Filters








2,682 Hits in 6.7 sec

Collaborative Multi-View Denoising

Lei Zhang, Shupeng Wang, Xiaoyu Zhang, Yong Wang, Binbin Li, Dinggang Shen, Shuiwang Ji
2016 Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16  
i.e., the intra-and inter-view noises.  ...  Furthermore, to remove the intra-and inter-view noises, we present a new Multi-view Semi-supervised Collaborative Denoising (MSCD) method with elementary transformation constraints and gradient energy  ...  As shown in Fig.5 , MSCD model eliminates the intra-and inter-view noises by means of semi-supervised learning.  ... 
doi:10.1145/2939672.2939811 dblp:conf/kdd/ZhangWZWLSJ16 fatcat:rrldrohh2nbt7jzguugznpm4ay

Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry and Fusion [article]

Yang Wang
2020 arXiv   pre-print
With the development of web technology, multi-modal or multi-view data has surged as a major stream for big data, where each modal/view encodes individual property of data objects.  ...  Throughout this survey, we further indicate that the critical components for this field go to collaboration, adversarial competition and fusion over multi-modal spaces.  ...  [21] proposed structured generative adversarial networks (SGANs) for semi-supervised image classification.  ... 
arXiv:2006.08159v1 fatcat:g4467zmutndglmy35n3eyfwxku

Multi-view Classification via Adaptive Discriminant Analysis

Deyan Xie, Qin Li, Wei Xia, Shiwei Pang, Huihui He, Quanxue Gao
2019 IEEE Access  
Therefore, it is highly desirable to recognize the object from distinct and even heterogeneous views.  ...  In this paper, we propose a novel method, the named multi-view locality adaptively discriminant analysis (MvLADA), for multi-view classification.  ...  ACKNOWLEDGMENT The authors would like to thank the anonymous reviewers and AE for their constructive comments and suggestions. VOLUME 7, 2019  ... 
doi:10.1109/access.2019.2905008 fatcat:u6zpgxrx4nbnhf43keinbv5r3u

Multi-View Representation Learning via Dual Optimal Transportation

Peng Li, Jing Gao, Bin Zhai, Jianing Zhang, Zhikui Chen
2021 IEEE Access  
In MDOT-Net, the multi-view representation learning is modelled as an optimal transportation (OT) problem in manifold fitting, which is further decomposed into the intra-view OT and the inter-view OT.  ...  The inter-view OT is implemented by a view-fusion adversarial inference network, which models fusion representations compatible with diversities of sub-manifolds by utilizing view-specific knowledge.  ...  In this paper, MDOT-Net is designed based on the optimal transportation to learn multi-view fusion representations that can well merge the heterogeneous topologies of each view based on a weak-structure  ... 
doi:10.1109/access.2021.3123078 fatcat:7p2yhb2tgrbfxodhqnt4q7tnye

Face video retrieval with image query via hashing across Euclidean space and Riemannian manifold

Yan Li, Ruiping Wang, Zhiwu Huang, Shiguang Shan, Xilin Chen
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
, and then iteratively optimize the intra-and inter-space Hamming distances in a maxmargin framework to learn the hash functions for the two spaces.  ...  It thus incurs a new hashing-based retrieval problem of matching two heterogeneous representations, respectively in Euclidean space and Riemannian manifold.  ...  Acknowledgements This work is partially supported by 973 Program under contract No. 2015CB351802, Natural Science Foundation of China under contracts Nos. 61390511, 61222211, 61379083, and the FiDiPro  ... 
doi:10.1109/cvpr.2015.7299108 dblp:conf/cvpr/LiWHSC15 fatcat:dmqi7lgqzvdz7pzcaxfcgtirti

Cross-Domain Kernel Induction for Transfer Learning

Wei-Cheng Chang, Yuexin Wu, Hanxiao Liu, Yiming Yang
2017 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
label propagation in cross-domain settings, and to optimize semi-supervised learning based on labeled and unlabeled data in both source and target domains.  ...  Common methods so far require source and target domains to have a shared/homogeneous feature space, or the projection of features from heterogeneous domains onto a shared space.  ...  We thank the reviewers for their helpful comments. This work is supported in part by the National Science Foundation (NSF) under grant IIS-1546329.  ... 
doi:10.1609/aaai.v31i1.10901 fatcat:tuhy7vmyfvhs5ohk7jmfjz3pjm

Cross-modal Zero-shot Hashing [article]

Xuanwu Liu, Zhao Li, Jun Wang, Guoxian Yu, Carlotta Domeniconi, Xiangliang Zhang
2019 arXiv   pre-print
It then defines an objective function to achieve deep feature learning compatible with the composite similarity preserving, category attribute space learning, and hashing coding function learning.  ...  Hashing has been widely studied for big data retrieval due to its low storage cost and fast query speed.  ...  'UN', 'SU' AND 'SE' ARE SHORT FOR 'UNSUPERVISED', 'SUPERVISED' AND 'SEMI-SUPERVISED' CMH, RESPECTIVELY.  ... 
arXiv:1908.07388v1 fatcat:uaj7z5dnfrgvvmy7llwjfkuwo4

