A5006269744- Face and Expression Recognition
- Text and Document Classification Technologies
- Advanced Computing and Algorithms
- Video Surveillance and Tracking Methods
- Music and Audio Processing
- Domain Adaptation and Few-Shot Learning
- Advanced Clustering Algorithms Research
- Image Retrieval and Classification Techniques
- Advanced Image and Video Retrieval Techniques
- Multimodal Machine Learning Applications
- Remote-Sensing Image Classification
- Video Analysis and Summarization
- Speech Recognition and Synthesis
- Human Pose and Action Recognition
- Sparse and Compressive Sensing Techniques
- Speech and Audio Processing
- Advanced materials and composites
- Intermetallics and Advanced Alloy Properties
- Tensor decomposition and applications
- Machine Learning and Data Classification
- High Temperature Alloys and Creep
- Advanced Data Compression Techniques
- Extraction and Separation Processes
- Additive Manufacturing and 3D Printing Technologies
- 3D Modeling in Geospatial Applications
Fuzhou University
2012-2025
Shandong University
2024
Xi'an Jiaotong University
2017-2022
Recently, label distribution learning (LDL) has drawn much attention in machine learning, where LDL model is learned from labelel instances. Different single-label and multi-label annotations, distributions describe the instance by multiple labels with different intensities accommodate to more general scenes. Since most existing datasets merely provide logical labels, are unavailable many real-world applications. To handle this problem, we propose two novel enhancement methods, i.e., Label...
In this paper, we delve into the challenging problem in multi-view learning, namely unsupervised representation goal of which is to effectively integrate information from multiple views and learn unified feature with comprehensive an manner. Despite progress attained recent years, it still a issue since correlations across are complex difficult model during learning process, especially absence label information. To address problem, introduce novel method, termed Collaborative Unsupervised...
Without the valuable label information to guide learning process, it is demanding fully excavate and integrate underlying from different views learn unified multi-view representation. This paper focuses on this challenge presents a novel method, termed Graph-guided Unsupervised Multi-view Representation Learning (GUMRL), taking full advantage of graph during process. To be specific, GUMRL jointly conducts view-specific feature representation learning, which under guidance information, fuses...
Multi-view clustering has attracted significant attention in recent years because it can leverage the consistent and complementary information of multiple views to improve performance. However, effectively fuse balance are common challenges faced by multi-view clustering. Most existing fusion works focus on weighted-sum concatenating fusion, which unable fully underlying information, not consider balancing views. To this end, we propose Cross-view Fusion for Clustering (CFMVC). Specifically,...
Driven by the complementarity and consistency inherent in multiview data, clustering (MVC) has garnered widespread attention various domains. Real-world data often encounters issue of missing information, leading to a surge interest domain incomplete MVC (IMVC). Despite existing approaches having made significant progress addressing IMVC, two challenges persist: 1) many alignment-based methodologies tend overlook topological relationships among instances 2) view representations based on...
Zero-shot Natural Language Video Localization (NLVL) aims to automatically generate moments and corresponding pseudo queries from raw videos for the training of localization model without any manual annotations. Existing approaches typically produce as simple words, which overlook complexity in real-world scenarios. Considering powerful text modeling capabilities large language models (LLMs), leveraging LLMs complete that are closer human descriptions is a potential solution. However,...
The mechanical and thermodynamic properties of intermetallic compounds in the Ni–Ti system are studied by first-principles calculations. All phases show anisotropic elasticity different crystallographic directions, which Ni 3 Ti NiTi 2 approaching isotropy structure. elastic moduli Vicker’s hardness decrease following order: [Formula: see text] B2_NiTi B19[Formula: text]_NiTi , shows best properties. intrinsic ductile nature is confirmed obtained text]/[Formula: ratio. temperature dependence...
Compared with single-label and multi-label annotations, label distribution describes the instance by multiple labels different intensities accommodates to more-general conditions. Nevertheless, learning is unavailable in many real-world applications because most existing datasets merely provide logical labels. To handle this problem, a novel enhancement method, Label Enhancement Sample Correlations via low-rank representation, proposed paper. Unlike methods, representation method employed so...
Large-scale Multi-View Clustering (LMVC) is a hot research problem in the fields of signal processing and machine learning, many anchor-based multi-view subspace clustering algorithms are proposed recent years. However, most existing methods usually concentrate on issue reducing time cost ignore exploration complementary information during process. To this end, we propose Fast Essential Subspace Representation Learning (FESRL) method for large-scale clustering. Specifically, FESRL introduces...