Shuai Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shuai Zhao has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Xiaoqian Zhang
Southwest University of Science and Technology
6 shared publications - Xiao Wang
School of Information Engineering, Southwest University of Science and Technology, Mianyang, China
3 shared publications - Chao Luo
School of Information Engineering, Southwest University of Science and Technology, Mianyang, China
2 shared publications - Huaijiang Sun
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China
2 shared publications - Jinghao Li
School of Information Engineering, Southwest University of Science and Technology, Mianyang, China
2 shared publications - Yilu Zheng
School of Computer Science and Technology, University of Science and Technology of China, Hefei 230026, China
2 shared publications
Latest Publications
- 5 June 2024
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 80 (14) , 21001-21022
Global and local structure projection learning for image feature extraction
- 5 June 2024
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 80 (14) , 21001-21022
Global and local structure projection learning for image feature extraction
- 31 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 7160-7173
Learnable Tensor Graph Fusion Framework for Natural Image Segmentation
Existing natural image segmentation tasks often face some troubles in getting accurate contours or causing over-segmentation of local areas during segmentation, and the multi-feature information mining of images is insufficient. To address these problems, learnable tensor graph fusion framework for natural image segmentation (LTGF-NIS) is proposed in this paper. Firstly, we pre-process the original images by adaptive morphological reconstruction watershed transform, and the multi-feature data is extracted, the multi-feature data matrix contains information about the image. Then we design an adaptive weighted tensor affinity graph fusion method (AWTAGF), which learns the higher-order correlation of the multi-feature information by two coupling tensor, while achieving consistent representation of the multi-feature information by using adaptive weighted graph fusion. Finally, the obtained affinity graph is clustered and segmented using spectral clustering to realize the segmentation of natural images. We test affinity graph learning ability and natural image segmentation effect of the proposed algorithm on several datasets, the experimental data indicates that the segmentation effect of our framework is superior to some existing advanced methods.
- 31 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 7160-7173
Learnable Tensor Graph Fusion Framework for Natural Image Segmentation
Existing natural image segmentation tasks often face some troubles in getting accurate contours or causing over-segmentation of local areas during segmentation, and the multi-feature information mining of images is insufficient. To address these problems, learnable tensor graph fusion framework for natural image segmentation (LTGF-NIS) is proposed in this paper. Firstly, we pre-process the original images by adaptive morphological reconstruction watershed transform, and the multi-feature data is extracted, the multi-feature data matrix contains information about the image. Then we design an adaptive weighted tensor affinity graph fusion method (AWTAGF), which learns the higher-order correlation of the multi-feature information by two coupling tensor, while achieving consistent representation of the multi-feature information by using adaptive weighted graph fusion. Finally, the obtained affinity graph is clustered and segmented using spectral clustering to realize the segmentation of natural images. We test affinity graph learning ability and natural image segmentation effect of the proposed algorithm on several datasets, the experimental data indicates that the segmentation effect of our framework is superior to some existing advanced methods.
