Semi-supervised multi-view deep discriminant representation learning
Learning an expressive representation from multi-view data is a key step in various real-
world applications. In this paper, we propose a semi-supervised multi-view deep …
world applications. In this paper, we propose a semi-supervised multi-view deep …
MMatch: Semi-supervised discriminative representation learning for multi-view classification
Semi-supervised multi-view learning has been an important research topic due to its
capability to exploit complementary information from unlabeled multi-view data. This work …
capability to exploit complementary information from unlabeled multi-view data. This work …
Video anomaly detection guided by clustering learning
S Qiu, J Ye, J Zhao, L He, L Liu, E Bicong, X Huang - Pattern Recognition, 2024 - Elsevier
With the fuzzy boundary between normal and abnormal video data, which cannot be well
distinguished by most methods, anomaly detection in video requires better characterization …
distinguished by most methods, anomaly detection in video requires better characterization …
Learning enhanced specific representations for multi-view feature learning
Y Hao, XY Jing, R Chen, W Liu - Knowledge-Based Systems, 2023 - Elsevier
Multi-view data has two basic characteristics: consensus property and complementary
property, in which complementary information refers to all view-specific information. Inspired …
property, in which complementary information refers to all view-specific information. Inspired …
Semi-supervised classification of dual-frequency polsar image using joint feature learning and cross label-information network
X Xin, M Li, Y Wu, M Zheng, P Zhang… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Dual-frequency polarimetric synthetic aperture radar (PolSAR) data can provide more
information than single-frequency data, which can effectively improve classification …
information than single-frequency data, which can effectively improve classification …
Self-Supervised deep correlational multi-view clustering
In conventional unsupervised multi-view clustering (MVC), learning of representations from
heterogeneous multiview data and its subsequent clustering are often separately optimized …
heterogeneous multiview data and its subsequent clustering are often separately optimized …
Deep constrained low-rank subspace learning for multi-view semi-supervised classification
Semi-supervised classification receives increasing interests because it can predict class
labels based on both limited labeled and sufficient unlabeled data. In this letter, we propose …
labels based on both limited labeled and sufficient unlabeled data. In this letter, we propose …
Inferring the importance of product appearance with semi-supervised multi-modal enhancement: A step towards the screenless retailing
Nowadays, almost all the online orders were placed through screened devices such as
mobile phones, tablets, and computers. With the rapid development of the Internet of Things …
mobile phones, tablets, and computers. With the rapid development of the Internet of Things …
Persistent Laplacian-enhanced algorithm for scarcely labeled data classification
The success of many machine learning (ML) methods depends crucially on having large
amounts of labeled data. However, obtaining enough labeled data can be expensive, time …
amounts of labeled data. However, obtaining enough labeled data can be expensive, time …
Co-embedding: a semi-supervised multi-view representation learning approach
X Jia, XY Jing, X Zhu, Z Cai, CH Hu - Neural Computing and Applications, 2022 - Springer
Learning an expressive representation from multi-view data is a crucial step in various real-
world applications. In this paper, we propose a semi-supervised multi-view representation …
world applications. In this paper, we propose a semi-supervised multi-view representation …