Xiaohong Jia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Xiaohong Jia has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Asoke Kumar Nandi
Brunel University of London
5 shared publications - Tao Lei
Fuzhou University, Fuzhou, China
5 shared publications - Yao Zhao
Institute of Information Science, Beijing Jiaotong University, Beijing, China and Visual Intelligence + X International Joint Laboratory, Beijing, China
5 shared publications - Hongying Meng
Brunel University of London
4 shared publications Dinghua Xue
School of Electrical and Control Engineering, Shaanxi University of Science and Technology, Xian, China
2 shared publicationsPeng Liu
School of Electrical and Control Engineering, Shaanxi University of Science and Technology, Xi’an 710021, China
2 shared publications
Latest Publications
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 553-557
Entropy Regularized Simple Multiple Kernel K-Means with Adaptive Deviation Correction
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 553-557
Open AccessEntropy Regularized Simple Multiple Kernel K-Means with Adaptive Deviation Correction
- 8 March 2026
- Published by Springer Nature in International Journal of Fuzzy Systems
- p. 1-18
Super-Aware Fuzzy C-Means Clustering for Hyperspectral Image Segmentation
- 8 March 2026
- Published by Springer Nature in International Journal of Fuzzy Systems
- p. 1-18
Super-Aware Fuzzy C-Means Clustering for Hyperspectral Image Segmentation
- 8 January 2026
- Published by Springer Nature in Multimedia Systems
- Vol. 32 (1) , 67
Vulnerability Positioner (VulP): enhancing code vulnerability localization with CodeBERT
- 8 January 2026
- Published by Springer Nature in Multimedia Systems
- Vol. 32 (1) , 67
Vulnerability Positioner (VulP): enhancing code vulnerability localization with CodeBERT
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Letters
- Vol. 10 (8) , 1-4
Adaptive Fusion of CNN-Transformer for Superpixel Segmentation
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Letters
- Vol. 10 (8) , 1-4
Adaptive Fusion of CNN-Transformer for Superpixel Segmentation
- Open Access
- 10 April 2025
- Published by Springer Nature in International Journal of Fuzzy Systems
- Vol. 28 (4) , 1217-1235
Fuzzy C-Means Clustering with Region Constraints for Superpixel Generation
Superpixels are becoming increasingly essential in computer vision applications, as they significantly reduce the number of computational primitives required for subsequent tasks. However, most existing superpixel algorithms primarily focus on color intensity and position coordinates, often ignoring local neighborhood factors and region constraints. This oversight reduces their effectiveness in noisy and cluttered environments. To address this issue, we propose a seminal and novel Fuzzy C-Means clustering with Region Constraints for Superpixel generation (RCFCMS). First, RCFCMS employs watershed transform to establish region constraints, effectively preventing boundary crossings. Second, relative position relationship is utilized to initialize superpixel centers within each region, offering an adaptive grid layout. Third, RCFCMS adopts spatial information to perceive local similarity, significantly mitigating noise interference. Finally, connected components are applied to eliminate isolated pixels, further optimizing pixel assignment. The experimental results on two benchmark datasets demonstrate that the proposed RCFCMS achieves competitive performance across varying numbers of superpixels. Specifically, when the number of superpixels is 500, RCFCMS achieves the following metrics: UE = 0.102, ASA = 0.948, FM = 0.401, and CO = 0.572 on BSDS500; and UE = 0.124, ASA = 0.935, FM = 0.296, and CO = 0.608 on SBD. These results further highlight the effectiveness of RCFCMS for superpixel generation.
- 10 April 2025
- Published by Springer Nature in International Journal of Fuzzy Systems
- Vol. 28 (4) , 1217-1235
Open AccessFuzzy C-Means Clustering with Region Constraints for Superpixel Generation
Superpixels are becoming increasingly essential in computer vision applications, as they significantly reduce the number of computational primitives required for subsequent tasks. However, most existing superpixel algorithms primarily focus on color intensity and position coordinates, often ignoring local neighborhood factors and region constraints. This oversight reduces their effectiveness in noisy and cluttered environments. To address this issue, we propose a seminal and novel Fuzzy C-Means clustering with Region Constraints for Superpixel generation (RCFCMS). First, RCFCMS employs watershed transform to establish region constraints, effectively preventing boundary crossings. Second, relative position relationship is utilized to initialize superpixel centers within each region, offering an adaptive grid layout. Third, RCFCMS adopts spatial information to perceive local similarity, significantly mitigating noise interference. Finally, connected components are applied to eliminate isolated pixels, further optimizing pixel assignment. The experimental results on two benchmark datasets demonstrate that the proposed RCFCMS achieves competitive performance across varying numbers of superpixels. Specifically, when the number of superpixels is 500, RCFCMS achieves the following metrics: UE = 0.102, ASA = 0.948, FM = 0.401, and CO = 0.572 on BSDS500; and UE = 0.124, ASA = 0.935, FM = 0.296, and CO = 0.608 on SBD. These results further highlight the effectiveness of RCFCMS for superpixel generation.
