Xuetao Zhang
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
Xuetao Zhang has a total of 81 co-authors. Here are the top co-authors by number of shared publications:
- Ben Yang
State Key Laboratory of HumanMachine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xian Jiaotong University, Xian, China
22 shared publications - Badong Chen
Xi’an Jiaotong University
12 shared publications Fei Wang
10 shared publications- Jinghan Wu
Xi'an Jiaotong University
10 shared publications - Feiping Nie
Northwestern Polytechnical University
8 shared publications - Zhiping Lin
Nanyang Technological University
8 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 10769-10778
Efficient Spiking Neural Networks with Autapse-Enhanced Temporal Coding?
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 10769-10778
Open AccessEfficient Spiking Neural Networks with Autapse-Enhanced Temporal Coding?
- 3 November 2026
- Published by Elsevier in Neural Networks
- Vol. 206
Unified global adaptive anchor graph learning and factorization for incomplete multi-view clustering
- 3 November 2026
- Published by Elsevier in Neural Networks
- Vol. 206
Unified global adaptive anchor graph learning and factorization for incomplete multi-view clustering
- 27 February 2026
- Published by Elsevier in Neurocomputing
- Vol. 678
Efficient superpixel-guided global-local spectral clustering for large-scale HSI
- 27 February 2026
- Published by Elsevier in Neurocomputing
- Vol. 678
Efficient superpixel-guided global-local spectral clustering for large-scale HSI
- Top Cited Papers
- 15 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 3768-3780
One-Step Multi-View Clustering With Adaptive Low-Rank Anchor-Graph Learning
In light of their capability to capture structural information while reducing computing complexity, anchor graph-based multi-view clustering (AGMC) methods have attracted considerable attention in large-scale clustering problems. Nevertheless, existing AGMC methods still face the following two issues: 1) They directly embedded diverse anchor graphs into a consensus anchor graph (CAG), and hence ignore redundant information and numerous noises contained in these anchor graphs, leading to a decrease in clustering effectiveness; 2) They drop effectiveness and efficiency due to independent post-processing to acquire clustering indicators. To overcome the aforementioned issues, we deliver a novel one-step multi-view clustering method with adaptive low-rank anchor-graph learning (OMCAL). To construct a high-quality CAG, OMCAL provides a nuclear norm-based adaptive CAG learning model against information redundancy and noise interference. Then, to boost clustering effectiveness and efficiency substantially, we incorporate category indicator acquisition and CAG learning into a unified framework. Numerous studies conducted on ordinary and large-scale datasets indicate that OMCAL outperforms existing state-of-the-art methods in terms of clustering effectiveness and efficiency.
- 15 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 3768-3780
Top Cited PapersOne-Step Multi-View Clustering With Adaptive Low-Rank Anchor-Graph Learning
In light of their capability to capture structural information while reducing computing complexity, anchor graph-based multi-view clustering (AGMC) methods have attracted considerable attention in large-scale clustering problems. Nevertheless, existing AGMC methods still face the following two issues: 1) They directly embedded diverse anchor graphs into a consensus anchor graph (CAG), and hence ignore redundant information and numerous noises contained in these anchor graphs, leading to a decrease in clustering effectiveness; 2) They drop effectiveness and efficiency due to independent post-processing to acquire clustering indicators. To overcome the aforementioned issues, we deliver a novel one-step multi-view clustering method with adaptive low-rank anchor-graph learning (OMCAL). To construct a high-quality CAG, OMCAL provides a nuclear norm-based adaptive CAG learning model against information redundancy and noise interference. Then, to boost clustering effectiveness and efficiency substantially, we incorporate category indicator acquisition and CAG learning into a unified framework. Numerous studies conducted on ordinary and large-scale datasets indicate that OMCAL outperforms existing state-of-the-art methods in terms of clustering effectiveness and efficiency.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 13936-13948
Plug-and-Adapt: Multimodal Coreference Resolution at First Sight With a Pretrained Alignment Model
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 13936-13948
Plug-and-Adapt: Multimodal Coreference Resolution at First Sight With a Pretrained Alignment Model
- 31 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (5) , 5095-5112
Fast Multi-view Discrete Clustering via Spectral Embedding Fusion
Multi-view spectral clustering (MVSC) has garnered growing interest across various real-world applications, owing to its flexibility in managing diverse data space structures. Nevertheless, the fusion of multiple$n\times n$ similarity matrices and the separate post-discretization process hinder the utilization of MVSC in large-scale tasks, where$n$ denotes the number of samples. Moreover, noise in different similarity matrices, along with the two-stage mismatch caused by the post-discretization, results in a reduction in clustering effectiveness. To overcome these challenges, we establish a novel fast multi-view discrete clustering (FMVDC) model via spectral embedding fusion, which integrates spectral embedding matrices ($n\times c$ ,$c\ll n$ ) to directly obtain discrete sample categories, where$c$ indicates the number of clusters, bypassing the need for both similarity matrix fusion and post-discretization. To further enhance clustering efficiency, we employ an anchor-based spectral embedding strategy to decrease the computational complexity of spectral analysis from cubic to linear. Since gradient descent methods are incapable of discrete models, we propose a fast optimization strategy based on the coordinate descent method to solve the FMVDC model efficiently. Extensive studies demonstrate that FMVDC significantly improves clustering performance compared to existing state-of-the-art methods, particularly in large-scale clustering tasks.- 31 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (5) , 5095-5112