- Open Access
- 23 December 2023
- Published by MDPI AG in Electronics
- Vol. 13 (1) , 83
Large-Scale Subspace Clustering Based on Purity Kernel Tensor Learning
In conventional subspace clustering methods, affinity matrix learning and spectral clustering algorithms are widely used for clustering tasks. However, these steps face issues, including high time consumption and spatial complexity, making large-scale subspace clustering (LSC) tasks challenging to execute effectively. To address these issues, we propose a large-scale subspace clustering method based on pure kernel tensor learning (PKTLSC). Specifically, we design a pure kernel tensor learning (PKT) method to acquire as much data feature information as possible while ensuring model robustness. Next, we extract a small sample dataset from the original data and use PKT to learn its affinity matrix while simultaneously training a deep encoder. Finally, we apply the trained deep encoder to the original large-scale dataset to quickly obtain its projection sparse coding representation and perform clustering. Through extensive experiments on large-scale real datasets, we demonstrate that the PKTLSC method outperforms existing LSC methods in clustering performance.- 23 December 2023
- Published by MDPI AG in Electronics
- Vol. 13 (1) , 83
Open AccessLarge-Scale Subspace Clustering Based on Purity Kernel Tensor Learning
In conventional subspace clustering methods, affinity matrix learning and spectral clustering algorithms are widely used for clustering tasks. However, these steps face issues, including high time consumption and spatial complexity, making large-scale subspace clustering (LSC) tasks challenging to execute effectively. To address these issues, we propose a large-scale subspace clustering method based on pure kernel tensor learning (PKTLSC). Specifically, we design a pure kernel tensor learning (PKT) method to acquire as much data feature information as possible while ensuring model robustness. Next, we extract a small sample dataset from the original data and use PKT to learn its affinity matrix while simultaneously training a deep encoder. Finally, we apply the trained deep encoder to the original large-scale dataset to quickly obtain its projection sparse coding representation and perform clustering. Through extensive experiments on large-scale real datasets, we demonstrate that the PKTLSC method outperforms existing LSC methods in clustering performance. - 30 November 2023
- Published by Elsevier in Information Processing & Management
- Vol. 61 (2)
Pure kernel graph fusion tensor subspace clustering under non-negative matrix factorization framework
- 30 November 2023
- Published by Elsevier in Information Processing & Management
- Vol. 61 (2)
Pure kernel graph fusion tensor subspace clustering under non-negative matrix factorization framework
- 27 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (3) , 1900-1913
Purity-Preserving Kernel Tensor Low-Rank Learning for Robust Subspace Clustering
In recent years, multi-kernel learning (MKL) methods have been widely used in performing nonlinear data subspace clustering tasks, benefiting from the fact that they do not require the selection and tuning of predefined kernels. However, the effect of raw noise on the data structure in the feature space has been neglected in most MKL studies so far. In this paper, we propose a robust subspace clustering method called purity kernel tensor low-rank learning (KTLL), which effectively isolates noise transfer from the original data space to the high-dimensional feature space. Specifically, we construct the kernel pool obtained by MKL as a primitive third-order kernel tensor, separate the corrupted information in the feature space, and use the separated pure kernel tensor to learn the optimal affinity matrix. The tensor learning of the kernel pool can effectively mine the higher-order correlations among different kernel matrices, thus improving the clustering performance of KTLL.We have conducted extensive experiments to compare KTLL with state-of-the-art MKL and deep subspace clustering algorithms, and our results demonstrate the superiority of KTLL.
- 27 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (3) , 1900-1913
Purity-Preserving Kernel Tensor Low-Rank Learning for Robust Subspace Clustering
In recent years, multi-kernel learning (MKL) methods have been widely used in performing nonlinear data subspace clustering tasks, benefiting from the fact that they do not require the selection and tuning of predefined kernels. However, the effect of raw noise on the data structure in the feature space has been neglected in most MKL studies so far. In this paper, we propose a robust subspace clustering method called purity kernel tensor low-rank learning (KTLL), which effectively isolates noise transfer from the original data space to the high-dimensional feature space. Specifically, we construct the kernel pool obtained by MKL as a primitive third-order kernel tensor, separate the corrupted information in the feature space, and use the separated pure kernel tensor to learn the optimal affinity matrix. The tensor learning of the kernel pool can effectively mine the higher-order correlations among different kernel matrices, thus improving the clustering performance of KTLL.We have conducted extensive experiments to compare KTLL with state-of-the-art MKL and deep subspace clustering algorithms, and our results demonstrate the superiority of KTLL.
- 12 February 2023
- Published by Springer Nature in Neural Computing and Applications
- Vol. 35 (15) , 1-16
Tensor-based multi-feature affinity graph learning for natural image segmentation
- 12 February 2023
- Published by Springer Nature in Neural Computing and Applications
- Vol. 35 (15) , 1-16
Tensor-based multi-feature affinity graph learning for natural image segmentation