Results 111 to 120 of about 1,404 (207)

Dual convolutional network based on hypergraph and multilevel feature fusion for road extraction from high-resolution remote sensing images

International Journal of Digital Earth
Road extraction from high-resolution remote sensing images (HRSI) is confronted with the challenge that roads are occluded by other objects, including opaque obstructions and similarly colored areas. This paper proposes a dual convolutional network based
BoWen Li, XiangHong Tang, Rang Xiao, JianGuang Lu, YuHao Wang   +4 more
doaj   +1 more source

Prototype-Enhanced Hypergraph Learning for Heterogeneous Information Networks [PDF]

The variety and complexity of relations in multimedia data lead to Heterogeneous Information Networks (HINs). Capturing the semantics from such networks requires approaches capable of utilizing the full richness of the HINs. Existing methods for modeling
Efthymiou, A., Wijnberg, N.; id_orcid, Shen, J., Worring, M.; id_orcid, Rudinac, S., Kackovic, M.; id_orcid, Wang, S.; id_orcid   +6 more
core   +1 more source

HGSNet: A hypergraph network for subtle lesions segmentation in medical imaging

IET Image Processing
Lesion segmentation is a fundamental task in medical image processing, often facing the challenge of subtle lesions. It is important to detect these lesions, even though they can be difficult to identify.
Junze Wang, Wenjun Zhang, Dandan Li, Chao Li, Weipeng Jing   +4 more
doaj   +1 more source

Hyperedge Anomaly Detection with Hypergraph Neural Network

CoRR
Hypergraph is a data structure that enables us to model higher-order associations among data entities. Conventional graph-structured data can represent pairwise relationships only, whereas hypergraph enables us to associate any number of entities, which is essential in many real-life applications.
Md. Tanvir Alam, Chowdhury Farhan Ahmed, Carson K. Leung   +2 more
openaire   +2 more sources

ERP Insights and Truncated SVD in Conjunction with Dual-Tree Complex Wavelet Transform and Multi-View Hypergraph Neural Networks for Cognitive Distortion Analysis

International Journal of Computational Intelligence Systems
Multi-modal EEG data analysis requires sophisticated methods for accurate prediction in the critical area of cognitive depression study in neuroscience.
N. Banupriya, Neelakandan Subramani, M. Prakash, S. Velmurugan   +3 more
doaj   +1 more source

A Novel EEG-Based Hypergraph Convolution Network for Depression Detection: Incorporating Unified Brain Network and Multi-Segment Spatiotemporal EEG Features

IEEE Access
Detecting depression from Electroencephalography (EEG) signals remains a challenging task due to the complexity of brain networks and the significant individual differences in neural activity. Traditional models significantly fall short: 1) capturing the
Sudipta Priyadarshinee, Madhumita Panda
doaj   +1 more source

Hypergraph Neural Networks Accelerate MUS Enumeration

CoRR
Enumerating Minimal Unsatisfiable Subsets (MUSes) is a fundamental task in constraint satisfaction problems (CSPs). Its major challenge is the exponential growth of the search space, which becomes particularly severe when satisfiability checks are expensive.
Hiroya Ijima, Koichiro Yawata
openaire   +2 more sources

HyperMagNet: A Magnetic Laplacian based Hypergraph Neural Network

In data science, hypergraphs are natural models for data exhibiting multi-way relations, whereas graphs only capture pairwise. Nonetheless, many proposed hypergraph neural networks effectively reduce hypergraphs to undirected graphs via symmetrized ...
Amburg, Ilya, Benko, Tatyana, Aksoy, Sinan G., Buck, Martin, Young, Stephen J.   +4 more
core  

SSRES: A Student Academic Paper Social Recommendation Model Based on a Heterogeneous Graph Approach

Mathematics
In an era overwhelmed by academic big data, students grapple with identifying academic papers that resonate with their learning objectives and research interests, due to the sheer volume and complexity of available information.
Yiyang Guo, Zheyu Zhou
doaj   +1 more source

EquiHGNN: Scalable rotationally equivariant hypergraph neural networks

The Journal of Chemical Physics
Molecular interactions often involve higher-order relationships that cannot be fully captured by traditional graph-based models limited to pairwise connections. Hypergraphs naturally extend graphs by enabling multi-way interactions, making them well-suited for modeling complex molecular systems.
Tien Dang, Truong-Son Hy
openaire   +2 more sources