- 9 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 32 (10709908) , 1715-1719
SSMamba: Superpixel Segmentation With Mamba
Deep convolutional networks have achieved remarkable success in superpixel segmentation. However, they only focus on local features ignoring global attributes. The visual Mamba demonstrates an exceptional capability to capture long-range dependencies and offers a lower computational cost compared to the Transformer. Building on this inspiration, we propose a novel superpixel segmentation with Mamba, termed SSMamba. In SSMamba, Mamba is integrated into a global-local architecture, enabling efficient interaction between global attributes and local features to produce high-quality superpixels. The designed activation function further enhances the effectiveness of SSMamba. Extensive experiments on four public datasets demonstrate that SSMamba outperforms existing state-of-the-art methods, achieving competitive average values of ASA = 0.9541, BR = 0.8768, BP = 0.2124, UE = 0.0910, and CO = 0.3698.
- 9 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 32 (10709908) , 1715-1719
SSMamba: Superpixel Segmentation With Mamba
Deep convolutional networks have achieved remarkable success in superpixel segmentation. However, they only focus on local features ignoring global attributes. The visual Mamba demonstrates an exceptional capability to capture long-range dependencies and offers a lower computational cost compared to the Transformer. Building on this inspiration, we propose a novel superpixel segmentation with Mamba, termed SSMamba. In SSMamba, Mamba is integrated into a global-local architecture, enabling efficient interaction between global attributes and local features to produce high-quality superpixels. The designed activation function further enhances the effectiveness of SSMamba. Extensive experiments on four public datasets demonstrate that SSMamba outperforms existing state-of-the-art methods, achieving competitive average values of ASA = 0.9541, BR = 0.8768, BP = 0.2124, UE = 0.0910, and CO = 0.3698.
- Open Access
- 30 January 2024
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 171, 108087
Thyroid ultrasound diagnosis improvement via multi-view self-supervised learning and two-stage pre-training
- 30 January 2024
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 171, 108087
Open AccessThyroid ultrasound diagnosis improvement via multi-view self-supervised learning and two-stage pre-training
- Open Access
- 26 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 30 (8) , 3023-3037
Fuzzy STUDENT’S T-Distribution Model Based on Richer Spatial Combination
Fuzzy c-means (FCM) algorithms with spatial information have been widely applied in the field of image segmentation. However, most of them suffer from two challenges. One is that the introduction of fixed or adaptive single neighboring information with narrow receptive field limits contextual constraints leading to clutter segmentations. The other is that the incorporation of superpixels with wide receptive field enlarges spatial coherency leading to block effects. To address these challenges, we propose fuzzy STUDENT’S t-distribution model based on richer spatial combination (FRSC) for image segmentation. In this article, we make two significant contributions. The first is that both the narrow and wide receptive fields are integrated into the objective function of FRSC, which is convenient to mine image features and distinguish local difference. The second is that the rich spatial combination under STUDENT’S t-distribution ensures that spatial information is introduced into the updated parameters of FRSC, which is helpful in finding a balance between the noise-immunity and detail-preservation. Experimental results on synthetic and publicly available images further demonstrate that the proposed FRSC addresses successfully the limitations of FCM algorithms with spatial information, and provides better segmentation results than state-of-the-art clustering algorithms.
- 26 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 30 (8) , 3023-3037
Open AccessFuzzy STUDENT’S T-Distribution Model Based on Richer Spatial Combination
Fuzzy c-means (FCM) algorithms with spatial information have been widely applied in the field of image segmentation. However, most of them suffer from two challenges. One is that the introduction of fixed or adaptive single neighboring information with narrow receptive field limits contextual constraints leading to clutter segmentations. The other is that the incorporation of superpixels with wide receptive field enlarges spatial coherency leading to block effects. To address these challenges, we propose fuzzy STUDENT’S t-distribution model based on richer spatial combination (FRSC) for image segmentation. In this article, we make two significant contributions. The first is that both the narrow and wide receptive fields are integrated into the objective function of FRSC, which is convenient to mine image features and distinguish local difference. The second is that the rich spatial combination under STUDENT’S t-distribution ensures that spatial information is introduced into the updated parameters of FRSC, which is helpful in finding a balance between the noise-immunity and detail-preservation. Experimental results on synthetic and publicly available images further demonstrate that the proposed FRSC addresses successfully the limitations of FCM algorithms with spatial information, and provides better segmentation results than state-of-the-art clustering algorithms.
