10.1109/CVPR.2012.6247961Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition2464-2471PIVR
A significant portion of the data today, e.g, social networks, web connections, etc., can be modeled...
The graph embedding process aims to transform nodes and edges into a low dimensional vector space, w...
Graph data are prevalent in communication networks, social media, and biological networks. These dat...
Non-negative data factorization has been widely used re-cently. However, existing techniques, such a...
10.1109/CVPR.2008.458766526th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
Abstract—Nonnegative Matrix Factorization (NMF) has re-ceived considerable attention in image proces...
The existing non-negative matrix factorization (NMF) algorithms still have some shortcomings. On one...
In this paper, we study the problem of nonnegative graph embedding, originally investigated in [14] ...
Graph embedding methods are useful for a wide range of graph analysis tasks including link predictio...
The performance of graph representation learning is affected by the quality of graph input. While ex...
Graph Embedding for Pattern Analysis covers theory methods, computation, and applications widely use...
This is the Supplementary Material of the submitted RAL paper: Binary Graph Descriptor for Robust Re...
© 2018, The Author(s). A graph-based classification method is proposed for both semi-supervised lear...
International audienceKnowledge graph (KG) embedding methods learn the low dimensional vector repres...
In this paper, we propose novel algorithms for low dimensionality nonnegative embedding of vectorial...
A significant portion of the data today, e.g, social networks, web connections, etc., can be modeled...
The graph embedding process aims to transform nodes and edges into a low dimensional vector space, w...
Graph data are prevalent in communication networks, social media, and biological networks. These dat...
Non-negative data factorization has been widely used re-cently. However, existing techniques, such a...
10.1109/CVPR.2008.458766526th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
Abstract—Nonnegative Matrix Factorization (NMF) has re-ceived considerable attention in image proces...
The existing non-negative matrix factorization (NMF) algorithms still have some shortcomings. On one...
In this paper, we study the problem of nonnegative graph embedding, originally investigated in [14] ...
Graph embedding methods are useful for a wide range of graph analysis tasks including link predictio...
The performance of graph representation learning is affected by the quality of graph input. While ex...
Graph Embedding for Pattern Analysis covers theory methods, computation, and applications widely use...
This is the Supplementary Material of the submitted RAL paper: Binary Graph Descriptor for Robust Re...
© 2018, The Author(s). A graph-based classification method is proposed for both semi-supervised lear...
International audienceKnowledge graph (KG) embedding methods learn the low dimensional vector repres...
In this paper, we propose novel algorithms for low dimensionality nonnegative embedding of vectorial...
A significant portion of the data today, e.g, social networks, web connections, etc., can be modeled...
The graph embedding process aims to transform nodes and edges into a low dimensional vector space, w...
Graph data are prevalent in communication networks, social media, and biological networks. These dat...
DOI
Add to ORKG