4.7 Article

NIM-Nets: Noise-Aware Incomplete Multi-View Learning Networks

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Automation & Control Systems

Consistency-Induced Multiview Subspace Clustering

Yalan Qin et al.

Summary: This article proposes a novel consistency-induced multiview subspace clustering (CiMSC) method that effectively handles high-dimensional data and exploits consistency for the number of connected components in similarity matrices. Experimental results demonstrate the superiority of CiMSC over other algorithms in multiview clustering.

IEEE TRANSACTIONS ON CYBERNETICS (2023)

Article Computer Science, Artificial Intelligence

Unsupervised Contrastive Cross-Modal Hashing

Peng Hu et al.

Summary: In this paper, we propose a novel approach to make unsupervised cross-modal hashing benefit from contrastive learning by addressing the performance degradation issue caused by binary optimization for hashing and alleviating the influence brought by false-negative pairs (FNPs). To achieve this, we introduce a momentum optimizer and a Cross-modal Ranking Learning loss (CRL) that utilizes the discrimination from all negative pairs. Our method shows better retrieval performance and could be one of the first successful contrastive hashing methods.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2023)

Article Computer Science, Artificial Intelligence

Block-Diagonal Guided Symmetric Nonnegative Matrix Factorization

Yalan Qin et al.

Summary: In this paper, a new semi-supervised structured nonnegative matrix factorization (S3NMF) based clustering approach is proposed, which considers both sparseness and smoothness by enforcing a block-diagonal structure in the similarity matrix. The proposed method achieves better performance and satisfactory stability on five benchmark datasets.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2023)

Article Computer Science, Artificial Intelligence

Dual Contrastive Prediction for Incomplete Multi-View Representation Learning

Yijie Lin et al.

Summary: In this article, a unified framework is proposed to address the challenges in incomplete multi-view representation learning, including learning a consistent representation and recovering missing views. The consistency learning and data recovery are treated as a whole using an information theoretical framework. A novel objective function is introduced to jointly solve these two problems and achieve a provable sufficient and minimal representation. Experimental results show that the proposed method outperforms 20 competitive multi-view learning methods on six datasets.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2023)

Article Computer Science, Artificial Intelligence

Semi-Supervised Structured Subspace Learning for Multi-View Clustering

Yalan Qin et al.

Summary: The paper proposes a semi-supervised structured subspace learning algorithm for multi-view clustering. By introducing a small amount of supervisory information, we construct an anti-block-diagonal indicator matrix to pursue the block-diagonal structure of the shared affinity matrix. The proposed method regularizes multiple view-specific affinity matrices into a shared affinity matrix through backward encoding networks and self-expressive mapping, resulting in improved clustering results.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2022)

Article Computer Science, Artificial Intelligence

Maximum Block Energy Guided Robust Subspace Clustering

Yalan Qin et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

Article Automation & Control Systems

Deep Semisupervised Multiview Learning With Increasing Views

Peng Hu et al.

Summary: This article addresses two challenging problems in semisupervised cross-view learning and proposes a novel method that employs multiple independent semisupervised view-specific networks (ISVNs) to learn representations for multiple views in a view-decoupling fashion. The method effectively utilizes labeled and unlabeled data, while efficiently handling increasing views without retraining the entire model. Verification through comprehensive experiments shows the method's effectiveness and efficiency compared to state-of-the-art approaches on multiview datasets.

IEEE TRANSACTIONS ON CYBERNETICS (2022)

Article Computer Science, Artificial Intelligence

Enforced block diagonal subspace clustering with closed form solution

Yalan Qin et al.

Summary: This paper establishes the theoretical connection between subspace clustering based on block diagonal representation and spectral clustering. The proposed Enforced Block Diagonal Subspace Clustering (EBDSC) provides an analytical, nonnegative, and symmetrical solution, which is more general compared to existing methods. Experimental analysis demonstrates the efficiency and effectiveness of the proposed method on synthetic and benchmark datasets using different metrics.

PATTERN RECOGNITION (2022)

Article Automation & Control Systems

Joint Versus Independent Multiview Hashing for Cross-View Retrieval

Peng Hu et al.

