2,277 Hits in 5.2 sec

Online Robust Low-Rank Tensor Learning

Ping Li, Jiashi Feng, Xiaojie Jin, Luming Zhang, Xianghua Xu, Shuicheng Yan
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
In this paper, we propose an Online Robust Low-rank Tensor Modeling (ORLTM) approach to address these challenges.  ...  ORLTM dynamically explores the high-order correlations across all tensor modes for low-rank structure modeling.  ...  In this work, we propose an Online Robust Low-rank Tensor Modeling (ORLTM) method for learning low-rank structures of tensors from streaming noisy tensor data.  ... 
doi:10.24963/ijcai.2017/303 dblp:conf/ijcai/LiFJZXY17 fatcat:25d5umlpuzeqxhjpofkst6piiu

Variational Bayesian Inference for Robust Streaming Tensor Factorization and Completion [article]

Cole Hawkins, Zheng Zhang
2018 arXiv   pre-print
This paper presents a Bayesian robust streaming tensor factorization model to identify sparse outliers, automatically determine the underlying tensor rank and accurately fit low-rank structure.  ...  Streaming tensor factorization is a powerful tool for processing high-volume and multi-way temporal data in Internet networks, recommender systems and image/video data analysis.  ...  ACKNOWLEDGEMENTS We thank the anonymous referees for their helpful comments. A special thanks to Chunfeng Cui for many suggestions to improve this manuscript.  ... 
arXiv:1809.02153v2 fatcat:skzisc7dejevrbrwut33p6trdu

Robust Factorization and Completion of Streaming Tensor Data via Variational Bayesian Inference [article]

Cole Hawkins, Zheng Zhang
2018 arXiv   pre-print
This paper presents the first Bayesian robust streaming tensor factorization model.  ...  Streaming tensor factorization is a powerful tool for processing high-volume and multi-way temporal data in Internet networks, recommender systems and image/video data analysis.  ...  BAYESIAN MODEL FOR ROBUST STREAMING TENSOR FACTORIZATION & COMPLETION In this section, we present a Bayesian method for the robust factorization and completion of streaming tensors {X t }. A.  ... 
arXiv:1809.01265v1 fatcat:layfw6phkzhbppw6gllet5hdgu

Online Stochastic Tensor Decomposition for Background Subtraction in Multispectral Video Sequences

Andrews Sobral, Sajid Javed, Soon Ki Jung, Thierry Bouwmans, El-hadi Zahzah
2015 2015 IEEE International Conference on Computer Vision Workshop (ICCVW)  
In order to address these major difficulties of multispectral imaging for video surveillance, this paper propose an online stochastic framework for tensor decomposition of multispectral video sequences  ...  First, the experimental evaluations on synthetic generated data show the robustness of the OSTD with other state of the art approaches then, we apply the same idea on seven multispectral video bands to  ...  The authors gratefully acknowledge the financial support of CAPES (Brazil) for granting a PhD scholarship to the first author.  ... 
doi:10.1109/iccvw.2015.125 dblp:conf/iccvw/SobralJJBZ15 fatcat:htzy5ep4lrdjhp2kixrsspnr6e

Incremental and Multi-feature Tensor Subspace Learning Applied for Background Modeling and Subtraction [chapter]

Andrews Sobral, Christopher G. Baker, Thierry Bouwmans, El-hadi Zahzah
2014 Lecture Notes in Computer Science  
In addition, the multi-feature model allows us to build a robust low-rank background model of the scene.  ...  In this work, we propose an incremental tensor subspace learning that uses only a small part of the entire data and updates the low-rank model incrementally when new data arrive.  ...  Acknowledgments The authors gratefully acknowledge the financial support of CAPES (Brazil) through Brazilian Science Without Borders program (CsF) for granting a scholarship to the first author.  ... 
doi:10.1007/978-3-319-11758-4_11 fatcat:wcpzmau22ne5no4rusot7t6cay

