Article
Automation & Control Systems
Wei Zhou, Yue Wu, Junlin Li, Maolin Wang, Hai-Tao Zhang
Summary: This paper proposes a joint dictionary and classifier learning algorithm that optimizes dictionaries and sparse codes using Gaussian priors to improve classification performance. The algorithm achieves group sparsity in sparse coding through Bayesian learning and Gaussian priors. Hyperparameters are optimized using an evidence maximization method without manual parameter tuning.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Jian-Sheng Wu, Meng-Xiao Song, Weidong Min, Jian-Huang Lai, Wei-Shi Zheng
Summary: The study introduces a novel unsupervised feature selection framework JAMEL, which aims to preserve the manifold structure among data by iteratively and adaptively learning lower-dimensional embeddings. The results show the effectiveness and efficiency of the approach in various tasks such as k-means, spectral clustering and nearest neighbor classification.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Artificial Intelligence
Xiaojin Fan, Mengmeng Liao, Jingfeng Xue, Hao Wu, Lei Jin, Jian Zhao, Liehuang Zhu
Summary: In this paper, a Joint Coupled Representation and Homogeneous Reconstruction (JCRHR) method is proposed for multi-resolution small sample face recognition. The method improves the coherent representation of coding coefficients and the reconstruction effect of samples at different resolutions by introducing an analysis dictionary, a synthetic dictionary, and a coherence enhancement term. Experimental results demonstrate that the proposed JCRHR method outperforms existing methods on several small sample face databases.
Article
Acoustics
Zhuopeng Xie, Huichao Yang, Zhongfu Ye
Summary: This paper proposes a method to incorporate group structure into joint sparse representations in the modulation domain to enhance signals. Experimental results show that this method performs better in terms of speech quality and can improve PESQ and segSNR scores.
Article
Computer Science, Artificial Intelligence
Jinyu Cai, Shiping Wang, Wenzhong Guo
Summary: The paper proposes a deep stacked sparse embedded clustering method that considers both local structure preservation and input sparsity. The deep learning approach jointly learns clustering-oriented features and optimizes cluster label assignments by minimizing both the reconstruction and clustering loss. Comprehensive experiments validate the effectiveness of introducing sparsity and preserving local structure in the proposed method.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Bo Liu, Xiaodong Chen, Yanshan Xiao, Weibin Li, Laiwang Liu, Changdong Liu
Summary: Multi-view learning explores information from different perspectives, with dictionary learning being advantageous for classification, but there is limited research on combining the two. The proposed MVDL-CV method enhances multi-view classification by learning specific dictionaries and utilizing regularization between them for improved discriminative representation.
INFORMATION SCIENCES
(2021)
Article
Geochemistry & Geophysics
Lianru Gao, Danfeng Hong, Jing Yao, Bing Zhang, Paolo Gamba, Jocelyn Chanussot
Summary: Extensive attention has been paid to enhancing the spatial resolution of hyperspectral images using multispectral images in remote sensing. This study introduces a novel approach to improve the spectral resolution of remote sensing imagery by super-resolving multispectral images in the spectral domain. The developed joint sparse and low-rank learning (J-SLoL) method effectively enhances multispectral images by learning low-rank HS-MS dictionary pairs from overlapped regions, showing superior performance compared to existing state-of-the-art baselines.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Engineering, Mechanical
Hao Wang, Guangming Dong, Jin Chen, Xugang Hu, Zhibing Zhu
Summary: Dictionary learning has shown excellent performances in various fields. However, in some applications, training data is often scarce, making it difficult to achieve good sparse representation on a single learned dictionary. In order to solve this problem, a novel approach called deep and shared dictionary learning (DSDL) is proposed.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Ting Liu, Hongzhong Tang, Dongbo Zhang, Shuying Zeng, Biao Luo, Zhaoyang Ai
Summary: In this paper, a feature-guided dictionary learning method is proposed for single image deraining, which combines external and internal dictionaries to produce more favorable visual effects and superior quality results.
