...
The incompleteness of knowledge graphs (KGs) negatively impacts the performance KGs in downstream applications (e.g., recommendation systems and information retrieval). This phenomenon has brought an increasing rise research related to graph reasoning. Recently, emerged reinforcement learning (RL)-based multi-hop reasoning methods can infer missing through according existing KGs, which better interpretability. However, these always use relation-entity pairs that have been pre-cropped as...
Prosodic model makes the speech synthesis system has a rhythm of simulation and emulation capabilities, it plays crucial role to enhance naturalness synthesized speech. The paper studies Tibetan rhythmic structure based on characteristics Lhasa Tibetan, determines parameters that affect prosodic features. To meet actual needs establishing high-quality model, designs corpus selection rules optimizes it. annotation is proposed been eventually established. highly scientifically completed, which...
This paper is concerned with a backward problem of stochastic partial differential equation bi-harmonic operator. The source term driven by fractional Brownian motion. Based on the Gevrey-type space, regularity mild solution studied. However, this ill-posed since it unstable. instability discussed in sense expectation and variance. Moreover, regularization method proposed. error estimation between given using an prior parameter choice rule.