Stochastic Decomposition into Low Rank and Sparse Tensor for Robust Background Subtraction

S. Javed, T. Bouwmans, Soon Ki Jung
2015 6th International Conference on Imaging for Crime Prevention and Detection (ICDP-15)  
Higher-Order Robust Principal Component Analysis (HORPCA) based robust tensor recovery or decomposition provides a very nice potential for BS.  ...  In order to tackle these challenges, we apply the idea of stochastic optimization on tensor for robust low-rank and sparse error separation.  ...  In order to address these major difficulties for BG/FG segmentation. This paper presents a robust recovery of low-rank tensor model for accurate FG segmentation.  ... 
doi:10.1049/ic.2015.0105 dblp:conf/icdp/JavedBJ15 fatcat:ibxvu5hibvbpraaylnbp52ganq

Robust Visual Tracking Based on Incremental Tensor Subspace Learning

Xi Li, Weiming Hu, Zhongfei Zhang, Xiaoqin Zhang, Guan Luo
2007 2007 IEEE 11th International Conference on Computer Vision  
In this paper, we present an effective online tensor subspace learning algorithm which models the appearance changes of a target by incrementally learning a low-order tensor eigenspace representation through  ...  Most existing subspace analysis-based tracking algorithms utilize a flattened vector to represent a target, resulting in a high dimensional data learning problem.  ...  In the first stage, a low dimensional tensor eigenspace model is learned online.  ... 
doi:10.1109/iccv.2007.4408950 dblp:conf/iccv/LiHZZL07 fatcat:gjuwv5hljjhddmx2zkzpqnqnum

Introduction to the Issue on Robust Subspace Learning and Tracking: Theory, Algorithms, and Applications

T. Bouwmans, N. Vaswani, P. Rodriguez, R. Vidal, Z. Lin
2018 IEEE Journal on Selected Topics in Signal Processing  
By using a new tensor nuclear norm that extends the conventional TNN, Liu et al. better extract the low-rank tensor components in multi-way data by investigating the low-rank structure for core tensor  ...  He has co-authored a book entitled Low-Rank Models in Visual Analysis: Theories, Algorithms, and Applications in 2017.  ... 
doi:10.1109/jstsp.2018.2879245 fatcat:z3ohqdl37nat3pjo65fzsf2ady

Streaming data preprocessing via online tensor recovery for large environmental sensor networks [article]

Yue Hu, Ao Qu, Yanbing Wang, Dan Work
2021 arXiv   pre-print
To address these challenges, we propose an online robust tensor recovery (OLRTR) method to preprocess streaming high-dimensional urban environmental datasets.  ...  and batch-based low rank decomposition methods.  ...  [34] develops an online robust low-rank tensor modeling (ORLTM) method that can deal with streaming tensor data drawn from a mixture of multiple subspaces effectively through dictionary learning.  ... 
arXiv:2109.00596v1 fatcat:2p2dnsjbqnfpvfpzq73r5wq3om

Urban Traffic State Estimation with Online Car-Hailing Data: A Dynamic Tensor-Based Bayesian Probabilistic Decomposition Approach

Wenqi Lu, Ziwei Yi, Dongyu Luo, Yikang Rui, Bin Ran, Jianqing Wu, Tao Li
2022 Journal of Advanced Transportation  
Finally, the real-world traffic speeds data extracted from online car-hailing trajectories are employed to validate the model performance.  ...  Firstly, the real-time traffic speed data are organized in the form of a dynamic tensor which contains the spatiotemporal characteristics of the traffic state.  ...  supported by the National Natural Science Foundation of China (Grant no. 41971342), the Key Research and Development Program of Shandong Province (Grant no. 2020CXGC010118), the Fundamental Research Funds for  ... 
doi:10.1155/2022/1793060 doaj:bbf3dce58ddb4428bad219401597be8c fatcat:3u2ruynlifbxxe3ngchek6ansa

Online Rank-Revealing Block-Term Tensor Decomposition [article]

