Duanqing Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Duanqing Xu has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Yabo Dong
Zhejiang University, Hangzhou, China
4 shared publications - Junru Zhang
Zhejiang University
3 shared publications - Lang Feng
Zhejiang University
2 shared publications - Yuhan Wu
College of Computer Science and Technology, Zhejiang University, Hangzhou, China
2 shared publications - Zhidan Liu
Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China
2 shared publications - Cheng Peng
School of Software Technology, Zhejiang University, Hangzhou, Zhejiang, China
1 shared publication
Latest Publications
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 3764-3773
Diffusion-Guided Diversity for Single Domain Generalization in Time Series Classification
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 3764-3773
Open AccessDiffusion-Guided Diversity for Single Domain Generalization in Time Series Classification
- 21 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (10) , 10760-10777
DI2SDiff++: Activity Style Decomposition and Diffusion-Based Fusion for Cross-Person Generalization in Activity Recognition
Existing domain generalization (DG) methods for cross-person sensor-based activity recognition tasks often struggle to capture both intra- and inter-domain style diversity, leading to significant domain gaps with the target domain. In this study, we explore a novel perspective to tackle this problem, a process conceptualized as domain padding. This proposal aims to enrich the domain diversity by synthesizing intra- and inter-domain style data while maintaining robustness to class labels. We instantiate this concept using a conditional diffusion model and introduce a style-fused sampling strategy to enhance data generation diversity, termed Diversified Intra- and Inter-domain distributions via activity Style-fused Diffusion modeling (DI2SDiff). In contrast to traditional condition-guided sampling, our style-fused sampling strategy allows for the flexible use of one or more random style representations from the same class to guide data synthesis. This feature presents a notable advancement: it allows for the maximum utilization of possible combinations among existing styles to generate a broad spectrum of new style instances. We further extend DI2SDiff into DI2SDiff++ by enhancing the diversity of style guidance. Specifically, DI2SDiff++ integrates a multi-head style conditioner to provide multiple distinct, decomposed substyles and introduces a substyle-fused sampling strategy that allows cross-class substyle fusion for broader guidance. Empirical evaluations on a wide range of datasets demonstrate that our generated data achieves remarkable diversity within the domain space. Both intra- and inter-domain generated data have been proven significant and valuable, enabling DI2SDiff and DI2SDiff++ to surpass state-of-the-art DG methods in various cross-person activity recognition tasks.
- 21 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (10) , 10760-10777
DI2SDiff++: Activity Style Decomposition and Diffusion-Based Fusion for Cross-Person Generalization in Activity Recognition
Existing domain generalization (DG) methods for cross-person sensor-based activity recognition tasks often struggle to capture both intra- and inter-domain style diversity, leading to significant domain gaps with the target domain. In this study, we explore a novel perspective to tackle this problem, a process conceptualized as domain padding. This proposal aims to enrich the domain diversity by synthesizing intra- and inter-domain style data while maintaining robustness to class labels. We instantiate this concept using a conditional diffusion model and introduce a style-fused sampling strategy to enhance data generation diversity, termed Diversified Intra- and Inter-domain distributions via activity Style-fused Diffusion modeling (DI2SDiff). In contrast to traditional condition-guided sampling, our style-fused sampling strategy allows for the flexible use of one or more random style representations from the same class to guide data synthesis. This feature presents a notable advancement: it allows for the maximum utilization of possible combinations among existing styles to generate a broad spectrum of new style instances. We further extend DI2SDiff into DI2SDiff++ by enhancing the diversity of style guidance. Specifically, DI2SDiff++ integrates a multi-head style conditioner to provide multiple distinct, decomposed substyles and introduces a substyle-fused sampling strategy that allows cross-class substyle fusion for broader guidance. Empirical evaluations on a wide range of datasets demonstrate that our generated data achieves remarkable diversity within the domain space. Both intra- and inter-domain generated data have been proven significant and valuable, enabling DI2SDiff and DI2SDiff++ to surpass state-of-the-art DG methods in various cross-person activity recognition tasks.
