Results 41 to 50 of about 24,544,958 (149)

Multi-View Representation Learning with Manifold Smoothness

, 2021
Multi-view representation learning attempts to learn a representation from multiple views and most existing methods are unsupervised. However, representation learned only from unlabeled data may not be discriminative enough for further applications (e.g.,
Chen, Pan, Wang, Wei, Li, Wen-Tao, Li, Shu   +3 more
core   +1 more source

A Novel Information-based Multi-view Representation Learning

Journal of Applied Science and Engineering
Multi-view representation learning methods achieve great performance in various domains via fusing complementary and consistent information of views, which have gained great attention. However, there still exist two issues in current methods.
Hongdan Wang, Jian Zhang
doaj   +1 more source

Transductive Multi-View Zero-Shot Learning [PDF]

, 2015
(c) 2012. The copyright of this document resides with its authors.
Yanwei Fu, Tao Xiang, Fu, Y, Timothy M. Hospedales, Hospedales, T, Shaogang Gong, Xiang, T, Hospedales, TM, Gong, S   +8 more
core   +1 more source

Incomplete multi–view partial multi–label learning network with structure–aware consistent fusion

Journal of King Saud University: Computer and Information Sciences
In recent years, incomplete multi-view partial multi-label classification has attracted growing attention due to its practical relevance. However, many existing methods rely on equal-weight (average) fusion and thus overlook sample-wise reliability ...
Xingang Mao, Yang Xu, Wenbin Bu, Zherui Yang   +3 more
doaj   +1 more source

View-Driven Multi-View Clustering via Contrastive Double-Learning

Entropy
Multi-view clustering requires simultaneous attention to both consistency and the diversity of information between views. Deep learning techniques have shown impressive abilities to learn complex features when working with extensive datasets; however ...
Shengcheng Liu, Changming Zhu, Zishi Li, Zhiyuan Yang, Wenjie Gu   +4 more
doaj   +1 more source

Self-correction of 3D reconstruction from multi-view stereo images [PDF]

, 2009
We present a self-correction approach to improving the 3D reconstruction of a multi-view 3D photogrammetry system. The self-correction approach has been able to repair the reconstructed 3D surface damaged by depth discontinuities.
Ju, X, Siebert, JP, Ashraf F Ayoub, Khambay, B.S., Siebert, J.P., Xiangyang Ju, Ayoub, A.F., Khambay, BS, Balvinder S Khambay, Ju, X., Ayoub, AF, J Paul Siebert   +11 more
core   +1 more source

Incremental Data Stream Classification with Adaptive Multi-Task Multi-View Learning

Big Data Mining and Analytics
With the enhancement of data collection capabilities, massive streaming data have been accumulated in numerous application scenarios. Specifically, the issue of classifying data streams based on mobile sensors can be formalized as a multi-task multi-view
Jun Wang, Maiwang Shi, Xiao Zhang, Yan Li, Yunsheng Yuan, Chenglei Yang, Dongxiao Yu   +6 more
doaj   +1 more source

Multi-View Graph Clustering by Adaptive Manifold Learning

Mathematics, 2022
Graph-oriented methods have been widely adopted in multi-view clustering because of their efficiency in learning heterogeneous relationships and complex structures hidden in data.
Peng Zhao, Hongjie Wu, Shudong Huang
doaj   +1 more source

Consensus Graph Learning for Multi-Task Multi-View Clustering [PDF]

Jisuanji gongcheng
Multi-view clustering focuses on mining consistency information between different views to improve performance. Most existing multi-view clustering algorithms focus on single-task multi-view clustering while ignoring the similarity of related tasks ...
WANG Lijuan, LI Xueyan, YIN Ming, HAO Zhifeng, CAI Ruichu, CHEN Wei, LIU Rui
doaj   +1 more source

Robust Auto-weighted Multi-view Subspace Clustering

Jisuanji kexue yu tansuo, 2021
As the ability to collect and store data improving, real data are usually made up of different forms (view). Therefore, multi-view learning plays a more and more important role in the field of machine learning and pattern recognition.
FAN Ruidong, HOU Chenping
doaj   +1 more source