Athanasios A. Rontogiannis, Eleftherios Kofidis, Paris V. Giampouras
2021 arXiv   pre-print
In data-streaming scenarios and/or big data applications, where the tensor dimension in one of its modes grows in time or can only be processed incrementally, it is essential to be able to perform model  ...  The so-called block-term decomposition (BTD) tensor model, especially in its rank-(L_r,L_r,1) version, has been recently receiving increasing attention due to its enhanced ability of representing systems  ...  [44] relies on the well-known in robust principal component analysis (PCA) [12] , [45] low rank plus sparse representation model to come up with an online CPD scheme for (ADMM-based) outlier-resistant  ... 
arXiv:2106.10755v2 fatcat:yhnihktv2jddjly2sc3wq3xdle

Subspace Learning and Imputation for Streaming Big Data Matrices and Tensors

Morteza Mardani, Gonzalo Mateos, Georgios B. Giannakis
2015 IEEE Transactions on Signal Processing  
Under the same unifying framework, a novel online (adaptive) algorithm is developed to obtain multi-way decompositions of low-rank tensors with missing entries, and perform imputation as a byproduct.  ...  For low-rank matrix data, a subspace estimator is proposed based on an exponentially-weighted least-squares criterion regularized with the nuclear norm.  ...  The algorithm in the following section offers a novel approach for decomposing and imputing low-rank streaming tensors with missing data. B.  ... 
doi:10.1109/tsp.2015.2417491 fatcat:4upze7gda5dubngompfntmmc6y

Robust foreground segmentation based on two effective background models

Xi Li, Weiming Hu, Zhongfei Zhang, Xiaoqin Zhang
2008 Proceeding of the 1st ACM international conference on Multimedia information retrieval - MIR '08  
These two IRTSA-based background models (i.e., IRTSA-GBM and IRTSA-CBM respectively for grayscale and color images) incrementally learn low-order tensor-based eigenspace representations to fully capture  ...  In order to address this problem, we propose two block-based background models using the recently developed incremental rank-(R1, R2, R3) tensor-based subspace learning algorithm (referred to as IRTSA)  ...  In the first stage, a low dimensional tensor-based eigenspace background model is online learned by IRTSA as new data arrive.  ... 
doi:10.1145/1460096.1460133 dblp:conf/mir/LiHZZ08 fatcat:qjdnaa6mira4nbry5lj4xdirti

Identifying and Alleviating Concept Drift in Streaming Tensor Decomposition [article]

Ravdeep Pasricha, Ekta Gujral, Evangelos E. Papalexakis
2018 arXiv   pre-print
Many real-world applications are dynamic in nature and so are their data. To deal with this dynamic nature of data, there exist a variety of online tensor decomposition algorithms.  ...  Furthermore, we introduce SeekAndDestroy, an algorithm that detects concept drift in streaming tensor decomposition and is able to produce results robust to that drift.  ...  N00174-17-1-0005, the National Science Foundation EAGER Grant no. 1746031, and by an Adobe Data Science Research Faculty Award.  ... 
arXiv:1804.09619v2 fatcat:tc2xtfb5dfe53od53bjz6xtiey

Rethinking PCA for Modern Data Sets: Theory, Algorithms, and Applications [Scanning the Issue]

Namrata Vaswani, Yuejie Chi, Thierry Bouwmans
2018 Proceedings of the IEEE  
A common way to do this is via solving the principal component analysis (PCA) problem or its robust extensions.  ...  It is often the first step in various types of exploratory data analysis, predictive modeling, and classification and clustering tasks, and finds applications in biomedical imaging, computer vision, process  ...  The same is true for dynamic PCA (subspace tracking or streaming PCA), dynamic or recursive robust PCA (robust subspace tracking), PCA and subspace tracking with missing data, and the related low-rank  ... 
doi:10.1109/jproc.2018.2853498 fatcat:6d52ecsbgfcnxchfeiugxzoerm
« Previous Showing results 1 — 15 out of 2,277 results