A5046010508- Advanced Clustering Algorithms Research
- Face and Expression Recognition
- Tensor decomposition and applications
- IoT and Edge/Fog Computing
- Blockchain Technology Applications and Security
- Privacy-Preserving Technologies in Data
- Advanced Image and Video Retrieval Techniques
- Advanced Neuroimaging Techniques and Applications
- FinTech, Crowdfunding, Digital Finance
- Cloud Computing and Resource Management
- Image Retrieval and Classification Techniques
- Text and Document Classification Technologies
- Internet Traffic Analysis and Secure E-voting
- Mobile Crowdsensing and Crowdsourcing
- Robotics and Sensor-Based Localization
- Traffic Prediction and Management Techniques
- Advanced Vision and Imaging
Sun Yat-sen University
2022-2025
With the continuous development of web technology, Web 3.0 has attracted a considerable amount attention due to its unique decentralized characteristics. The digital economy is an important driver high-quality economic and currently in rapid stage. In scenario, centralized nature Internet other characteristics usually bring about security issues such as infringement privacy leakage. Therefore, it necessary investigate how use technologies solve pain points encountered by fully exploring...
Federated Learning (FL) provides a novel paradigm for privacy-preserving machine learning, enabling multiple clients to collaborate on model training without sharing private data. To handle multi-source heterogeneous data, Vertical (VFL) has been extensively investigated. However, in the context of VFL, label information tends be kept one authoritative client and is very limited. This poses two challenges VFL scenario. On hand, small number labels cannot guarantee train well with informative...
Most multi-view clustering methods based on shallow models are limited in sound nonlinear information perception capability, or fail to effectively exploit complementary hidden different views. To tackle these issues, we propose a novel Subspace-Contrastive Multi-View Clustering (SCMC) approach. Specifically, SCMC utilizes set of view-specific auto-encoders map the original data into compact features capturing its structures. Considering large semantic gap from modalities, project multiple...
In deep multi-view clustering, three intractable problems are posed ahead of researchers, namely, the complementarity exploration problem, information preservation and cluster structure discovery problem. this paper, we consider clustering from perspective mutual (MI), attempt to address important concerns with a Mutual Information-Driven Multi-View Clustering (MIMC) method, which extracts common view-specific hidden in data constructs clustering-oriented comprehensive representation....
The neural radiance field (NeRF) has emerged as a prominent methodology for synthesizing realistic images of novel views. While representations based on voxels or mesh individually offer distinct advantages, excelling in either rendering quality speed, each limitations the other aspect. In response, we propose pioneering hybrid representation named Vosh, seamlessly combining both voxel and components view synthesis. Vosh is meticulously crafted by optimizing grid NeRF, strategically with...