Xiao Kang
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
Research Interests
Xiao Kang has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Xingbo Liu
Shandong Jianzhu University, Jinan, China
8 shared publications - Xiushan Nie
Shandong Jianzhu University
6 shared publications - Shaohua Wang
School of Computer Science and Technology, Shandong Jianzhu University, Jinan, China
4 shared publications - Xuening Zhang
Harbin Institute of Technology, Shenzhen, China
4 shared publications - Yilong Yin
Shandong University
4 shared publications Xiushan Nie
2 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (21) , 49777-49787
FURINA: Free From Unmergeable Router via Linear Aggregation of Mixed Experts
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (21) , 49777-49787
FURINA: Free From Unmergeable Router via Linear Aggregation of Mixed Experts
- Open Access
- 21 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (12) , 1-20
Online Hashing with Discriminative Attribute Embedding
Online hashing has emerged as a powerful tool for efficiently processing large-scale and streaming data. However, existing approaches often struggle with scalability limitations in similarity relations and inadequate discrimination provided by one-hot labels. To address these challenges, we propose Online Hashing with Discriminative Attribute Embedding (OHDAE). This novel method leverages a triple-matrix decomposition framework to dynamically decompose features into a dictionary, attributes, and category representations, effectively capturing semantic consistency without relying on accumulated data. To enhance the consistency and discriminability of attributes, we introduce an attribute construction strategy that integrates dictionary constraints with an online optimization strategy. Additionally, fine-grained semantic labels are embedded to improve the discriminability of hash codes by incorporating both semantic and similarity relationships. Experiments conducted on three benchmark datasets validate the superior performance, scalability, and robustness of OHDAE compared to existing state-of-the-art methods.
- 21 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (12) , 1-20
Open AccessOnline Hashing with Discriminative Attribute Embedding
Online hashing has emerged as a powerful tool for efficiently processing large-scale and streaming data. However, existing approaches often struggle with scalability limitations in similarity relations and inadequate discrimination provided by one-hot labels. To address these challenges, we propose Online Hashing with Discriminative Attribute Embedding (OHDAE). This novel method leverages a triple-matrix decomposition framework to dynamically decompose features into a dictionary, attributes, and category representations, effectively capturing semantic consistency without relying on accumulated data. To enhance the consistency and discriminability of attributes, we introduce an attribute construction strategy that integrates dictionary constraints with an online optimization strategy. Additionally, fine-grained semantic labels are embedded to improve the discriminability of hash codes by incorporating both semantic and similarity relationships. Experiments conducted on three benchmark datasets validate the superior performance, scalability, and robustness of OHDAE compared to existing state-of-the-art methods.
- 15 June 2024
- Published by Elsevier in Pattern Recognition
- Vol. 155
Discrete online cross-modal hashing with consistency preservation
- 15 June 2024
- Published by Elsevier in Pattern Recognition
- Vol. 155
Discrete online cross-modal hashing with consistency preservation
- Open Access
- 13 June 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (8) , 1-18
Online Cross-modal Hashing With Dynamic Prototype
Online cross-modal hashing has received increasing attention due to its efficiency and effectiveness in handling cross-modal streaming data retrieval. Despite the promising performance, these methods mainly focus on the supervised learning paradigm, demanding expensive and laborious work to obtain clean annotated data. Existing unsupervised online hashing methods mostly struggle to construct instructive semantic correlations among data chunks, resulting in the forgetting of accumulated data distribution. To this end, we propose a Dynamic Prototype-based Online Cross-modal Hashing method, called DPOCH. Based on the pre-learned reliable common representations, DPOCH generates prototypes incrementally as sketches of accumulated data and updates them dynamically for adapting streaming data. Thereafter, the prototype-based semantic embedding and similarity graphs are designed to promote stability and generalization of the hashing process, thereby obtaining globally adaptive hash codes and hash functions. Experimental results on benchmarked datasets demonstrate that the proposed DPOCH outperforms state-of-the-art unsupervised online cross-modal hashing methods.