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 4213-4222
Diverse Intra- and Inter-Domain Activity Style Fusion for Cross-Person Generalization in Activity Recognition
Existing domain generalization (DG) methods for cross-person generalization tasks often face challenges in capturing intra- and inter-domain style diversity, resulting in domain gaps with the target domain. In this study, we explore a novel perspective to tackle this problem, a process conceptualized as domain padding. This proposal aims to enrich the domain diversity by synthesizing intra- and inter-domain style data while maintaining robustness to class labels. We instantiate this concept using a conditional diffusion model and introduce a style-fused sampling strategy to enhance data generation diversity. In contrast to traditional condition-guided sampling, our style-fused sampling strategy allows for the flexible use of one or more random styles to guide data synthesis. This feature presents a notable advancement: it allows for the maximum utilization of possible permutations and combinations among existing styles to generate a broad spectrum of new style instances. Empirical evaluations on a broad range of datasets demonstrate that our generated data achieves remarkable diversity within the domain space. Both intra- and inter-domain generated data have proven to be significant and valuable, contributing to varying degrees of performance enhancements. Notably, our approach outperforms state-of-the-art DG methods in all human activity recognition tasks.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 4213-4222
Open AccessDiverse Intra- and Inter-Domain Activity Style Fusion for Cross-Person Generalization in Activity Recognition
Existing domain generalization (DG) methods for cross-person generalization tasks often face challenges in capturing intra- and inter-domain style diversity, resulting in domain gaps with the target domain. In this study, we explore a novel perspective to tackle this problem, a process conceptualized as domain padding. This proposal aims to enrich the domain diversity by synthesizing intra- and inter-domain style data while maintaining robustness to class labels. We instantiate this concept using a conditional diffusion model and introduce a style-fused sampling strategy to enhance data generation diversity. In contrast to traditional condition-guided sampling, our style-fused sampling strategy allows for the flexible use of one or more random styles to guide data synthesis. This feature presents a notable advancement: it allows for the maximum utilization of possible permutations and combinations among existing styles to generate a broad spectrum of new style instances. Empirical evaluations on a broad range of datasets demonstrate that our generated data achieves remarkable diversity within the domain space. Both intra- and inter-domain generated data have proven to be significant and valuable, contributing to varying degrees of performance enhancements. Notably, our approach outperforms state-of-the-art DG methods in all human activity recognition tasks.
- 16 February 2022
- Published by SPIE-Intl Soc Optical Eng
- p. 108
Learning structure-aware transformations for arbitrary image style transfer
Arbitrary image style transfer aims to mimic the artistic features of a randomly given style image while maintaining the semantic characters of a reference content image. Existing algorithms have achieved astonishing style transfer results. However, they are insufficient to capture the global information of the content image due to the locality in convolutional neural networks. As a result, the content structures of the stylized images are disrupted by scattered textures. To address this issue, we propose to embed additional global spatial information of the reference content image into image style transfer algorithms with the adaptive instance normalization trick. We train a light-weighted network to distill the global structural information provided by the depth map of the reference content image. We then utilize the refined results to enhance the transformations between deep features of the inputs. Experimental results show that our proposed method can generate stylized outputs with more consistent structures and less unwanted textures, achieving impressive visual effects.
- 16 February 2022
- Published by SPIE-Intl Soc Optical Eng
- p. 108
Learning structure-aware transformations for arbitrary image style transfer
Arbitrary image style transfer aims to mimic the artistic features of a randomly given style image while maintaining the semantic characters of a reference content image. Existing algorithms have achieved astonishing style transfer results. However, they are insufficient to capture the global information of the content image due to the locality in convolutional neural networks. As a result, the content structures of the stylized images are disrupted by scattered textures. To address this issue, we propose to embed additional global spatial information of the reference content image into image style transfer algorithms with the adaptive instance normalization trick. We train a light-weighted network to distill the global structural information provided by the depth map of the reference content image. We then utilize the refined results to enhance the transformations between deep features of the inputs. Experimental results show that our proposed method can generate stylized outputs with more consistent structures and less unwanted textures, achieving impressive visual effects.
- 1 October 2021
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 37 (2) , 1697-1722
Accelerating exact nearest neighbor search in high dimensional Euclidean space via block vectors
- 1 October 2021
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 37 (2) , 1697-1722
Accelerating exact nearest neighbor search in high dimensional Euclidean space via block vectors
- 21 April 2020
- Published by Springer Nature
- p. 317-327
FSIS: Fast and Seamless Image Stitching of High-Resolution Dunhuang Murals
- 21 April 2020
- Published by Springer Nature
- p. 317-327
FSIS: Fast and Seamless Image Stitching of High-Resolution Dunhuang Murals