Article
Operations Research & Management Science
Bin Gao, P-A Absil
Summary: In this paper, a Riemannian rank-adaptive method is proposed to address the low-rank matrix completion problem on a set of bounded-rank matrices. Numerical experiments demonstrate its superior performance compared to state-of-the-art algorithms, and show that each aspect of this rank-adaptive framework can be separately incorporated into existing algorithms for performance improvement.
COMPUTATIONAL OPTIMIZATION AND APPLICATIONS
(2022)
Article
Computer Science, Interdisciplinary Applications
Xinlin Zhang, Hengfa Lu, Di Guo, Zongying Lai, Huihui Ye, Xi Peng, Bo Zhao, Xiaobo Qu
Summary: Magnetic resonance imaging is an essential tool for clinical diagnosis, but it suffers from long acquisition time. Sparse sampling can save time, but faithful reconstruction from undersampled data is needed. Among the existing reconstruction methods, structured low-rank methods have advantages in robustness and lower error. However, they consume considerable time and memory. To reduce the size of the Hankel matrix, we proposed a method to construct multiple small Hankel matrices from rows and columns of the k-space, leading to reduced computational time. However, this approach ignores correlation and may result in increased reconstruction error. To improve the reconstruction without increasing computation, we introduced self-consistency of k-space and virtual coil prior. The proposed method achieves the lowest reconstruction error with fast computation.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Engineering, Electrical & Electronic
Chengkan Lv, Fei Shen, Zhengtao Zhang, De Xu, Yonghao He
Summary: An anomaly detection method based on background reconstruction is proposed for defect inspection on the texture surface of industrial products. The method consists of two modules: background reconstruction and pixel-wise analysis, and experimental results demonstrate its effectiveness and versatility.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Physics, Multidisciplinary
Abdullateef O. Balogun, Shuib Basri, Luiz Fernando Capretz, Saipunidzam Mahamad, Abdullahi A. Imam, Malek A. Almomani, Victor E. Adeyemo, Ganesh Kumar
Summary: The study introduced a novel adaptive rank aggregation-based ensemble multi-filter feature selection (AREMFFS) method to address the high dimensionality and filter rank selection problems in software defect prediction. Experimental results demonstrated the superiority of AREMFFS over other baseline FFS methods and existing multi-filter FS methods, suggesting the combination of multiple FFS methods to enhance prediction performances of SDP models.
Article
Engineering, Electrical & Electronic
Farnaz Sedighin, Andrzej Cichocki, Anh-Huy Phan
Summary: The paper introduces a new rank selection method for TR decomposition, which gradually increases TR rank sizes in each iteration and selects core tensors based on their sensitivity to approximation errors, leading to a significant reduction in storage costs while maintaining the desired approximation accuracy.
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING
(2021)
Article
Engineering, Electrical & Electronic
Yuanke Zhang, Dong Zeng, Zhaoying Bian, Hongbing Lu, Jianhua Ma
Summary: This study proposed a novel weighted tensor low-rank and learnable analysis sparse representation model to enhance CT image reconstruction performance, by introducing a series of innovative algorithms and demonstrating the effectiveness of the proposed algorithm through extensive experiments.
IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING
(2021)
Article
Automation & Control Systems
Dongmei Mo, Wai Keung Wong, Zhihui Lai, Jie Zhou
Summary: This article proposes a weighted double-low-rank decomposition method to treat matrix singular values differently and preserve the most important characteristics of a fabric image for defect detection. This method is more robust and outperforms existing low-rank-based methods in locating defective regions on fabric images.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2021)
Article
Computer Science, Information Systems
Guangxu Li, Zhouzhou Zheng, Yuyi Shao, Jinyue Shen, Yan Zhang
Summary: In this work, an automated tire visual inspection system based on low rank matrix recovery is proposed. Deep Network is employed for texture segmentation, improving both quality and efficiency. A dual optimization method is proposed to improve convergence speed and matrix sparsity, with successful experimental results validating its effectiveness.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Lizhi Wang, Shipeng Zhang, Hua Huang
Summary: In this paper, a high-order tensor optimization based reconstruction method is proposed to boost the quality of computational hyperspectral imaging (CHI) by utilizing an adaptive dimension-discriminative low-rank tensor recovery (ADLTR) model. By integrating the structure prior in ADLTR with the system imaging principle, and solving it via the alternating minimization scheme, the proposed method outperforms state-of-the-art methods in both synthetic and real data experiments.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Article
Computer Science, Artificial Intelligence
Xiuhong Chen, Tong Chen
Summary: This article proposes a flexible sparse robust low-rank approximation of matrices model, which integrates feature selection into subspace learning and excludes redundant features. The method introduces two recovery matrices to recover the original image data from the selected features' subspace, allowing for more freedom and flexibility in selecting useful features for low-dimensional representation.
