Xiaoqing Luo
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
Xiaoqing Luo has a total of 80 co-authors. Here are the top co-authors by number of shared publications:
- Zhancheng Zhang
Suzhou University of Science and Technology, Suzhou, China
14 shared publications Zhancheng Zhang
9 shared publications- Xiao-Jun Wu
Jiangnan University
8 shared publications Xiao-Jun Wu
7 shared publications- Anqi Wang
School of Naval Architecture and Maritime, Zhejiang Ocean University, Zhoushan 316022, China
3 shared publications - Tianyang Xu
Jiangnan University
3 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 10258-10266
CRIF: Precision-Oriented Parallel Guidance for Controllable Referring Infrared and Visible Image Fusion
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 10258-10266
Open AccessCRIF: Precision-Oriented Parallel Guidance for Controllable Referring Infrared and Visible Image Fusion
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 11225-11235
Towards Robust EEG Decoding Based on Riemannian Self-Attention
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 11225-11235
Open AccessTowards Robust EEG Decoding Based on Riemannian Self-Attention
- Open Access
Wasserstein-Aligned Hyperbolic Multi-View Clustering
Multi-view clustering (MVC) aims to uncover the latent structure of multi-view data by learning view-common and view-specific information. Although recent studies have explored hyperbolic representations for better tackling the representation gap between different views, they focus primarily on instance-level alignment and neglect global semantic consistency, rendering them vulnerable to view-specific information (\textit{e.g.}, noise and cross-view discrepancies). To this end, this paper proposes a novel Wasserstein-Aligned Hyperbolic (WAH) framework for multi-view clustering. Specifically, our method exploits a view-specific hyperbolic encoder for each view to embed features into the Lorentz manifold for hierarchical semantic modeling. Whereafter, a global semantic loss based on the hyperbolic sliced-Wasserstein distance is introduced to align manifold distributions across views. This is followed by soft cluster assignments to encourage cross-view semantic consistency. Extensive experiments on multiple benchmarking datasets show that our method can achieve SOTA clustering performance.
Open AccessWasserstein-Aligned Hyperbolic Multi-View Clustering
Multi-view clustering (MVC) aims to uncover the latent structure of multi-view data by learning view-common and view-specific information. Although recent studies have explored hyperbolic representations for better tackling the representation gap between different views, they focus primarily on instance-level alignment and neglect global semantic consistency, rendering them vulnerable to view-specific information (\textit{e.g.}, noise and cross-view discrepancies). To this end, this paper proposes a novel Wasserstein-Aligned Hyperbolic (WAH) framework for multi-view clustering. Specifically, our method exploits a view-specific hyperbolic encoder for each view to embed features into the Lorentz manifold for hierarchical semantic modeling. Whereafter, a global semantic loss based on the hyperbolic sliced-Wasserstein distance is introduced to align manifold distributions across views. This is followed by soft cluster assignments to encourage cross-view semantic consistency. Extensive experiments on multiple benchmarking datasets show that our method can achieve SOTA clustering performance.
