Hongze Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hongze Sun has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Daqing Guo
Clinical Hospital of Chengdu Brain Science Institute, MOE-K Lab for NeuroInformation, Brain-Apparatus Communication Institute, University of Electronic Science and Technology of China, Chengdu, China
5 shared publications - Dezhong Yao
Clinical Hospital of Chengdu Brain Science Institute, MOE-K Lab for NeuroInformation, Brain-Apparatus Communication Institute, University of Electronic Science and Technology of China, Chengdu, China
4 shared publications - Wuque Cai
Clinical Hospital of Chengdu Brain Science Institute, MOE-K Lab for NeuroInformation, Int Institute of Brain-Apparatus Communication, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 611731, China
4 shared publications - Duo Chen
University of Electronic Science and Technology of China
3 shared publications - Qianqian Liao
Clinical Hospital of Chengdu Brain Science Institute, MOE-K Lab for NeuroInformation, Int Institute of Brain-Apparatus Communication, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 611731, China
2 shared publications Baoxin Yang
The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for NeuroInformation, China-Cuba Belt and Road Joint Laboratory on Neurotechnology and Brain-Apparatus Communication, School of Life Science and Technology, University of Electronic Science and Technology of China
1 shared publication
Latest Publications
- 29 December 2025
- Published by Elsevier in Neural Networks
- Vol. 197, 108526
A brain-to-population graph learning framework for diagnosing brain disorders
- 29 December 2025
- Published by Elsevier in Neural Networks
- Vol. 197, 108526
A brain-to-population graph learning framework for diagnosing brain disorders
- 11 December 2025
- Published by Elsevier in Neural Networks
- Vol. 197, 108417
NSPDI-SNN: An efficient lightweight SNN based on nonlinear synaptic pruning and dendritic integration
- 11 December 2025
- Published by Elsevier in Neural Networks
- Vol. 197, 108417
NSPDI-SNN: An efficient lightweight SNN based on nonlinear synaptic pruning and dendritic integration
- 21 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 7109-7124
Manifold Embedding for Fast and Accurate 3D Reconstruction
The goal of the fusion process in RGB-D reconstruction systems is to verify and update the 3D model while ensuring both completeness and accuracy. However, achieving precise dense correspondences in a point-to-point or pixel model during this process is challenging and computationally intensive. To address this challenge, we propose a Manifold Embedding framework that facilitates rapid point-to-surface fusion, removing the need for direct point-to-point or pixel correspondences. Our approach consists of three main steps: 1) Manifold Voxel: We transform discrete point sets into smooth surfaces using the Implicit Moving Least Squares (IMLS) method; 2) Two-Step Filtering: We enhance reconstruction accuracy through a two-step filtering technique that evaluates sampling points based on probabilistic measures; 3) Embedding for Smooth Surface: Lastly, we embed points into a smooth manifold surface represented via IMLS, ensuring high-quality reconstructed surfaces. Extensive experiments on both real and synthetic 3D scenes demonstrate the effectiveness of our Manifold Embedding framework. For instance, on the public Replica dataset, our method surpasses state-of-the-art fusion techniques regarding both completeness and accuracy. Our average accuracy is 2.11 cm and completeness is 2.80 cm, while NICE-SLAM achieves 2.85 cm and 3.00 cm, respectively (with lower values indicating better performance). Overall, our proposed method provides superior reconstruction quality and enhanced computational efficiency (See Fig. 1).