- 13 June 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (8) , 1-18
Open AccessOnline Cross-modal Hashing With Dynamic Prototype
Online cross-modal hashing has received increasing attention due to its efficiency and effectiveness in handling cross-modal streaming data retrieval. Despite the promising performance, these methods mainly focus on the supervised learning paradigm, demanding expensive and laborious work to obtain clean annotated data. Existing unsupervised online hashing methods mostly struggle to construct instructive semantic correlations among data chunks, resulting in the forgetting of accumulated data distribution. To this end, we propose a Dynamic Prototype-based Online Cross-modal Hashing method, called DPOCH. Based on the pre-learned reliable common representations, DPOCH generates prototypes incrementally as sketches of accumulated data and updates them dynamically for adapting streaming data. Thereafter, the prototype-based semantic embedding and similarity graphs are designed to promote stability and generalization of the hashing process, thereby obtaining globally adaptive hash codes and hash functions. Experimental results on benchmarked datasets demonstrate that the proposed DPOCH outperforms state-of-the-art unsupervised online cross-modal hashing methods.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (7) , 5242-5254
Online Discriminative Cross-Modal Hashing
Online cross-modal hashing has received increasing research attention due to its capability of encoding streaming data and updating hash functions simultaneously. Despite significant progress, there is still room for further improving accuracy from two aspects, i.e ., 1) enhancing discrimination of hash codes with an efficient training process; 2) elevating generalization performance by harmonizing the training and retrieval process. Inspired by this, we propose an Online Discriminative Cross-modal Hashing method, called ODCH. To enlarge the inter-class margin and magnify the intra-class similarity, ODCH skillfully constructs a discriminative semantic space and seamlessly integrates bit balance and uncorrelation constraints, discrete optimization, and asymmetric strategy for embedding the discriminative semantic information into hamming space. Furthermore, ODCH attempts to boost the generalization process by bridging the gap between learning and generalization. It develops adaptive bit-wise weights to reflect different learning conditions among bits and transmits them into the generalization process. Besides, the proposed discriminative embedding and adaptive weighting can be adopted by existing supervised cross-modal hashing methods, achieving more precise performance than the original versions. Extensive experiments on three benchmarked datasets show that ODCH achieves up to an average of 4.17% mAP score gains compared to state-of-the-art online cross-modal hashing methods, indicating its superiority.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (7) , 5242-5254
Online Discriminative Cross-Modal Hashing
Online cross-modal hashing has received increasing research attention due to its capability of encoding streaming data and updating hash functions simultaneously. Despite significant progress, there is still room for further improving accuracy from two aspects, i.e ., 1) enhancing discrimination of hash codes with an efficient training process; 2) elevating generalization performance by harmonizing the training and retrieval process. Inspired by this, we propose an Online Discriminative Cross-modal Hashing method, called ODCH. To enlarge the inter-class margin and magnify the intra-class similarity, ODCH skillfully constructs a discriminative semantic space and seamlessly integrates bit balance and uncorrelation constraints, discrete optimization, and asymmetric strategy for embedding the discriminative semantic information into hamming space. Furthermore, ODCH attempts to boost the generalization process by bridging the gap between learning and generalization. It develops adaptive bit-wise weights to reflect different learning conditions among bits and transmits them into the generalization process. Besides, the proposed discriminative embedding and adaptive weighting can be adopted by existing supervised cross-modal hashing methods, achieving more precise performance than the original versions. Extensive experiments on three benchmarked datasets show that ODCH achieves up to an average of 4.17% mAP score gains compared to state-of-the-art online cross-modal hashing methods, indicating its superiority.
