Jiangrong Shen
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
Jiangrong Shen has a total of 76 co-authors. Here are the top co-authors by number of shared publications:
- Qi Xu
Dalian University of Technology, Dalian, China
18 shared publications - Gang Pan
Zhejiang University, Hangzhou, China
16 shared publications - Huajin Tang
Zhejiang University
14 shared publications - Jian. K. Liu
University of Birmingham
6 shared publications Huajin Tang
State Key Lab of Brain-Machine Intelligence Zhejiang University Hangzhou China
5 shared publicationsQi Xu
School of Computer Science and Technology Dalian Uni- versity of Technology Dalian China
5 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 14527-14536
Towards Energy Efficient Spiking Neural Networks: a Homeostatic Metabolic Pruning Framework
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 14527-14536
Open AccessTowards Energy Efficient Spiking Neural Networks: a Homeostatic Metabolic Pruning Framework
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 564-572
Spiking Neural Network with Mixture of Heterogeneous Enhancement Experts for Underwater Object Detection
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 564-572
Open AccessSpiking Neural Network with Mixture of Heterogeneous Enhancement Experts for Underwater Object Detection
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8665-8674
Adaptive Sparse Structural Evolution for Continual Learning in Spiking Neural Networks
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8665-8674
Open AccessAdaptive Sparse Structural Evolution for Continual Learning in Spiking Neural Networks
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8655-8664
An Efficient Structural Pruning for Spiking Neural Networks by Balancing Accuracy and Sparsification
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8655-8664
Open AccessAn Efficient Structural Pruning for Spiking Neural Networks by Balancing Accuracy and Sparsification
- 16 June 2026
- Published by Aerospace Information Research Institute, Chinese Academy of Sciences in Journal of Image and Graphics
- Vol. 31 (6) , 2070-2102
脑启发的人工智能研究进展与展望
脑启发的人工智能以人类大脑的结构与功能机制为灵感,旨在构建具备低功耗与强泛化能力的新型智能系统。当前以深度学习为核心的人工智能方法在计算资源开销、能耗、可解释性与适应性方面仍存在显著不足,难以在复杂多变或资源受限的环境中实现持续学习与灵活推理。相比之下,大脑展现出在并行处理、低功耗、快速泛化及自适应学习等方面的天然优势,这为突破传统人工智能范式提供了重要启示。本文系统综述了脑启发的人工智能领域的国内外研究进展。从脑结构启发的角度,分析了神经元模型、神经环路与神经调制机制的多层级建模方法;从脑功能启发的角度,探讨了感知、认知、学习、决策与控制等智能环节的算法创新路径;从硬件系统的角度,总结了具有近内存与存算一体架构的新型类脑计算系统的发展现状。报告进一步比较了国际与国内在理论研究、算法优化与硬件实现等方面的差异与互补优势。最后,展望了未来脑启发的人工智能在算法–硬件协同、跨学科融合及产业化应用方面的发展趋势,提出了推动我国在该领域实现跨越式突破的关键方向。
- 16 June 2026
- Published by Aerospace Information Research Institute, Chinese Academy of Sciences in Journal of Image and Graphics
- Vol. 31 (6) , 2070-2102
脑启发的人工智能研究进展与展望
脑启发的人工智能以人类大脑的结构与功能机制为灵感,旨在构建具备低功耗与强泛化能力的新型智能系统。当前以深度学习为核心的人工智能方法在计算资源开销、能耗、可解释性与适应性方面仍存在显著不足,难以在复杂多变或资源受限的环境中实现持续学习与灵活推理。相比之下,大脑展现出在并行处理、低功耗、快速泛化及自适应学习等方面的天然优势,这为突破传统人工智能范式提供了重要启示。本文系统综述了脑启发的人工智能领域的国内外研究进展。从脑结构启发的角度,分析了神经元模型、神经环路与神经调制机制的多层级建模方法;从脑功能启发的角度,探讨了感知、认知、学习、决策与控制等智能环节的算法创新路径;从硬件系统的角度,总结了具有近内存与存算一体架构的新型类脑计算系统的发展现状。报告进一步比较了国际与国内在理论研究、算法优化与硬件实现等方面的差异与互补优势。最后,展望了未来脑启发的人工智能在算法–硬件协同、跨学科融合及产业化应用方面的发展趋势,提出了推动我国在该领域实现跨越式突破的关键方向。
- Open Access
- 10 January 2026
- Published by Elsevier in Neural Networks
- Vol. 198, 108576
Key-value pair-free continual learner via task-specific prompt-prototype
- 10 January 2026
- Published by Elsevier in Neural Networks
- Vol. 198, 108576
Open AccessKey-value pair-free continual learner via task-specific prompt-prototype
- 14 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 902-914
Generic-to-Personalised Learning for Multimodal Image Synthesis With Bidirectional Variational GAN