Fast Multi-view Discrete Clustering via Spectral Embedding Fusion
Multi-view spectral clustering (MVSC) has garnered growing interest across various real-world applications, owing to its flexibility in managing diverse data space structures. Nevertheless, the fusion of multiple$n\times n$ similarity matrices and the separate post-discretization process hinder the utilization of MVSC in large-scale tasks, where$n$ denotes the number of samples. Moreover, noise in different similarity matrices, along with the two-stage mismatch caused by the post-discretization, results in a reduction in clustering effectiveness. To overcome these challenges, we establish a novel fast multi-view discrete clustering (FMVDC) model via spectral embedding fusion, which integrates spectral embedding matrices ($n\times c$ ,$c\ll n$ ) to directly obtain discrete sample categories, where$c$ indicates the number of clusters, bypassing the need for both similarity matrix fusion and post-discretization. To further enhance clustering efficiency, we employ an anchor-based spectral embedding strategy to decrease the computational complexity of spectral analysis from cubic to linear. Since gradient descent methods are incapable of discrete models, we propose a fast optimization strategy based on the coordinate descent method to solve the FMVDC model efficiently. Extensive studies demonstrate that FMVDC significantly improves clustering performance compared to existing state-of-the-art methods, particularly in large-scale clustering tasks.- 14 November 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Neural Systems
- Vol. 36 (01) , 2592001
ERRATUM — Multi-Layer Feature Cascade Fusion Spiking Neural Network for Object Detection
- 14 November 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Neural Systems
- Vol. 36 (01) , 2592001
ERRATUM — Multi-Layer Feature Cascade Fusion Spiking Neural Network for Object Detection
- 20 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (4) , 4814-4826
Momentum Centroid Alignment With Temporal-Relational Disentanglement for Cross-Domain Few-Shot Action Recognition
Traditional few-shot action recognition (FSAR) aims to address the problem of the scarcity of action videos, enabling the recognition of action categories with just a few labeled samples. It is generally believed that the samples in the meta-training phase and the meta-testing phase are all drawn from the same domain. However, in practical applications, they often come from different domains, which may lead to significant differences in the distribution of spatiotemporal features. Researchers have started to study the problem of cross-domain few-shot action recognition (CDFSAR). The current solution is to train the model by combining source domain video and unlabeled target domain video to improve the model’s generalization ability. In this paper, we follow this paradigm but make a more refined use of the unlabeled target domain videos to better extract transferable features. First, we decouple the source and target domain videos along the temporal dimension and extract the domain-irrelevant features in both the source and target domains. Second, in each episode, we calculate the centroid of the domain-irrelevant features of the target domain and perform a momentum update on this feature centroid. We use Cross-Attention to align the domain-irrelevant features of the source domain toward this dynamic centroid. Finally, we use these aligned source domain features for few-shot classification. Experimental results demonstrate that our approach significantly improves few-shot classification performance across diverse domain shifts, validating the effectiveness of our refined use of unlabeled target video. Our code has been published at the URL: https://github.com/cofly2014/MCA-TRD.git.
- 20 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (4) , 4814-4826
Momentum Centroid Alignment With Temporal-Relational Disentanglement for Cross-Domain Few-Shot Action Recognition
Traditional few-shot action recognition (FSAR) aims to address the problem of the scarcity of action videos, enabling the recognition of action categories with just a few labeled samples. It is generally believed that the samples in the meta-training phase and the meta-testing phase are all drawn from the same domain. However, in practical applications, they often come from different domains, which may lead to significant differences in the distribution of spatiotemporal features. Researchers have started to study the problem of cross-domain few-shot action recognition (CDFSAR). The current solution is to train the model by combining source domain video and unlabeled target domain video to improve the model’s generalization ability. In this paper, we follow this paradigm but make a more refined use of the unlabeled target domain videos to better extract transferable features. First, we decouple the source and target domain videos along the temporal dimension and extract the domain-irrelevant features in both the source and target domains. Second, in each episode, we calculate the centroid of the domain-irrelevant features of the target domain and perform a momentum update on this feature centroid. We use Cross-Attention to align the domain-irrelevant features of the source domain toward this dynamic centroid. Finally, we use these aligned source domain features for few-shot classification. Experimental results demonstrate that our approach significantly improves few-shot classification performance across diverse domain shifts, validating the effectiveness of our refined use of unlabeled target video. Our code has been published at the URL: https://github.com/cofly2014/MCA-TRD.git.