- 6 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (7) , 6517-6529
Semi-Supervised Semi-Paired Cross-Modal Hashing
Large-scale cross-modal hashing has drawn extensive attention due to its attractive efficiency in both storage and retrieval. Existing methods exhibit poor performance when exploiting the semantic correlations implied in unsupervised and unpaired data during training process. To deal with this issue, we propose a novel hashing method, named Semi-supervised Semi-paired Cross-modal Hashing (SSCH). By leveraging a general and flexible two-step scheme, the proposed method can handle the complex training data effectively and efficiently, where both the common semantics and the modality-specific optimal pseudo semantics are well captured. Specifically, the proposed SSCH performs an alignment-free pseudo-labeling process to get strengthened semantic information. Furthermore, hash representations for various data are learned via a label-enhanced strategy, through which the cross-modal correlations are strengthened and preserved with considering efficiency. The semantic-preserving proof of SSCH is given based on statistical analysis. Also, we prove the stability of the proposed time-saving algorithm using properties of Bregman divergence. Experimental results on three benchmark datasets show that SSCH can obtain satisfactory precision and scalability in various scenarios.
- 6 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (7) , 6517-6529
Semi-Supervised Semi-Paired Cross-Modal Hashing
Large-scale cross-modal hashing has drawn extensive attention due to its attractive efficiency in both storage and retrieval. Existing methods exhibit poor performance when exploiting the semantic correlations implied in unsupervised and unpaired data during training process. To deal with this issue, we propose a novel hashing method, named Semi-supervised Semi-paired Cross-modal Hashing (SSCH). By leveraging a general and flexible two-step scheme, the proposed method can handle the complex training data effectively and efficiently, where both the common semantics and the modality-specific optimal pseudo semantics are well captured. Specifically, the proposed SSCH performs an alignment-free pseudo-labeling process to get strengthened semantic information. Furthermore, hash representations for various data are learned via a label-enhanced strategy, through which the cross-modal correlations are strengthened and preserved with considering efficiency. The semantic-preserving proof of SSCH is given based on statistical analysis. Also, we prove the stability of the proposed time-saving algorithm using properties of Bregman divergence. Experimental results on three benchmark datasets show that SSCH can obtain satisfactory precision and scalability in various scenarios.
- Open Access
- 26 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 197-203
Breast Tumor Classification With Attention Model Enhancement Network
Breast tumor classification remains challenging due to its inter-class ambiguity and intra-class variability. Existing deep learning-based methods typically adopt convolutional neural networks and complex nonlinear projections to extract global features from entire images. However, they usually neglect some local features that may be crucial in improving classification accuracy. To this end, we propose a novel breast tumor classification method, named Attention Model Enhancement Network (AMEN), which is formulated in a multi-branch iterative fashion. In each branch, we design the flexible and adaptive attention mechanism for generating pixel-wise weights; thereafter, the inputs in the next branch are enhanced by this weight information for obtaining more discriminative features. Meanwhile, a boosting strategy is designed to fuse multi-branch classification results for better performance. Experiments conducted on three benchmark datasets demonstrate the superiority of the proposed method under various scenarios.
- 26 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 197-203
Open AccessBreast Tumor Classification With Attention Model Enhancement Network
Breast tumor classification remains challenging due to its inter-class ambiguity and intra-class variability. Existing deep learning-based methods typically adopt convolutional neural networks and complex nonlinear projections to extract global features from entire images. However, they usually neglect some local features that may be crucial in improving classification accuracy. To this end, we propose a novel breast tumor classification method, named Attention Model Enhancement Network (AMEN), which is formulated in a multi-branch iterative fashion. In each branch, we design the flexible and adaptive attention mechanism for generating pixel-wise weights; thereafter, the inputs in the next branch are enhanced by this weight information for obtaining more discriminative features. Meanwhile, a boosting strategy is designed to fuse multi-branch classification results for better performance. Experiments conducted on three benchmark datasets demonstrate the superiority of the proposed method under various scenarios.
- 23 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 26 (7) , 3240-3250
Learning Binary Semantic Embedding for Large-Scale Breast Histology Image Analysis
With the progress of clinical imaging innovation and machine learning, the computer-assisted diagnosis of breast histology images has attracted broad attention. Nonetheless, the use of computer-assisted diagnoses has been blocked due to the incomprehensibility of customary classification models. In view of this question, we propose a novel method for L earning B inary S emantic E mbedding (LBSE). In this study, bit balance and uncorrelation constraints, double supervision, discrete optimization and asymmetric pairwise similarity are seamlessly integrated for learning binary semantic-preserving embedding. Moreover, a fusion-based strategy is carefully designed to handle the intractable problem of parameter setting, saving huge amounts of time for boundary tuning. Based on the above-mentioned proficient and effective embedding, classification and retrieval are simultaneously performed to give interpretable image-based deduction and model helped conclusions for breast histology images. Extensive experiments are conducted on three benchmark datasets to approve the predominance of LBSE in different situations.