- Top Cited Papers
- 14 January 2025
- Published by Elsevier in Information Fusion
- Vol. 118
KDFuse: A high-level vision task-driven infrared and visible image fusion method based on cross-domain knowledge distillation
- 14 January 2025
- Published by Elsevier in Information Fusion
- Vol. 118
Top Cited PapersKDFuse: A high-level vision task-driven infrared and visible image fusion method based on cross-domain knowledge distillation
- 4 December 2024
- Published by Springer Nature
- p. 332-347
Learning Explicit Modulation Vectors for Disentangled Transformer Attention-Based RGB-D Visual Tracking
- 4 December 2024
- Published by Springer Nature
- p. 332-347
Learning Explicit Modulation Vectors for Disentangled Transformer Attention-Based RGB-D Visual Tracking
- 30 November 2024
- Published by Springer Nature
- p. 62-77
Infrared and Visible Image Fusion Method Based on Learnable Joint Sparse Low-Rank Decomposition
- 30 November 2024
- Published by Springer Nature
- p. 62-77
Infrared and Visible Image Fusion Method Based on Learnable Joint Sparse Low-Rank Decomposition
- Open Access
Capture Artifacts via Progressive Disentangling and Purifying Blended Identities for Deepfake Detection
The Deepfake technology has raised serious concerns regarding privacy breaches and trust issues. To tackle these challenges, Deepfake detection technology has emerged. Current methods over-rely on the global feature space, which contains redundant information independent of the artifacts. As a result, existing Deepfake detection techniques suffer performance degradation when encountering unknown datasets. To reduce information redundancy, the current methods use disentanglement techniques to roughly separate the fake faces into artifacts and content information. However, these methods lack a solid disentanglement foundation and cannot guarantee the reliability of their disentangling process. To address these issues, a Deepfake detection method based on progressive disentangling and purifying blended identities is innovatively proposed in this paper. Based on the artifact generation mechanism, the coarse- and fine-grained strategies are combined to ensure the reliability of the disentanglement method. Our method aims to more accurately capture and separate artifact features in fake faces. Specifically, we first perform the coarse-grained disentangling on fake faces to obtain a pair of blended identities that require no additional annotation to distinguish between source face and target face. Then, the artifact features from each identity are separated to achieve fine-grained disentanglement. To obtain pure identity information and artifacts, an Identity-Artifact Correlation Compression module (IACC) is designed based on the information bottleneck theory, effectively reducing the potential correlation between identity information and artifacts. Additionally, an Identity-Artifact Separation Contrast Loss is designed to enhance the independence of artifact features post-disentangling. Finally, the classifier only focuses on pure artifact features to achieve a generalized Deepfake detector.
Open AccessCapture Artifacts via Progressive Disentangling and Purifying Blended Identities for Deepfake Detection
The Deepfake technology has raised serious concerns regarding privacy breaches and trust issues. To tackle these challenges, Deepfake detection technology has emerged. Current methods over-rely on the global feature space, which contains redundant information independent of the artifacts. As a result, existing Deepfake detection techniques suffer performance degradation when encountering unknown datasets. To reduce information redundancy, the current methods use disentanglement techniques to roughly separate the fake faces into artifacts and content information. However, these methods lack a solid disentanglement foundation and cannot guarantee the reliability of their disentangling process. To address these issues, a Deepfake detection method based on progressive disentangling and purifying blended identities is innovatively proposed in this paper. Based on the artifact generation mechanism, the coarse- and fine-grained strategies are combined to ensure the reliability of the disentanglement method. Our method aims to more accurately capture and separate artifact features in fake faces. Specifically, we first perform the coarse-grained disentangling on fake faces to obtain a pair of blended identities that require no additional annotation to distinguish between source face and target face. Then, the artifact features from each identity are separated to achieve fine-grained disentanglement. To obtain pure identity information and artifacts, an Identity-Artifact Correlation Compression module (IACC) is designed based on the information bottleneck theory, effectively reducing the potential correlation between identity information and artifacts. Additionally, an Identity-Artifact Separation Contrast Loss is designed to enhance the independence of artifact features post-disentangling. Finally, the classifier only focuses on pure artifact features to achieve a generalized Deepfake detector.
- 5 August 2024
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 180, 108946
Contrastive learning based method for X-ray and CT registration under surgical equipment occlusion
- 5 August 2024
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 180, 108946
Contrastive learning based method for X-ray and CT registration under surgical equipment occlusion
- 19 June 2024
- Published by Springer Nature
- p. 107-113
Spatiotemporal Prediction of Harmful Algal Blooms Based on Spatiotemporal Attention and Transformer
- 19 June 2024
- Published by Springer Nature
- p. 107-113
Spatiotemporal Prediction of Harmful Algal Blooms Based on Spatiotemporal Attention and Transformer