Character index

2011 2011 IEEE International Conference on Multimedia and Expo  
SIMILAR IMAGE SETS USING LOW FREQUENCY TEMPLATE TOWARDS ROBUST AND EFFICIENT SEGMENTATION: AN APPROACH BASED ON INTER-REGION CONTOUR AND INTRA-REGION CONTENT ANALYSIS DATA HIDING IN DOT DIFFUSED HALFTONE  ...  TO DETECT SALIENT REGION OF IMAGE UNDER WEAK SUPERVISION Jiwen Lu LOCALITY REPULSION PROJECTIONS FOR IMAGE-TO-SET FACE RECOGNITION ADAPTIVE MAXIMUM MARGIN CRITERION FOR IMAGE CLASSIFICATION SET-TO-SET  ... 
doi:10.1109/icme.2011.6011827 fatcat:wjy7yvkmvbbf3hj4wbyjapx5gu

Joint Intermodal and Intramodal Label Transfers for Extremely Rare or Unseen Classes [article]

Guo-Jun Qi, Wei Liu, Charu Aggarwal, Thomas Huang
2017 arXiv   pre-print
On one hand, labeled text data is more widely available than the labeled images for classification tasks.  ...  In this paper, we present a label transfer model from texts to images for image classification tasks. The problem of image classification is often much more challenging than text classification.  ...  We also would like to thank the anonymous reviewers for bringing the zero-shot learning problem into our attention, which inspires us to study the applicability of the proposed approach to this problem  ... 
arXiv:1703.07519v1 fatcat:5dpyi4stczf33okgvf3fne22t4

Multi-view learning overview: Recent progress and new challenges

Jing Zhao, Xijiong Xie, Xin Xu, Shiliang Sun
2017 Information Fusion  
The main feature of this survey is that we provide comprehensive introduction for the recent developments of multi-view learning methods on the basis of coherence with early methods.  ...  Since the last survey of multi-view machine learning in early 2013, multi-view learning has made great progress and developments in recent years, and is facing new challenges.  ...  They made generalization error analysis for both supervised and semi-supervised multi-view learning methods.  ... 
doi:10.1016/j.inffus.2017.02.007 fatcat:6we7lm2buncftg7xzym63ncxmy

A Survey of Different Machine Learning Models for Alzheimer Disease Prediction

Ragavamsi Davuluri
2020 International Journal of Emerging Trends in Engineering Research  
Machine learning model is one of the best disease prediction framework in various medical disease prediction processes.  ...  Several high dimensional classification and clustering methods have recently been proposed to predict the AD automatically.  ...  TRADITIONAL SUPERVISED MACHINE LEARNING MODELS Supervised learning involves training the model for the labelled data and makes predictions on the new data using this trained model.  ... 
doi:10.30534/ijeter/2020/73872020 fatcat:6z5ke75e4zfenbthmmj3all32e

Semi-Supervised Deep Learning for Multiplex Networks [article]

Anasua Mitra, Priyesh Vijayan, Ranbir Sanasam, Diganta Goswami, Srinivasan Parthasarathy, Balaraman Ravindran
2021 arXiv   pre-print
In this work, we present a novel semi-supervised approach for structure-aware representation learning on multiplex networks.  ...  Empirically, we demonstrate that the proposed architecture outperforms state-of-the-art methods in a range of tasks: classification, clustering, visualization, and similarity search on seven real-world  ...  Node Classification For semi-supervised methods, we use the predicted labels directly to compute the node classification scores based on ground-truth.  ... 
arXiv:2110.02038v1 fatcat:koof45ms6fbrpaz6izecoswroi

A Survey on Multi-view Learning [article]

Chang Xu, Dacheng Tao, Chao Xu
2013 arXiv   pre-print
Since accessing multiple views is the fundament of multi-view learning, with the exception of study on learning a model from multiple views, it is also valuable to study how to construct multiple views  ...  In trying to organize and highlight similarities and differences between the variety of multi-view learning approaches, we review a number of representative multi-view learning algorithms in different  ...  Co-regression Most studies on multi-view and semi-supervised learning focus on classification problems, and regression problems can also be solved in a similar way.  ... 
arXiv:1304.5634v1 fatcat:nnux76pyobdzhovzlcywxrzkty

A Comparative Study of Radiomics and Deep-Learning Based Methods for Pulmonary Nodule Malignancy Prediction in Low Dose CT Images

Mehdi Astaraki, Guang Yang, Yousuf Zakko, Iuliana Toma-Dasu, Örjan Smedby, Chunliang Wang
2021 Frontiers in Oncology  
ObjectivesBoth radiomics and deep learning methods have shown great promise in predicting lesion malignancy in various image-based oncology studies.  ...  In this study, we try to compare the performance of a series of carefully selected conventional radiomics methods, end-to-end deep learning models, and deep-feature based radiomics pipelines for pulmonary  ...  (35) developed a semi-supervised adversarial classification model that consists of an unsupervised adversarial autoencoder network, a supervised classification network, and learnable transition layers  ... 
doi:10.3389/fonc.2021.737368 pmid:34976794 pmcid:PMC8718670 fatcat:owwqvpi26zf4jp5yzm4pvilcsu

A Review of Hashing Methods for Multimodal Retrieval

Wenming Cao, Wenshuo Feng, Qiubin Lin, Guitao Cao, Zhihai He
2020 IEEE Access  
For more information, see http://creativecommons.org/licenses/by/4.0/  ...  This review clarifies the definition of multimodal retrieval requirements and some related concepts, then introduces some representative hashing methods, mainly supervised methods that make full use of  ...  In addition, Linear Discriminant Analysis Hashing (LDAhash) [28] and Supervised Discrete Hashing (SDH) [29] are also based on similar ideas which convert the hash learning problem into a linear classification  ... 
doi:10.1109/access.2020.2968154 fatcat:e3vmte5hrnhu3b3lf5ws4gwnhm
« Previous Showing results 1 — 15 out of 2,682 results