Di Wang
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
Di Wang has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Guanghua Yang
School of Intelligent Systems Science and Engineering and the GBA and BR International Joint Research Center for Smart Logistics, Jinan University, Zhuhai, China
4 shared publications - Xu Wang
Jinan University, Zhuhai, China
4 shared publications - Zheng Shi
School of Intelligent Systems Science and Engineering, Jinan University, Zhuhai, China
4 shared publications - Haozhi Huang
Jinan University, Zhuhai, China
2 shared publications - Jiayu Chen
Tsinghua University
2 shared publications - Jintao Wang
State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 175-184
VCAR: Training-Free 3DGS Segmentation via View Completeness and Axis-Aware Boundary Refinement
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 175-184
Open AccessVCAR: Training-Free 3DGS Segmentation via View Completeness and Axis-Aware Boundary Refinement
- 6 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (8) , 17032-17047
Semantic HARQ: Joint Source–Channel Coding-Powered Reliable Retransmissions for IoT Networks
The rapid expansion of Internet of Things (IoT) devices places growing pressure on limited spectrum resources. Semantic communication offers a promising solution by transmitting only the essential meaning of data, thereby reducing redundancy. However, the dynamic and heterogeneous nature of IoT environments leads to fluctuating channel conditions that can degrade semantic reliability. To address this challenge, we propose semantic Hybrid Automatic Repeat reQuest (sem-HARQ), a framework that integrates Hybrid Automatic Repeat reQuest (HARQ) with Joint Source–Channel Coding (JSCC) to enable reliable semantic transmission. To mitigate the adverse effects of multipath fading and noise, we introduce a semantic equalizer module that leverages conditional generative modeling to correct semantic distortions. Furthermore, three sem-HARQ schemes are developed: sem-HARQ-I, sem-HARQ with Weighted Combining (sem-HARQ-WC), and sem-HARQ with Synonymous Combining (sem-HARQ-SC). While sem-HARQ-I and sem-HARQ-WC retransmit the same semantic signals, sem-HARQ-SC introduces new semantic redundancies via synonymous mapping across HARQ rounds. At the receiver, sem-HARQ-WC and sem-HARQ-SC enhance reliability by fusing current and previous semantic features, effectively reusing information from prior erroneous transmissions. Simulation results demonstrate that the proposed sem-HARQ framework significantly improves semantic reliability compared to no-HARQ baselines. Among the three designs, sem-HARQ-SC achieves the best performance, albeit with higher complexity, while sem-HARQ-I provides the simplest but least effective solution.
- 6 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (8) , 17032-17047
Semantic HARQ: Joint Source–Channel Coding-Powered Reliable Retransmissions for IoT Networks
The rapid expansion of Internet of Things (IoT) devices places growing pressure on limited spectrum resources. Semantic communication offers a promising solution by transmitting only the essential meaning of data, thereby reducing redundancy. However, the dynamic and heterogeneous nature of IoT environments leads to fluctuating channel conditions that can degrade semantic reliability. To address this challenge, we propose semantic Hybrid Automatic Repeat reQuest (sem-HARQ), a framework that integrates Hybrid Automatic Repeat reQuest (HARQ) with Joint Source–Channel Coding (JSCC) to enable reliable semantic transmission. To mitigate the adverse effects of multipath fading and noise, we introduce a semantic equalizer module that leverages conditional generative modeling to correct semantic distortions. Furthermore, three sem-HARQ schemes are developed: sem-HARQ-I, sem-HARQ with Weighted Combining (sem-HARQ-WC), and sem-HARQ with Synonymous Combining (sem-HARQ-SC). While sem-HARQ-I and sem-HARQ-WC retransmit the same semantic signals, sem-HARQ-SC introduces new semantic redundancies via synonymous mapping across HARQ rounds. At the receiver, sem-HARQ-WC and sem-HARQ-SC enhance reliability by fusing current and previous semantic features, effectively reusing information from prior erroneous transmissions. Simulation results demonstrate that the proposed sem-HARQ framework significantly improves semantic reliability compared to no-HARQ baselines. Among the three designs, sem-HARQ-SC achieves the best performance, albeit with higher complexity, while sem-HARQ-I provides the simplest but least effective solution.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15, 6228-6232
Robust Discrete Semantic Low-Altitude Communications With Learnable Codebook Transformation
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15, 6228-6232
Robust Discrete Semantic Low-Altitude Communications With Learnable Codebook Transformation
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 30, 3493-3497
Secure Semantic Communications With Information-Theoretic Honeypoints
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 30, 3493-3497
Secure Semantic Communications With Information-Theoretic Honeypoints
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33, 2974-2978
FS-DICP: A Fast and Simple Point-to-Point Iterative Closest Point Algorithm With Doppler Velocity
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33, 2974-2978
FS-DICP: A Fast and Simple Point-to-Point Iterative Closest Point Algorithm With Doppler Velocity
- 23 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (1) , 184-191
Self-Supervised Point Cloud Understanding via Mask Transformer and Contrastive Learning
Self-supervised point cloud understanding can pre-train the point cloud learning network on a large dataset, which helps boost the performance of fine-tuning on other smaller datasets in downstream tasks. Motivated to design an efficient self-supervised pre-training strategy and capture useful and discriminative representations of the 3D point cloud, we propose ContrastMPCT, a self-reconstruction scheme with the contrastive learning principle. Specifically, two contrastive loss functions are designed for 3D point clouds to maximize the dependence between the input tokens and output tokens of the encoder and fasten the convergence of the model. Extensive experiments show that our pre-training strategy of ContrastMPCT can effectively improve the fine-tuning performance on the downstream tasks, including object classification and part segmentation. Moreover, compared with both CNN-based and Transformer-based existing works, the superior results indicate the efficacy of the proposed method.