APPLIED SOFT COMPUTING
(2021)
Article
Engineering, Electrical & Electronic
Wei Xu, Qing Zhu, Na Qi
Summary: This paper proposes a depth map super-resolution method using joint local gradient and nonlocal structural regularizations. By modeling the local patterns of the depth map and providing nonlocal constraints, the method effectively restores image details and suppresses noise.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Mengshi Huang, Hongmei Chen, Yong Mi, Chuan Luo, Shi-Jinn Horng, Tianrui Li
Summary: In this paper, a minimum-redundant unsupervised feature selection (UFS) approach, called SLRDR, is proposed to address the problems by combining sparse latent representation learning and dual manifold regularization. The proposed approach learns a subspace of latent representation and pseudo-label matrix in the high-quality latent space, and utilizes manifold learning and sparse regression to select more discriminative features. Experimental results on benchmark datasets demonstrate the effectiveness of the proposed approach.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Deyin Liu, Chengwu Liang, Shaokang Chen, Yun Tie, Lin Qi
Summary: The paper introduces a novel deep Auto-Encoder based Structured Dictionary (AESD) learning model that only requires learning one dictionary composed of class-specific sub-dictionaries, with supervision from discriminative category constraints. By optimizing the learning process based on the dictionary, a light-weight network training is achieved. Additionally, the proposed method is extended into a Convolutional Encoder based Block Sparse Representation (CEBSR) model in the testing phase to enhance image set based classification.
Article
Nuclear Science & Technology
Junhyeok Kim, Daehee Lee, Jinhwan Kim, Giyoon Kim, Jisung Hwang, Wonku Kim, Gyuseong Cho
Summary: This paper proposes a sparse representation with dictionary learning approach for identifying radioactive isotopes in plastic gamma-ray spectra. Monte Carlo simulation is used to generate learning samples, and experimental measurements are conducted to obtain practical spectra. The tested dictionaries show good accuracy for different source positions and measurement times, and acceptable performance when the spectra are artificially shifted.
NUCLEAR ENGINEERING AND TECHNOLOGY
(2022)
Article
Engineering, Mechanical
Jimeng Li, Jinxin Tao, Wanmeng Ding, Jinfeng Zhang, Zong Meng
Summary: This paper proposes a sparse representation method based on a period-assisted adaptive parameterized wavelet dictionary to accurately extract periodic transient features of rolling bearing faults from noise interference containing harmonics and large-amplitude random impulses. Experimental results demonstrate that the proposed method can more accurately extract periodic transient features in vibration signals, providing an effective analysis tool for rolling bearing fault detection.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Computer Science, Artificial Intelligence
Bao-Qing Yang, Xin-Ping Guan, Jun-Wu Zhu, Chao-Chen Gu, Kai-Jie Wu, Jia-Jie Xu
Summary: The paper presents a discriminative dictionary learning framework based on support vector machines and feedback mechanism to enhance image classification performance.
PATTERN RECOGNITION
(2021)
Editorial Material
Computer Science, Artificial Intelligence
Zhao Zhang, Meng Wang, Sheng Li, Zheng Zhang
Article
Computer Science, Information Systems
Rui Gao, Xingsong Hou, Jie Qin, Yuming Shen, Yang Long, Li Liu, Zhao Zhang, Ling Shao
Summary: Zero-shot learning aims to recognize unknown categories that are not available during training. Generative models have shown potential to address this problem by synthesizing unseen features based on semantic embeddings. We propose a visual-semantic aligned bidirectional network with cycle consistency to bridge the gap between visual and semantic spaces and generate high-quality unseen features. Two carefully designed strategies are incorporated to improve the overall ZSL performance by enhancing intra-domain class divergence and mitigating inter-domain shift.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Information Systems
Han Yan, Haijun Zhang, Linlin Liu, Dongliang Zhou, Xiaofei Xu, Zhao Zhang, Shuicheng Yan
Summary: The article introduces an AI-based framework for fashion design using generative adversarial networks to enhance designers' efficiency. The framework includes a sketch-generation module based on latent space and a rendering-generation module to learn the mapping between textures and sketches. Experimental results demonstrate the effectiveness of the proposed method in synthesizing semantic-aware textures on sketches.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Artificial Intelligence
Hongwei Yin, Guixiang Wang, Wenjun Hu, Zhao Zhang
Summary: Multi-view clustering is a hot research topic that leverages complementary information from multiple views to improve clustering performance. In this paper, a novel fine-grained multi-view clustering method is proposed. It divides the sample space of each view into sub-clusters using multi-prototypes representation, enhances the robustness of representation by reducing sub-cluster overlap, and assigns contribution weights based on clustering capacity. The method integrates robust multi-prototypes representation, fine-grained multi-view fusion, and clustering process into a unified framework, and achieves better clustering accuracy compared to traditional methods.
