Results 151 to 160 of about 1,673 (179)

Adaptive algorithms for hypergraph learning

2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016
Social media sharing platforms enable image content as well as context information (e.g., user friendships, geo-tags assigned to images) to be jointly analyzed in order to achieve accurate image annotation or successful image recommendation. The context information is expressed frequently in terms of high-order relations, such as the relations among ...
Aikaterini Chasapi, Constantine Kotropoulos, Konstantinos Pliakos   +2 more
openaire   +1 more source

Learning a hidden uniform hypergraph

Optimization Letters, 2017
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Huilan Chang, Hung-Lin Fu, Chih-Huai Shih   +2 more
openaire   +2 more sources

Scalable Hypergraph Learning and Processing

2015 IEEE International Conference on Data Mining, 2015
A hypergraph allows a hyperedge to connect more than two vertices, using which to capture the high-order relationships, many hypergraph learning algorithms are shown highly effective in various applications. When learning large hypergraphs, converting them to graphs to employ the distributed graph frameworks is a common approach, yet it results in ...
Jin Huang 0003, Rui Zhang 0003, Jeffrey Xu Yu   +2 more
openaire   +1 more source

Weight estimation in hypergraph learning

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015
The unremitting rising popularity of social media has led to an exponential increase in web activity as manifested by the vast volume of uploaded images. This boundless volume of image data has triggered the interest in image tagging. Here, an efficient hypergraph weight estimation scheme is proposed that improves the accuracy of image tagging, using ...
Konstantinos Pliakos, Constantine Kotropoulos   +1 more
openaire   +1 more source

Non-adaptive Learning of a Hidden Hypergraph

Theoretical Computer Science, 2015
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Hasan Abasi, Nader H. Bshouty, Hanna Mazzawi   +2 more
openaire   +2 more sources

Hypergraph Attention Networks for Multimodal Learning

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020
One of the fundamental problems that arise in multimodal learning tasks is the disparity of information levels between different modalities. To resolve this problem, we propose Hypergraph Attention Networks (HANs), which define a common semantic space among the modalities with symbolic graphs and extract a joint representation of the modalities based ...
Eun-Sol Kim, Woo-Young Kang, Kyoung-Woon On, Yu-Jung Heo, Byoung-Tak Zhang   +4 more
openaire   +1 more source

Self-supervised hypergraph structure learning

Artificial Intelligence Review
Zhonglin Ye, Haixing Zhao, Yanlin Yang   +2 more
exaly   +2 more sources

Hypergraph Learning With Cost Interval Optimization

Proceedings of the AAAI Conference on Artificial Intelligence, 2018
In many classification tasks, the misclassification costs of different categories usually vary significantly. Under such circumstances, it is essential to identify the importance of different categories and thus assign different misclassification losses in many applications, such as medical diagnosis, saliency detection and software ...
Xibin Zhao, Nan Wang 0015, Heyuan Shi, Hai Wan, Jin Huang 0002, Yue Gao 0002   +5 more
openaire   +1 more source

Metric learning based on attribute hypergraph

2017 IEEE International Conference on Image Processing (ICIP), 2017
In this paper, we propose an improved attribute hypergraph learning framework and adapt it for metric learning. Under the attribute hypergraph, each image is abstracted as a vertex and is contained in some hyperedges, each of which represents an attribute.
Yuchun Fang, Yandan Zheng
openaire   +1 more source

Hypergraph regularized sparse feature learning

Neurocomputing, 2017
As an important pre-processing stage in many machine learning and pattern recognition domains, feature selection deems to identify the most discriminate features for a compact data representation. As typical feature selection methods, Lasso and its variants using the l1-norm based regularization have received much attention in recent years.
Mingxia Liu 0001, Jun Zhang 0018, Xiaochun Guo, Liujuan Cao   +3 more
openaire   +1 more source