- 23 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (1) , 184-191
Self-Supervised Point Cloud Understanding via Mask Transformer and Contrastive Learning
Self-supervised point cloud understanding can pre-train the point cloud learning network on a large dataset, which helps boost the performance of fine-tuning on other smaller datasets in downstream tasks. Motivated to design an efficient self-supervised pre-training strategy and capture useful and discriminative representations of the 3D point cloud, we propose ContrastMPCT, a self-reconstruction scheme with the contrastive learning principle. Specifically, two contrastive loss functions are designed for 3D point clouds to maximize the dependence between the input tokens and output tokens of the encoder and fasten the convergence of the model. Extensive experiments show that our pre-training strategy of ContrastMPCT can effectively improve the fine-tuning performance on the downstream tasks, including object classification and part segmentation. Moreover, compared with both CNN-based and Transformer-based existing works, the superior results indicate the efficacy of the proposed method.
- 8 July 2022
- Published by Elsevier in Pattern Recognition
- Vol. 131
Improving deep learning on point cloud by maximizing mutual information across layers
- 8 July 2022
- Published by Elsevier in Pattern Recognition
- Vol. 131
Improving deep learning on point cloud by maximizing mutual information across layers
- 24 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 29 (10709908) , 1217-1221
Mutual Information Maximization Based Similarity Operation for 3D Point Cloud Completion Network
Reconstructing the incomplete point cloud into the complete and uniform one is a fundamental task in 3D point cloud processing. Some existing studies have explored the use of deep learning networks and representation learning to implement point cloud completion, but the completed shapes still appear unrealistic and non-uniform. To address this issue, we propose the idea of simulating the process of point cloud completion with local-to-global reasoning (LGR). Motivated to achieve the fine LGR, a novel mutual information (MI) maximization-based similarity operation is proposed, which realizes the reconstruction from incomplete point cloud to complete one by maximizing MI between global features and the prior features from the same 3D object. We adopt the Jenson-Shannon MI estimator to maximize the MI between global features and the priors in specific dimensions, which effectively increases the similarity of global and prior features. Compared with other existing works and similarity operations, the superior results indicate the efficacy of the proposed method and its advantages over existing ones in both the synthetic and real-world datasets. Our source code is available at https://github.com/wendydidi/MISO-PCN .
- 24 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 29 (10709908) , 1217-1221
Mutual Information Maximization Based Similarity Operation for 3D Point Cloud Completion Network
Reconstructing the incomplete point cloud into the complete and uniform one is a fundamental task in 3D point cloud processing. Some existing studies have explored the use of deep learning networks and representation learning to implement point cloud completion, but the completed shapes still appear unrealistic and non-uniform. To address this issue, we propose the idea of simulating the process of point cloud completion with local-to-global reasoning (LGR). Motivated to achieve the fine LGR, a novel mutual information (MI) maximization-based similarity operation is proposed, which realizes the reconstruction from incomplete point cloud to complete one by maximizing MI between global features and the prior features from the same 3D object. We adopt the Jenson-Shannon MI estimator to maximize the MI between global features and the priors in specific dimensions, which effectively increases the similarity of global and prior features. Compared with other existing works and similarity operations, the superior results indicate the efficacy of the proposed method and its advantages over existing ones in both the synthetic and real-world datasets. Our source code is available at https://github.com/wendydidi/MISO-PCN .
- 1 April 2019
- Published by Elsevier in Automation in Construction
- Vol. 100, 11-23
Detecting and measuring construction workers' vigilance through hybrid kinematic-EEG signals
- 1 April 2019
- Published by Elsevier in Automation in Construction
- Vol. 100, 11-23
Detecting and measuring construction workers' vigilance through hybrid kinematic-EEG signals
- 1 October 2017
- Published by Elsevier in Automation in Construction
- Vol. 82, 122-137
Monitoring workers' attention and vigilance in construction activities through a wireless and wearable electroencephalography system
- 1 October 2017
- Published by Elsevier in Automation in Construction
- Vol. 82, 122-137
Monitoring workers' attention and vigilance in construction activities through a wireless and wearable electroencephalography system