- Open Access
- 23 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 14 (19391404) , 1796-1809
Unsupervised Change Detection Using Multiscale and Multiresolution Gaussian-Mixture-Model Guided by Saliency Enhancement
Popular unsupervised change detection algorithms suffer from two problems: firstly, the difference image generated by bitemporal images usually includes a large number of falsely changed regions due to noise corruption and illumination change; secondly, fuzzy clustering algorithms are sensitive to noise and they miss the relationship among feature components. To address these issues, we propose a multi-scale and multi-resolution Gaussian-mixture-model guided by saliency-enhancement (SE-MGMM) for change detection in bitemporal remote sensing images. The proposed SE-MGMM makes two contributions. The first is a novel salient strategy that can enhance saliency objects while suppressing the image background. The strategy uses the saliency weight information to enhance changed regions leading to the improvement of grayscale contrast between changed regions and unchanged regions. The second is that we present a Gaussian-mixture-model based on spatial multi-scale and frequency multi-resolution information fusion (SM-FM), which can effectively utilize features of difference images and improve detection results of changed regions. Experiments show that the proposed SE-MGMM is robust for both very high-resolution (VHR) remote sensing images and synthetic aperture radar (SAR) images. Moreover, the SE-MGMM achieves better change detection and provides better performance metrics than state-of-the-art approaches.
- 23 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 14 (19391404) , 1796-1809
Open AccessUnsupervised Change Detection Using Multiscale and Multiresolution Gaussian-Mixture-Model Guided by Saliency Enhancement
Popular unsupervised change detection algorithms suffer from two problems: firstly, the difference image generated by bitemporal images usually includes a large number of falsely changed regions due to noise corruption and illumination change; secondly, fuzzy clustering algorithms are sensitive to noise and they miss the relationship among feature components. To address these issues, we propose a multi-scale and multi-resolution Gaussian-mixture-model guided by saliency-enhancement (SE-MGMM) for change detection in bitemporal remote sensing images. The proposed SE-MGMM makes two contributions. The first is a novel salient strategy that can enhance saliency objects while suppressing the image background. The strategy uses the saliency weight information to enhance changed regions leading to the improvement of grayscale contrast between changed regions and unchanged regions. The second is that we present a Gaussian-mixture-model based on spatial multi-scale and frequency multi-resolution information fusion (SM-FM), which can effectively utilize features of difference images and improve detection results of changed regions. Experiments show that the proposed SE-MGMM is robust for both very high-resolution (VHR) remote sensing images and synthetic aperture radar (SAR) images. Moreover, the SE-MGMM achieves better change detection and provides better performance metrics than state-of-the-art approaches.
- Open Access
- 24 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 211526-211539
Fast and Automatic Image Segmentation Using Superpixel-Based Graph Clustering
Although automatic fuzzy clustering framework (AFCF) based on improved density peak clustering is able to achieve automatic and efficient image segmentation, the framework suffers from two problems. The first one is that the adaptive morphological reconstruction (AMR) employed by the AFCF is easily influenced by the initial structuring element. The second one is that the improved density peak clustering using a density balance strategy is complex for finding potential clustering centers. To address these two problems, we propose a fast and automatic image segmentation algorithm using superpixel-based graph clustering (FAS-SGC). The proposed algorithm has two major contributions. First, the AMR based on regional minimum removal (AMR-RMR) is presented to improve the superpixel result generated by the AMR. The binary morphological reconstruction is performed on a regional minimum image, which overcomes the problem that the initial structuring element of the AMR is chosen empirically, since the geometrical information of images is effectively explored and utilized. Second, we use an eigenvalue gradient clustering (EGC) instead of improved density peak (DP) algorithms to obtain potential clustering centers, since the EGC is faster and requires fewer parameters than the DP algorithm. Experiments show that the proposed algorithm is able to achieve automatic image segmentation, providing better segmentation results while requiring less execution time than other state-of-the-art algorithms.
- 24 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 211526-211539
Open AccessFast and Automatic Image Segmentation Using Superpixel-Based Graph Clustering
Although automatic fuzzy clustering framework (AFCF) based on improved density peak clustering is able to achieve automatic and efficient image segmentation, the framework suffers from two problems. The first one is that the adaptive morphological reconstruction (AMR) employed by the AFCF is easily influenced by the initial structuring element. The second one is that the improved density peak clustering using a density balance strategy is complex for finding potential clustering centers. To address these two problems, we propose a fast and automatic image segmentation algorithm using superpixel-based graph clustering (FAS-SGC). The proposed algorithm has two major contributions. First, the AMR based on regional minimum removal (AMR-RMR) is presented to improve the superpixel result generated by the AMR. The binary morphological reconstruction is performed on a regional minimum image, which overcomes the problem that the initial structuring element of the AMR is chosen empirically, since the geometrical information of images is effectively explored and utilized. Second, we use an eigenvalue gradient clustering (EGC) instead of improved density peak (DP) algorithms to obtain potential clustering centers, since the EGC is faster and requires fewer parameters than the DP algorithm. Experiments show that the proposed algorithm is able to achieve automatic image segmentation, providing better segmentation results while requiring less execution time than other state-of-the-art algorithms.