Duantengchuan Li
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
Duantengchuan Li has a total of 118 co-authors. Here are the top co-authors by number of shared publications:
Bing Li
7 shared publications- Bing Li
School of Computer Science Wuhan University Wuhan China
6 shared publications Xiaoguang Wang
6 shared publications- Jian Wang
School of Computer Science, Wuhan University, China
5 shared publications - Ke Lin
Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China
5 shared publications Jian Wang
4 shared publications
Latest Publications
- 8 October 2026
- Published by Elsevier in Pattern Recognition
- Vol. 183
Beyond topology-driven graph convolution: Node patch convolutional network for node representation learning
- 8 October 2026
- Published by Elsevier in Pattern Recognition
- Vol. 183
Beyond topology-driven graph convolution: Node patch convolutional network for node representation learning
- 18 August 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 203
Dual token mixing-based graph transformer for semi-supervised node classification in attributed networks
- 18 August 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 203
Dual token mixing-based graph transformer for semi-supervised node classification in attributed networks
- 25 June 2026
- Published by Elsevier in Automation in Construction
- Vol. 190
Comprehensive benchmark of large language models for construction engineering and management
- 25 June 2026
- Published by Elsevier in Automation in Construction
- Vol. 190
Comprehensive benchmark of large language models for construction engineering and management
- 30 May 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 201
Integrating exercise complexity and learner capability representation for knowledge tracing
- 30 May 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 201
Integrating exercise complexity and learner capability representation for knowledge tracing
- 21 April 2026
- Published by Elsevier in Pattern Recognition
- Vol. 179
Multiple myeloma cell segmentation based on position prior information guidance in medical imaging
- 21 April 2026
- Published by Elsevier in Pattern Recognition
- Vol. 179
Multiple myeloma cell segmentation based on position prior information guidance in medical imaging
- Open Access
- 2 March 2026
- Published by MDPI AG in Information
- Vol. 17 (3) , 246
Facial Expression Recognition Integrating Multi-Stage Feature Sparse Constraints and Key Region Graph Learning
Current Facial expression recognition methods typically extract facial features indiscriminately, incorporating expression-irrelevant information that compromises recognition accuracy. To overcome this, we propose Multi-stage Feature Sparse Constraints (MFSC), a novel model that integrates a Multi-scale Attention-based Sparse Window Selection (MSAWS) mechanism with key region graph learning. Notably, MFSC operates without dependence on pre-extracted facial landmarks, enabling more flexible deployment. The MSAWS mechanism progressively filters redundant features through multi-stage sparse attention, adaptively selecting the most discriminative facial patches. The selected tokens are structured into a dynamic graph to model regional relationships via graph neural networks (GNNs). Critically, our framework further introduces a global-guided fusion module, which effectively integrates fine-grained local features from an IR50 backbone with the global topological features from the GNN through cross-attention. This integration enables complementary strengths, where local details are enhanced by global semantic context. Comprehensive experiments on RAF-DB, FER2013, and AffectNet-7 datasets demonstrate MFSC’s superior performance, achieving state-of-the-art accuracy of 92.31%, 76.21%, and 67.35%, respectively. These results validate the effectiveness of our approach in focusing computational resources on expression-salient regions while maintaining a lightweight and efficient architecture.
- 2 March 2026
- Published by MDPI AG in Information
- Vol. 17 (3) , 246
Open AccessFacial Expression Recognition Integrating Multi-Stage Feature Sparse Constraints and Key Region Graph Learning
Current Facial expression recognition methods typically extract facial features indiscriminately, incorporating expression-irrelevant information that compromises recognition accuracy. To overcome this, we propose Multi-stage Feature Sparse Constraints (MFSC), a novel model that integrates a Multi-scale Attention-based Sparse Window Selection (MSAWS) mechanism with key region graph learning. Notably, MFSC operates without dependence on pre-extracted facial landmarks, enabling more flexible deployment. The MSAWS mechanism progressively filters redundant features through multi-stage sparse attention, adaptively selecting the most discriminative facial patches. The selected tokens are structured into a dynamic graph to model regional relationships via graph neural networks (GNNs). Critically, our framework further introduces a global-guided fusion module, which effectively integrates fine-grained local features from an IR50 backbone with the global topological features from the GNN through cross-attention. This integration enables complementary strengths, where local details are enhanced by global semantic context. Comprehensive experiments on RAF-DB, FER2013, and AffectNet-7 datasets demonstrate MFSC’s superior performance, achieving state-of-the-art accuracy of 92.31%, 76.21%, and 67.35%, respectively. These results validate the effectiveness of our approach in focusing computational resources on expression-salient regions while maintaining a lightweight and efficient architecture.
- Open Access
- 25 February 2026
- Published by MDPI AG in Information
- Vol. 17 (3) , 224
Landmark-Guided Gaze Estimation via Conditional Keypoint Generation and Cross-Attention Fusion
In gaze estimation, existing mainstream methods face significant challenges in capturing the fine-grained structures of eye regions, particularly in the absence of explicit geometric prior information, which hampers gaze prediction accuracy. To address this limitation, we propose the landmark-guided gaze estimation network (LGNet), a gaze estimation method guided by keypoints, which effectively incorporates geometric prior information to enhance estimation performance. The proposed method begins by training an eye-keypoint generator on the synthetic UnityEyes dataset using a Conditional Variational Autoencoder (CVAE). Next, we introduce a Symmetric Spatial Feature Fusion module (SSFF), combined with a dual-stream cross-attention mechanism, to achieve semantic alignment between the keypoint features and the facial image features extracted using ResNet50. Furthermore, we propose a Gated Channel Reweighting module (GCR) to suppress redundant information and amplify the critical features, thereby enhancing the model’s overall response. Experimental results demonstrate that LGNet outperforms existing methods on three benchmark datasets. The code for this research has been made publicly available.
- 25 February 2026
- Published by MDPI AG in Information
- Vol. 17 (3) , 224
Open AccessLandmark-Guided Gaze Estimation via Conditional Keypoint Generation and Cross-Attention Fusion
In gaze estimation, existing mainstream methods face significant challenges in capturing the fine-grained structures of eye regions, particularly in the absence of explicit geometric prior information, which hampers gaze prediction accuracy. To address this limitation, we propose the landmark-guided gaze estimation network (LGNet), a gaze estimation method guided by keypoints, which effectively incorporates geometric prior information to enhance estimation performance. The proposed method begins by training an eye-keypoint generator on the synthetic UnityEyes dataset using a Conditional Variational Autoencoder (CVAE). Next, we introduce a Symmetric Spatial Feature Fusion module (SSFF), combined with a dual-stream cross-attention mechanism, to achieve semantic alignment between the keypoint features and the facial image features extracted using ResNet50. Furthermore, we propose a Gated Channel Reweighting module (GCR) to suppress redundant information and amplify the critical features, thereby enhancing the model’s overall response. Experimental results demonstrate that LGNet outperforms existing methods on three benchmark datasets. The code for this research has been made publicly available.
- 7 February 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 338
Integrating deep clustering and multi-view graph neural networks for recommender system
- 7 February 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 338
Integrating deep clustering and multi-view graph neural networks for recommender system
- 19 January 2026
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 273
Travel time resilience of national multimodal transport systems under extreme events: A passenger-oriented framework
- 19 January 2026
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 273
Travel time resilience of national multimodal transport systems under extreme events: A passenger-oriented framework