Tensorial Multi-View Clustering via Low-Rank Constrained High-Order Graph Learning

Jiang, Guangqi; Peng, Jinjia; Wang, Huibing; Mi, Zetian; Fu, Xianping

doi:10.1109/tcsvt.2022.3143848

Cited by 51 publications

(10 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Definition 2: (Tensor Transpose): For the tensor X with size n 1 × n 2 × n 3 , the transpose tensor X T ∈ R n2×n1×n3 is obtained by transposing each frontal slices and then reversing the order of frontal slices 2 to n 3 . For example, let X and its frontal slices be X (1) , X (2) , X (3) and X (4) , then…”

Section: Bcirc(mentioning

confidence: 99%

“…Resorting to the comprehensive information of multi-view features, multi-view learning has improved multimedia data (such as images, videos and documents) analysis performance and has been widely used in clustering, classification etc. [1], [2]. Multi-view clustering (MVC) [3]- [6] learns the correlation of multiple views in an unsupervised manner to divide multimedia data into different clusters [7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robustness Meets Low-Rankness: Unified Entropy and Tensor Learning for Multi-View Subspace Clustering

Wang

Chen

Lin

et al. 2023

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

In this paper, we develop the weighted error entropy-regularized tensor learning method for multi-view subspace clustering (WETMSC), which integrates the noise disturbance removal and subspace structure discovery into one unified framework. Unlike most existing methods which focus only on the affinity matrix learning for the subspace discovery by different optimization models and simply assume that the noise is independent and identically distributed (i.i.d.), our WETMSC method adopts the weighted error entropy to characterize the underlying noise by assuming that noise is independent and piecewise identically distributed (i.p.i.d.). Meanwhile, WETMSC constructs the self-representation tensor by storing all selfrepresentation matrices from the view dimension, preserving high-order correlation of views based on the tensor nuclear norm. To solve the proposed nonconvex optimization method, we design a half-quadratic (HQ) additive optimization technology and iteratively solve all subproblems under the alternating direction method of multipliers framework. Extensive comparison studies with state-of-the-art clustering methods on real-world datasets and synthetic noisy datasets demonstrate the ascendancy of the proposed WETMSC method.

show abstract

Section: Bcirc(mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Robustness Meets Low-Rankness: Unified Entropy and Tensor Learning for Multi-View Subspace Clustering

Wang

Chen

Lin

et al. 2023

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…The purpose of infrared and visible video fusion is to combine video features from different modalities, then obtain information-rich fused video. Video fusion can be considered as a special kind of video enhancement technology, usually, its downstream tasks contain object segmentation [3,4,5], object tracking [6], object detection [7]，video-based mesh reconstruction [8] and multi-view clustering [9] etc.…”

Section: Introductionmentioning

confidence: 99%

Infrared and visible video fusion method based on local differential correlation features and PID control

Tang,

Wang

2024

Preprint

View full text Add to dashboard Cite

The purpose of infrared and visible video fusion is to combine the complementary features of videos from different modalities. Most fusion algorithms ignore the feature associations of adjacent frames and the guidance of the source frames to the fusion process. Therefore, this paper proposes a new fusion method. First, a spatial-domain multi-attribute detail feature extraction model is proposed, which is capable of extracting the base layer, the bright detail layer and the dark detail layer of the source frames separately. Then, we propose an associated feature extraction model for adjacent frames, which improves the spatial continuity of the fused video. Furthermore, an exponential homomorphic filter is proposed, which simultaneously increases the dynamic range and contrast of the source infrared frames to obtain a general salient target extraction model. In the feature fusion stage, a weighted fusion rule based on edge intensity is used in the detail layer. Then we design the controller, transfer function and measurement function separately, so as to construct a closed-loop proportional-integral-derivative (PID) control system to fuse the base layer, which ensures that the fused video maintains more information of the source video. Experiments on public datasets demonstrate that our fusion method outperforms some state-of-the-art algorithms.

show abstract

“…To make better use of unlabeled data, unsupervised clustering has gradually attracted widespread attention. The main research directions of clustering at this stage can be divided into image, text [2], multi-view clustering [3,4] and so on. Among these data, the simplest and most intuitive feeling is image data.…”

Section: Introductionmentioning

confidence: 99%

Deep Image Clustering Based on Label Similarity and Maximizing Mutual Information across Views

Peng

2023

Applied Sciences

View full text Add to dashboard Cite

Most existing deep image clustering methods use only class-level representations for clustering. However, the class-level representation alone is not sufficient to describe the differences between images belonging to the same cluster. This may lead to high intra-class representation differences, which will harm the clustering performance. To address this problem, this paper proposes a clustering model named Deep Image Clustering based on Label Similarity and Maximizing Mutual Information Across Views (DCSM). DCSM consists of a backbone network, class-level and instance-level mapping block. The class-level mapping block learns discriminative class-level features by selecting similar (dissimilar) pairs of samples. The proposed extended mutual information is to maximize the mutual information between features extracted from views that were obtained by using data augmentation on the same image and as a constraint on the instance-level mapping block. This forces the instance-level mapping block to capture high-level features that affect multiple views of the same image, thus reducing intra-class differences. Four representative datasets are selected for our experiments, and the results show that the proposed model is superior to the current advanced image clustering models.

show abstract

Tensorial Multi-View Clustering via Low-Rank Constrained High-Order Graph Learning

Cited by 51 publications

References 42 publications

Robustness Meets Low-Rankness: Unified Entropy and Tensor Learning for Multi-View Subspace Clustering

Robustness Meets Low-Rankness: Unified Entropy and Tensor Learning for Multi-View Subspace Clustering

Infrared and visible video fusion method based on local differential correlation features and PID control

Deep Image Clustering Based on Label Similarity and Maximizing Mutual Information across Views

Contact Info

Product

Resources

About