APPLIED INTELLIGENCE
(2023)
Article
Automation & Control Systems
Qiaolin Ye, Peng Huang, Zhao Zhang, Yuhui Zheng, Liyong Fu, Wankou Yang
Summary: This article presents a new multiview learning approach, MvRDTSVM, to improve classification performance and robustness by introducing double-sided constraints and using L1-norm as the distance metric. Experimental results confirm the effectiveness of the proposed methods.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Automation & Control Systems
Jie Wen, Zheng Zhang, Lunke Fei, Bob Zhang, Yong Xu, Zhao Zhang, Jinxing Li
Summary: Conventional multiview clustering methods fail when not all views of samples are available in practical applications. Incomplete multiview clustering (IMC) is developed to address this issue. Recent years have seen significant advances in IMC research, but there are still open problems to be solved.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Lei Ma, Yuhui Zheng, Zhao Zhang, Yazhou Yao, Xijian Fan, Qiaolin Ye
Summary: Conventional action recognition algorithms face great challenges in recognizing unseen combinations of action and different objects, which is known as (zero-shot) compositional action recognition in real-world applications. Previous methods rely heavily on manual annotation or the quality of detectors to enhance the dynamic clues of objects in the scene. In this work, we propose a novel Motion Stimulation (MS) block to autonomously mine the temporal clues from moving objects or hands without explicit supervision, which can enhance the ability of compositional generalization for action recognition algorithms when integrated into existing video backbones. Experimental results on three action recognition datasets demonstrate the effectiveness and interpretability of our MS block.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Business
Yuan Sun, Zhebin Ding, Zuopeng Zhang
Summary: In recent years, China has made great progress in the adoption and use of emerging information technologies. The popularity of enterprise social media (ESM) in Chinese enterprises and the resulting innovation practices provide an opportunity to explore relevant theories and assumptions. This article applies the organizational information processing theory (OIPT) to study the innovative use cases of ESM in China and identify contributing factors through a multicase-analysis approach. The research contributes to the literature by studying the innovative use cases in the ESM context and provides valuable insights for practitioners in designing and implementing ESM effectively.
IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT
(2023)
Article
Computer Science, Artificial Intelligence
Dongliang Zhou, Haijun Zhang, Kai Yang, Linlin Liu, Han Yan, Xiaofei Xu, Zhao Zhang, Shuicheng Yan
Summary: The article introduces a novel outfit generation framework OutfitGAN, aiming to synthesize a set of complementary items to compose an entire outfit. Through extensive experiments on a large-scale dataset, OutfitGAN demonstrates superior performance in synthesizing photo-realistic outfits and improving compatibility.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Jie Wen, Shijie Deng, Lunke Fei, Zheng Zhang, Bob Zhang, Zhao Zhang, Yong Xu
Summary: In this article, a new linear regression-based multiclass classification method, called DRAGD, is proposed. It explores the high-order structure information and provides a new way to capture the structure of data, resulting in a more discriminative transformation matrix. Experimental results show that DRAGD outperforms existing LR methods.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhao Zhang, Xianzhen Li, Haijun Zhang, Yi Yang, Shuicheng Yan, Meng Wang
Summary: This paper introduces an effective multi-task strategy through self-supervised data augmentation, and proposes a new end-to-end trainable Triplet Deep Subspace Clustering Network (TDSC-net). TDSC-net generates triplet data from input data using spectral clustering and self-supervised data augmentation, and builds a triplet deep autoencoder network with a self-expression layer.
2021 21ST IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yangcheng Gao, Zhao Zhang, Haijun Zhang, Mingbo Zhao, Yi Yang, Meng Wang
Summary: This paper explores accelerating deep neural network (DNN) model compression process by reducing computation cost, proposing a new Dictionary Pair-based Data-Free Fast DNN Compression method. It aims to reduce memory consumption without extra training and improve compression efficiency significantly.
2021 21ST IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Jiahuan Ren, Zhao Zhang, Jicong Fan, Haijun Zhang, Mingliang Xu, Meng Wang
Summary: In this study, a general feature recovery layer named Low-rank Deep Feature Recovery (LDFR) is proposed to enhance the representation ability of convolutional features by seamlessly integrating low-rank recovery into Convolutional Neural Networks (CNNs). By learning low-rank projections and designing fusion strategy to recover the lost information, the convolutional feature maps can be effectively restored in the test phase through low-rank embedding.
2021 21ST IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhengqi Zhang, Li Zhang, Zhao Zhang
Summary: Pin-FisherSVM is a support vector machine method that integrates the pinball loss function and Fisher regularization, exhibiting good performance and statistical separability in noisy environments.
2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yan Zhang, Zhao Zhang, Yang Wang, Zheng Zhang, Li Zhang, Shuicheng Yan, Meng Wang
Summary: In this paper, a Dual-constrained Deep Semi-Supervised Coupled Factorization Network ((DSCF)-C-2-Net) is introduced to discover hierarchical coupled data representation. It can extract hidden deep features and maintain the relationships between data, which is effective for representation learning and clustering tasks.
THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE
(2021)