Article
Engineering, Electrical & Electronic
Yurong Sun, Yuyan Zhang, Yintang Wen
Summary: This paper proposes an imaging methodology using the fractional Tikhonov framework and automatic parameter selection to improve the stability and accuracy of planar array capacitance sensor imaging. The proposed method replaces the ill-posed inverse problem with a penalty least squares problem and utilizes the fractional power of the Moore-Penrose pseudoinverse as the weighting matrix to reduce the residual error in regularization.
IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING
(2022)
Article
Geochemistry & Geophysics
Yongchao Zhang, Jiawei Luo, Yongwei Zhang, Yulin Huang, Xiaochun Cai, Jianyu Yang, Deqing Mao, Jie Li, Xingyu Tuo, Yin Zhang
Summary: This article introduces a low-complexity super-resolution technique based on adaptive low-rank approximation, which aims to enhance the angular resolution of real beam mapping imagery. By constructing a random matrix sketch to sample the raw echo measurements and restore the surface reflectivity map in a low-dimensional linear space, the proposed strategy significantly reduces computational complexity. The Fourier transform-based antenna analysis method is used to determine the optimal low-rank approximation parameter, achieving a balance between error and computational efficiency.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Artificial Intelligence
Bo Liu, Yong Liu, Huiyan Zhang, Yonghui Xu, Can Tang, Lianggui Tang, Huafeng Qin, Chunyan Miao
Summary: Adaptive Power Iteration Clustering (AdaPIC) is a novel clustering method proposed to accelerate the computation of eigenvectors in spectral clustering tasks. By approximating the normalized similarity matrix using a sequence of rank-one matrices, AdaPIC is able to compute the first K+1 eigenvectors in parallel and automatically determine the stopping condition based on target clustering error. Experimental results show that AdaPIC outperforms classic PIC in running time and achieves superior clustering accuracy.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Operations Research & Management Science
Pan Shang, Lingchen Kong
Summary: In this paper, a novel rule for choosing the regularization parameter for nuclear norm regularized minimization (NRM) is developed using duality theory. The rule offers a safe set for the regularization parameter with an upper bound on the rank of the solution, and simple formulae are established for the regularization parameters. Numerical results show that the rule can reduce computation time for parameter selection in low rank matrix recovery.
JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Baoyuan Deng, Xiang Li, Hongjin Wang, Yunze He, Francesco Ciampa, Yiwen Li, Ke Zhou
Summary: The study proposes a non-orthogonal reconstructed space for line scanning thermography, achieving reconstruction of the excitation motion during line scanning process using time delay function. Experimental validation shows effective estimation of velocity and control of temporal alignment error.
IEEE SENSORS JOURNAL
(2021)
Article
Computer Science, Artificial Intelligence
Rui Lv, Dingheng Wang, Jiangbin Zheng, Zhao-Xu Yang
Summary: In this paper, the authors investigate tensor decomposition for neural network compression. They analyze the convergence and precision of tensor mapping theory, validate the rationality of tensor mapping and its superiority over traditional tensor approximation based on the Lottery Ticket Hypothesis. They propose an efficient method called 3D-KCPNet to compress 3D convolutional neural networks using the Kronecker canonical polyadic (KCP) tensor decomposition. Experimental results show that 3D-KCPNet achieves higher accuracy compared to the original baseline model and the corresponding tensor approximation model.
Article
Computer Science, Artificial Intelligence
Xiangkun He, Zhongxu Hu, Haohan Yang, Chen Lv
Summary: In this paper, a novel constrained multi-objective reinforcement learning algorithm is proposed for personalized end-to-end robotic control with continuous actions. The approach trains a single model using constraint design and a comprehensive index to achieve optimal policies based on user-specified preferences.
Article
Computer Science, Artificial Intelligence
Zhijian Zhuo, Bilian Chen, Shenbao Yu, Langcai Cao
Summary: In this paper, a novel method called Expansion with Contraction Method for Overlapping Community Detection (ECOCD) is proposed, which utilizes non-negative matrix factorization to obtain disjoint communities and applies expansion and contraction processes to adjust the degree of overlap. ECOCD is applicable to various networks with different properties and achieves high-quality overlapping community detection.
Article
Computer Science, Artificial Intelligence
Yizhe Zhu, Chunhui Zhang, Jialin Gao, Xin Sun, Zihan Rui, Xi Zhou
Summary: In this work, the authors propose a Contrastive Spatio-Temporal Distilling (CSTD) approach to improve the detection of high-compressed deepfake videos. The approach leverages spatial-frequency cues and temporal-contrastive alignment to fully exploit spatiotemporal inconsistency information.