- 21 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 7109-7124
Manifold Embedding for Fast and Accurate 3D Reconstruction
The goal of the fusion process in RGB-D reconstruction systems is to verify and update the 3D model while ensuring both completeness and accuracy. However, achieving precise dense correspondences in a point-to-point or pixel model during this process is challenging and computationally intensive. To address this challenge, we propose a Manifold Embedding framework that facilitates rapid point-to-surface fusion, removing the need for direct point-to-point or pixel correspondences. Our approach consists of three main steps: 1) Manifold Voxel: We transform discrete point sets into smooth surfaces using the Implicit Moving Least Squares (IMLS) method; 2) Two-Step Filtering: We enhance reconstruction accuracy through a two-step filtering technique that evaluates sampling points based on probabilistic measures; 3) Embedding for Smooth Surface: Lastly, we embed points into a smooth manifold surface represented via IMLS, ensuring high-quality reconstructed surfaces. Extensive experiments on both real and synthetic 3D scenes demonstrate the effectiveness of our Manifold Embedding framework. For instance, on the public Replica dataset, our method surpasses state-of-the-art fusion techniques regarding both completeness and accuracy. Our average accuracy is 2.11 cm and completeness is 2.80 cm, while NICE-SLAM achieves 2.85 cm and 3.00 cm, respectively (with lower values indicating better performance). Overall, our proposed method provides superior reconstruction quality and enhanced computational efficiency (See Fig. 1).
- 4 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (10) , 18995-19009
Robust Spatiotemporal Prototype Learning for Spiking Neural Networks
Spiking neural networks (SNNs) leverage their spike-driven nature to achieve high energy efficiency, positioning them as a promising alternative to traditional artificial neural networks (ANNs). The spiking decoder, a crucial component for output, significantly affects the performance of SNNs. However, current rate coding schemes for decoding of SNNs often lack robustness and do not have a training framework suitable for robust learning, while alternatives to rate coding generally produce worse overall performance. To address these challenges, we propose spatiotemporal prototype (STP) learning for SNNs, which uses multiple learnable binarized prototypes for distance-based decoding. In addition, we introduce a cotraining framework that jointly optimizes prototypes and model parameters, enabling mutual adaptation of the two components. STP learning clusters feature centers through supervised learning to ensure effective aggregation around the prototypes, while maintaining enough spacing between prototypes to handle noise and interference. This dual capability results in superior stability and robustness. On eight benchmark datasets with diverse challenges, the STP-SNN model achieves performance comparable to or superior to state-of-the-art methods. Notably, STP learning demonstrates exceptional robustness and stability in multitask experiments. Overall, these findings reveal that STP learning is an effective means of improving the performance and robustness of SNNs.
- 4 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (10) , 18995-19009
Robust Spatiotemporal Prototype Learning for Spiking Neural Networks
Spiking neural networks (SNNs) leverage their spike-driven nature to achieve high energy efficiency, positioning them as a promising alternative to traditional artificial neural networks (ANNs). The spiking decoder, a crucial component for output, significantly affects the performance of SNNs. However, current rate coding schemes for decoding of SNNs often lack robustness and do not have a training framework suitable for robust learning, while alternatives to rate coding generally produce worse overall performance. To address these challenges, we propose spatiotemporal prototype (STP) learning for SNNs, which uses multiple learnable binarized prototypes for distance-based decoding. In addition, we introduce a cotraining framework that jointly optimizes prototypes and model parameters, enabling mutual adaptation of the two components. STP learning clusters feature centers through supervised learning to ensure effective aggregation around the prototypes, while maintaining enough spacing between prototypes to handle noise and interference. This dual capability results in superior stability and robustness. On eight benchmark datasets with diverse challenges, the STP-SNN model achieves performance comparable to or superior to state-of-the-art methods. Notably, STP learning demonstrates exceptional robustness and stability in multitask experiments. Overall, these findings reveal that STP learning is an effective means of improving the performance and robustness of SNNs.
- Open Access
- 27 February 2025
- Published by Taylor & Francis in Brain-Apparatus Communication: A Journal of Bacomics
- Vol. 4 (1)
TR-SNN: a lightweight spiking neural network based on tensor ring decomposition
- 27 February 2025
- Published by Taylor & Francis in Brain-Apparatus Communication: A Journal of Bacomics
- Vol. 4 (1)
Open AccessTR-SNN: a lightweight spiking neural network based on tensor ring decomposition