- Open Access
One-step Multi-view Clustering With Adaptive Low-rank Anchor-graph Learning
In light of their capability to capture structural information while reducing computing complexity, anchor graph-based multi-view clustering (AGMC) methods have attracted considerable attention in large-scale clustering problems. Nevertheless, existing AGMC methods still face the following two issues: 1) They directly embedded diverse anchor graphs into a consensus anchor graph (CAG), and hence ignore redundant information and numerous noises contained in these anchor graphs, leading to a decrease in clustering effectiveness; 2) They drop effectiveness and efficiency due to independent post-processing to acquire clustering indicators. To overcome the aforementioned issues, we deliver a novel one-step multi-view clustering method with adaptive low-rank anchor-graph learning (OMCAL). To construct a high-quality CAG, OMCAL provides a nuclear norm-based adaptive CAG learning model against information redundancy and noise interference. Then, to boost clustering effectiveness and efficiency substantially, we incorporate category indicator acquisition and CAG learning into a unified framework. Numerous studies conducted on ordinary and large-scale datasets indicate that OMCAL outperforms existing state-of-the-art methods in terms of clustering effectiveness and efficiency.
Open AccessOne-step Multi-view Clustering With Adaptive Low-rank Anchor-graph Learning
In light of their capability to capture structural information while reducing computing complexity, anchor graph-based multi-view clustering (AGMC) methods have attracted considerable attention in large-scale clustering problems. Nevertheless, existing AGMC methods still face the following two issues: 1) They directly embedded diverse anchor graphs into a consensus anchor graph (CAG), and hence ignore redundant information and numerous noises contained in these anchor graphs, leading to a decrease in clustering effectiveness; 2) They drop effectiveness and efficiency due to independent post-processing to acquire clustering indicators. To overcome the aforementioned issues, we deliver a novel one-step multi-view clustering method with adaptive low-rank anchor-graph learning (OMCAL). To construct a high-quality CAG, OMCAL provides a nuclear norm-based adaptive CAG learning model against information redundancy and noise interference. Then, to boost clustering effectiveness and efficiency substantially, we incorporate category indicator acquisition and CAG learning into a unified framework. Numerous studies conducted on ordinary and large-scale datasets indicate that OMCAL outperforms existing state-of-the-art methods in terms of clustering effectiveness and efficiency.
- 15 September 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Neural Systems
- Vol. 35 (11) , 2550063
Multi-layer Feature Cascade Fusion Spiking Neural Network for Object Detection
Spiking Neural Networks (SNNs), as a biologically inspired computational model, have garnered significant attention in object detection and image classification due to their event-driven mechanism and low-power characteristics. However, in object detection tasks, the residual structures in conventional networks introduce nonspiking operations, posing a critical challenge for SNNs. To address this issue, we propose a multi-layer feature cascade fusion SNN (MFCF-SNN) for object detection. During feature extraction, our novel multi-level cascaded feature extraction module replaces residual connections with cascade operations, eliminating nonspiking computations while enhancing gradient propagation to deeper layers. For downsampling, we introduce a pooling-convolution module that combines max-pooling and spiking convolution, effectively preserving feature information and improving gradient flow. These two modules collectively ensure pure spike-based computation while facilitating deep network training, thereby enhancing detection accuracy. Experimental results on the PASCAL VOC 2012 and SSDD datasets demonstrate state-of-the-art performance, validating the effectiveness of our approach in advancing SNN-based object detection.
- 15 September 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Neural Systems
- Vol. 35 (11) , 2550063
Multi-layer Feature Cascade Fusion Spiking Neural Network for Object Detection
Spiking Neural Networks (SNNs), as a biologically inspired computational model, have garnered significant attention in object detection and image classification due to their event-driven mechanism and low-power characteristics. However, in object detection tasks, the residual structures in conventional networks introduce nonspiking operations, posing a critical challenge for SNNs. To address this issue, we propose a multi-layer feature cascade fusion SNN (MFCF-SNN) for object detection. During feature extraction, our novel multi-level cascaded feature extraction module replaces residual connections with cascade operations, eliminating nonspiking computations while enhancing gradient propagation to deeper layers. For downsampling, we introduce a pooling-convolution module that combines max-pooling and spiking convolution, effectively preserving feature information and improving gradient flow. These two modules collectively ensure pure spike-based computation while facilitating deep network training, thereby enhancing detection accuracy. Experimental results on the PASCAL VOC 2012 and SSDD datasets demonstrate state-of-the-art performance, validating the effectiveness of our approach in advancing SNN-based object detection.