Summary: Thanks to the low storage cost and high query speed, cross-view hashing has been widely used for similarity search in multimedia retrieval. The proposed decoupled CVH network approach includes a SHAM module and multiple MHNs, which allows for efficient handling of increasing number of views with only a few labels or the number of classes. Experimental results show the superiority of the independent hashing paradigm in terms of efficiency and adaptability to newly coming views, compared to common joint approaches.

IEEE TRANSACTIONS ON CYBERNETICS (2021)

Article Engineering, Electrical & Electronic

Structured subspace learning-induced symmetric nonnegative matrix factorization

Yalan Qin et al.

Summary: In this paper, we propose a novel approach SSLSNMF for structured subspace learning-induced symmetric nonnegative matrix factorization, which considers the global and local structures of data by learning a latent subspace based on the similarity space. The method utilizes semi-supervised learning with constraints to guarantee discriminative latent similarity subspace. Experiment results on benchmark datasets show that SSLSNMF outperforms state-of-the-art methods.

SIGNAL PROCESSING (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Partially View-aligned Representation Learning with Noise-robust Contrastive Loss

Mouxing Yang et al.

Summary: The proposed method addresses the Partially View-aligned Problem by simultaneously learning representation and aligning data using a noise-robust contrastive loss. It constructs positive and negative pairs, and uses a loss function to prevent false negatives, resulting in successful application in multi-view clustering and classification tasks with promising performance.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Proceedings Paper Computer Science, Artificial Intelligence

COMPLETER: Incomplete Multi-view Clustering via Contrastive Prediction

Yijie Lin et al.

Summary: This study introduces a novel framework that combines representation learning and data recovery to address challenging issues in incomplete multi-view clustering analysis. Experimental results demonstrate that the proposed method outperforms other competitive methods on multiple datasets.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Article Computer Science, Information Systems

Adaptive Graph Completion Based Incomplete Multi-View Clustering

Jie Wen et al.

Summary: The paper introduces a novel method AGC_IMC for clustering incomplete multi-view data, which combines graph completion and consensus representation learning. By incorporating within-view preservation, between-view inferring, and consensus representation learning, AGC_IMC effectively addresses the issue of information imbalance.

IEEE TRANSACTIONS ON MULTIMEDIA (2021)

Article Computer Science, Artificial Intelligence

Deep Spectral Representation Learning From Multi-View Data

Zhenyu Huang et al.

Summary: This paper proposes a novel multi-view unsupervised representation learning method, MvLNet, to address the limitations of existing methods by leveraging the representative capacity of deep learning. Experimental results on challenging datasets prove the effectiveness of the method in tasks such as clustering, recognition, and retrieval.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

Article Computer Science, Artificial Intelligence

A Survey of Multi-View Representation Learning

Yingming Li et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2019)

Article Computer Science, Artificial Intelligence

Multi-View Linear Discriminant Analysis Network

Peng Hu et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving

Jiwoong Choi et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Reciprocal Multi-Layer Subspace Learning for Multi-View Clustering

Ruihuang Li et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Probabilistic Face Embeddings

Yichun Shi et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

AE2-Nets: Autoencoder in Autoencoder Networks

Changqing Zhang et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Article Computer Science, Artificial Intelligence

Multi-view Clustering: A Survey

Yan Yang et al.

BIG DATA MINING AND ANALYTICS (2018)

Proceedings Paper Computer Science, Artificial Intelligence

Partial Multi-View Clustering via Consistent GAN

Qianqian Wang et al.

2018 IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM) (2018)

Article Computer Science, Artificial Intelligence

Flexible Multi-View Dimensionality Co-Reduction

Changqing Zhang et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Missing Modalities Imputation via Cascaded Residual Autoencoder

Luan Tran et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Latent Multi-view Subspace Clustering

Changqing Zhang et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Discriminatively Embedded K-Means for Multi-view Clustering

Jinglin Xu et al.

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2016)

Article Computer Science, Artificial Intelligence

Multi-View Learning With Incomplete Views

Chang Xu et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2015)

Article Computer Science, Artificial Intelligence

Sparse Subspace Clustering: Algorithm, Theory, and Applications

Ehsan Elhamifar et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2013)

Article Engineering, Ocean

On the treatment of uncertainties and probabilities in engineering decision analysis

MH Faber

JOURNAL OF OFFSHORE MECHANICS AND ARCTIC ENGINEERING-TRANSACTIONS OF THE ASME (2005)