Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleApril 2024
Multi-label Feature selection with adaptive graph learning and label information enhancement
AbstractThe high dimensionality and complexity of multi-label data make obtaining accurate label sets in practical applications difficult. Noisy data in the labels will affect the model’s classification performance. Existing methods only reconstruct ...
- research-articleJuly 2023
Adaptive graph regularized transferable regression for facial expression recognition
AbstractFacial expression recognition (FER) has tremendous potential in affective computing and human-computer interaction fields. Traditional FER algorithms usually perform the training and testing of models on a single domain. However, face ...
- research-articleJune 2023
Adaptive graph regularized non-negative Tucker decomposition for multiway dimensionality reduction
Multimedia Tools and Applications (MTAA), Volume 83, Issue 4Pages 9647–9668https://doi.org/10.1007/s11042-023-15622-4AbstractNon-negative Tucker decomposition (NTD) is a powerful tool for data representation to capture rich internal structure information from non-negative high-dimensional tensor data. Arguing that NTD methods often give global-like information, graph ...
- research-articleMay 2023
Robust latent discriminative adaptive graph preserving learning for image feature extraction
AbstractMany feature extraction methods based on subspace learning have been proposed and applied with good performance. Most existing methods fail to achieve a balance between characterizing the data and the sparsity of the feature weights. At the same ...
Highlights- We propose a new RLDAGP method for image feature extraction.
- An adaptive graph is included to enhance the grouping effect of low-dimensional data.
- The transformed l 2 , 1 norm extends the generalization of RLDAGP to the type of ...
- research-articleDecember 2022
Adaptive Graph Regularized Deep Semi-nonnegative Matrix Factorization for Data Representation
Neural Processing Letters (NPLE), Volume 54, Issue 6Pages 5721–5739https://doi.org/10.1007/s11063-022-10882-xAbstractRecently, matrix factorization-based data representation methods exhibit excellent performance in many real applications. However, traditional deep semi-nonnegative matrix factorization (DSNMF) models the relationship between samples by ...
- research-articleOctober 2022
Graph convolutional networks of reconstructed graph structure with constrained Laplacian rank
Multimedia Tools and Applications (MTAA), Volume 81, Issue 24Pages 34183–34194https://doi.org/10.1007/s11042-020-09984-2AbstractConvolutional neural networks (CNNs) have achieved unprecedented competitiveness in text and two-dimensional image data processing because of its good accuracy performance and high detection speed. Graph convolutional networks (GCNs), as an ...
- research-articleAugust 2022
Geometrical structure preservation joint with self-expression maintenance for adaptive graph learning
Neurocomputing (NEUROC), Volume 501, Issue CPages 436–450https://doi.org/10.1016/j.neucom.2022.06.045Highlights- The geometrical structure is explored in two different ways.
- Self-expressive ...
Locality preserving projection (LPP) is a subspace learning method that uses pairwise distance to measure the similarity between data points. However, when data points from different clusters are adjacent, the pairwise distance may not ...
- research-articleJuly 2022
Unsupervised feature selection via adaptive graph and dependency score
Highlights- A novel unsupervised feature selection method based on adaptive graph learning and dependency score (AGDS) is proposed.
Unsupervised feature selection is an important topic in the fields of machine learning, pattern recognition and data mining. The representation methods include adaptive-graph-based methods and self-representation-based methods. The ...
- research-articleJuly 2022
Multilabel learning based adaptive graph convolutional network for human parsing
Highlights- The fixed graph modeling may not be an optimal graph for the diversity of the samples.
In human parsing, graph convolutional networks (GCNs), which naturally model the skeleton of the human body as a fixed graph, have been witnessed to obtain remarkable performance. However, the existing methods perform the fixed graph ...
- research-articleJune 2022
An improved spatial temporal graph convolutional network for robust skeleton-based action recognition
Applied Intelligence (KLU-APIN), Volume 53, Issue 4Pages 4592–4608https://doi.org/10.1007/s10489-022-03589-yAbstractSkeleton-based action recognition methods using complete human skeletons have achieved remarkable performance, but the performance of these methods could significantly deteriorate when critical joints or frames of the skeleton sequence are ...
- ArticleOctober 2021
Skeleton-Based Sign Language Recognition with Attention-Enhanced Graph Convolutional Networks
Natural Language Processing and Chinese ComputingPages 773–785https://doi.org/10.1007/978-3-030-88480-2_62AbstractThe natural language processing of sign language is an important task in the field of artificial intelligence and information processing. In this paper, we propose an attention-enhanced graph convolutional networks (AEGCNs) for sign language ...
- research-articleOctober 2021
Adaptive graph guided concept factorization on Grassmann manifold
Information Sciences: an International Journal (ISCI), Volume 576, Issue CPages 725–742https://doi.org/10.1016/j.ins.2021.08.040AbstractMotivated by applications in clustering and optimization, there has been significant interest in the variant for which the database models are high-dimensional data (such as imagesets or videos). Matrix factorization approaches, ...
- research-articleSeptember 2021
Nonnegative spectral clustering and adaptive graph-based matrix regression for unsupervised image feature selection
Multimedia Tools and Applications (MTAA), Volume 80, Issue 21-23Pages 32885–32904https://doi.org/10.1007/s11042-021-11191-6AbstractMatrix regression model can directly take matrix data as input data, and its loss function is defined by left and right regression matrices. The spectral clustering-based matrix regression model can perform feature selection for unsupervised ...
- research-articleDecember 2019
Discriminative low-rank preserving projection for dimensionality reduction
AbstractAs an effective image clustering tool, low-rank representation (LRR) can capture the intrinsic representation of the observed samples. However, firstly, the good representation does not mean good classification performance. Secondly, ...
Highlights- Low-rank, projection and manifold learning are integrated into a unified model.
- ArticleSeptember 2018
Graph Adaptive Knowledge Transfer for Unsupervised Domain Adaptation
AbstractUnsupervised domain adaptation has caught appealing attentions as it facilitates the unlabeled target learning by borrowing existing well-established source domain knowledge. Recent practice on domain adaptation manages to extract effective ...
- research-articleFebruary 2016
3D human motion retrieval using graph kernels based on adaptive graph construction
Computers and Graphics (CGRS), Volume 54, Issue CPages 104–112https://doi.org/10.1016/j.cag.2015.07.005Graphs are frequently used to provide a powerful representation for structured data. However, it is still a challenging task to model 3D human motions due to its large spatio-temporal variations. This paper proposes a novel graph-based method for real ...