- 23 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 26 (7) , 3240-3250
Learning Binary Semantic Embedding for Large-Scale Breast Histology Image Analysis
With the progress of clinical imaging innovation and machine learning, the computer-assisted diagnosis of breast histology images has attracted broad attention. Nonetheless, the use of computer-assisted diagnoses has been blocked due to the incomprehensibility of customary classification models. In view of this question, we propose a novel method for L earning B inary S emantic E mbedding (LBSE). In this study, bit balance and uncorrelation constraints, double supervision, discrete optimization and asymmetric pairwise similarity are seamlessly integrated for learning binary semantic-preserving embedding. Moreover, a fusion-based strategy is carefully designed to handle the intractable problem of parameter setting, saving huge amounts of time for boundary tuning. Based on the above-mentioned proficient and effective embedding, classification and retrieval are simultaneously performed to give interpretable image-based deduction and model helped conclusions for breast histology images. Extensive experiments are conducted on three benchmark datasets to approve the predominance of LBSE in different situations.
- 1 November 2021
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 81
Discrete hashing with triple supervision learning
- 1 November 2021
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 81
Discrete hashing with triple supervision learning
- Open Access
- 1 January 2021
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2021 (1)
Discrete Two‐Step Cross‐Modal Hashing through the Exploitation of Pairwise Relations
The cross‐modal hashing method can map heterogeneous multimodal data into a compact binary code that preserves semantic similarity, which can significantly enhance the convenience of cross‐modal retrieval. However, the currently available supervised cross‐modal hashing methods generally only factorize the label matrix and do not fully exploit the supervised information. Furthermore, these methods often only use one‐directional mapping, which results in an unstable hash learning process. To address these problems, we propose a new supervised cross‐modal hash learning method called Discrete Two‐step Cross‐modal Hashing (DTCH) through the exploitation of pairwise relations. Specifically, this method fully exploits the pairwise similarity relations contained in the supervision information: for the label matrix, the hash learning process is stabilized by combining matrix factorization and label regression; for the pairwise similarity matrix, a semirelaxed and semidiscrete strategy is adopted to potentially reduce the cumulative quantization errors while improving the retrieval efficiency and accuracy. The approach further combines an exploration of fine‐grained features in the objective function with a novel out‐of‐sample extension strategy to enable the implicit preservation of consistency between the different modal distributions of samples and the pairwise similarity relations. The superiority of our method was verified through extensive experiments using two widely used datasets.
- 1 January 2021
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2021 (1)
Open AccessDiscrete Two‐Step Cross‐Modal Hashing through the Exploitation of Pairwise Relations
The cross‐modal hashing method can map heterogeneous multimodal data into a compact binary code that preserves semantic similarity, which can significantly enhance the convenience of cross‐modal retrieval. However, the currently available supervised cross‐modal hashing methods generally only factorize the label matrix and do not fully exploit the supervised information. Furthermore, these methods often only use one‐directional mapping, which results in an unstable hash learning process. To address these problems, we propose a new supervised cross‐modal hash learning method called Discrete Two‐step Cross‐modal Hashing (DTCH) through the exploitation of pairwise relations. Specifically, this method fully exploits the pairwise similarity relations contained in the supervision information: for the label matrix, the hash learning process is stabilized by combining matrix factorization and label regression; for the pairwise similarity matrix, a semirelaxed and semidiscrete strategy is adopted to potentially reduce the cumulative quantization errors while improving the retrieval efficiency and accuracy. The approach further combines an exploration of fine‐grained features in the objective function with a novel out‐of‐sample extension strategy to enable the implicit preservation of consistency between the different modal distributions of samples and the pairwise similarity relations. The superiority of our method was verified through extensive experiments using two widely used datasets.