Review
Computer Science, Artificial Intelligence
Laijin Meng, Xinghao Jiang, Tanfeng Sun
Summary: This paper provides a review of coverless steganographic algorithms, including the development process, known contributions, and general issues in image and video algorithms. It also discusses the security of coverless steganography from theoretical analysis to actual investigation for the first time.
Article
Computer Science, Artificial Intelligence
Yajie Bao, Tianwei Xing, Xun Chen
Summary: Visual question answering requires processing multi-modal information and effective reasoning. Neural-symbolic learning is a promising method, but current approaches lack uncertainty handling and can only provide a single answer. To address this, we propose a confidence based neural-symbolic approach that evaluates NN inferences and conducts reasoning based on confidence.
Article
Computer Science, Artificial Intelligence
Anh H. Vo, Bao T. Nguyen
Summary: Interior style classification is an interesting problem with potential applications in both commercial and academic domains. This project proposes a method named ISC-DeIT, which combines data-efficient image transformer architectures and knowledge distillation, to address the interior style classification problem. Experimental results demonstrate a significant improvement in predictive accuracy compared to other state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Shashank Kotyan, Danilo Vasconcellos Vargas
Summary: This article introduces a novel augmentation technique called Dynamic Scanning Augmentation to improve the accuracy and robustness of Vision Transformer (ViT). The technique leverages dynamic input sequences to adaptively focus on different patches, resulting in significant changes in ViT's attention mechanism. Experimental results demonstrate that Dynamic Scanning Augmentation outperforms ViT in terms of both robustness to adversarial attacks and accuracy against natural images.
Article
Computer Science, Artificial Intelligence
Hiba Alqasir, Damien Muselet, Christophe Ducottet
Summary: The article proposes a solution to improve the learning process of a classification network by providing shape priors, reducing the need for annotated data. The solution is tested on cross-domain digit classification tasks and a video surveillance application.
Article
Computer Science, Artificial Intelligence
Dexiu Ma, Mei Liu, Mingsheng Shang
Summary: This paper proposes a method using neural dynamics solvers to solve infinity-norm optimization problems. Two improved solvers are constructed and their effectiveness and superiority are demonstrated through theoretical analysis and simulation experiments.
Article
Computer Science, Artificial Intelligence
Francesco Gregoretti, Giovanni Pezzulo, Domenico Maisto
Summary: Active Inference is a computational framework that uses probabilistic inference and variational free energy minimization to describe perception, planning, and action. cpp-AIF is a header-only C++ library that provides a powerful tool for implementing Active Inference for Partially Observable Markov Decision Processes through multi-core computing. It is cross-platform and improves performance, memory management, and usability compared to existing software.
Article
Computer Science, Artificial Intelligence
Zelin Ying, Dawei Cheng, Cen Chen, Xiang Li, Peng Zhu, Yifeng Luo, Yuqi Liang
Summary: This paper proposes a novel stock market trends prediction framework called SMART, which includes a self-supervised stock technical data sequence embedding model S3E. By training with multiple self-supervised auxiliary tasks, the model encodes stock technical data sequences into embeddings and uses the learned sequence embeddings for predicting stock market trends. Extensive experiments on China A-Shares market and NASDAQ market prove the high effectiveness of our model in stock market trends prediction, and its effectiveness is further validated in real-world applications in a leading financial service provider in China.
Article
Computer Science, Artificial Intelligence
Hao Li, Hao Jiang, Dongsheng Ye, Qiang Wang, Liang Du, Yuanyuan Zeng, Liu Yuan, Yingxue Wang, C. Chen
Summary: DHGAT1, a dynamic hyperbolic graph attention network, utilizes hyperbolic metric properties to embed dynamic graphs. It employs a spatiotemporal self-attention mechanism and weighted node representations, resulting in excellent performance in link prediction tasks.
Article
Computer Science, Artificial Intelligence
Jiehui Huang, Zhenchao Tang, Xuedong He, Jun Zhou, Defeng Zhou, Calvin Yu-Chian Chen
Summary: This study proposes a progressive learning multi-scale feature blending model for image deraining tasks. The model utilizes detail dilation and texture extraction to improve the restoration of rainy images. Experimental results show that the model achieves near state-of-the-art performance in rain removal tasks and exhibits better rain removal realism.
Article
Computer Science, Artificial Intelligence
Lizhi Liu, Zilin Gao, Yinhe Wang, Yongfu Li
Summary: This paper proposes a novel discrete-time interconnected model for depicting complex dynamical networks. The model consists of nodes and edges subsystems, which consider the dynamic characteristic of both nodes and edges. By designing control strategies and coupling modes, the stabilization and synchronization of the network are achieved. Simulation results demonstrate the effectiveness of the proposed methods.