Multimodal image synthesis, which predicts target-modality images from source-modality images, has garnered considerable attention in the field of clinical diagnosis. Both unidirectional and bidirectional multimodal image synthesis methods have been explored in the medical domain, however, unidirectional models heavily rely on paired images, while current bidirectional models typically overlook local image details due to their unsupervised training patterns. In this work, we propose a Bidirectional Variational Generative Adversarial Network (BVGAN) for multimodal image synthesis, which achieves high-quality bidirectional translations between any two modalities using only a limited number paired images. Firstly, BVGAN's generator incorporates a variational structure (VAS) to regularise the latent space for noise reduction. This regularisation imposes smoothness to the latent space, enabling BVGAN to produce high-quality, noise-free images. Secondly, a novel generic-to-personalised (GTP) learning strategy is introduced to train BVGAN and reduce its reliance on a large sets of paired images. GTP initially leverages an unsupervised learning model to capture the global mapping between two modalities using unpaired images from generic patients. It then applies a supervised learning model to refine the mapping for individual patient, enhancing image details. Finally, the GTP learning strategy along with VAS enables BVGAN to achieve state-of-the-art performance on two multi-modality medical datasets: Brain CTMRI and BRATS.
- 14 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 902-914
Generic-to-Personalised Learning for Multimodal Image Synthesis With Bidirectional Variational GAN
Multimodal image synthesis, which predicts target-modality images from source-modality images, has garnered considerable attention in the field of clinical diagnosis. Both unidirectional and bidirectional multimodal image synthesis methods have been explored in the medical domain, however, unidirectional models heavily rely on paired images, while current bidirectional models typically overlook local image details due to their unsupervised training patterns. In this work, we propose a Bidirectional Variational Generative Adversarial Network (BVGAN) for multimodal image synthesis, which achieves high-quality bidirectional translations between any two modalities using only a limited number paired images. Firstly, BVGAN's generator incorporates a variational structure (VAS) to regularise the latent space for noise reduction. This regularisation imposes smoothness to the latent space, enabling BVGAN to produce high-quality, noise-free images. Secondly, a novel generic-to-personalised (GTP) learning strategy is introduced to train BVGAN and reduce its reliance on a large sets of paired images. GTP initially leverages an unsupervised learning model to capture the global mapping between two modalities using unpaired images from generic patients. It then applies a supervised learning model to refine the mapping for individual patient, enhancing image details. Finally, the GTP learning strategy along with VAS enables BVGAN to achieve state-of-the-art performance on two multi-modality medical datasets: Brain CTMRI and BRATS.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11042-11051
Spiking Neural Networks with Temporal Attention-Guided Adaptive Fusion for imbalanced Multi-modal Learning
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11042-11051
Open AccessSpiking Neural Networks with Temporal Attention-Guided Adaptive Fusion for imbalanced Multi-modal Learning
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 10837-10846
Advanced SpikingYOLOX: Extending Spiking Neural Network on Object Detection with Spike-based Partial Self-Attention and 2D-Spiking Transformer
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 10837-10846
Open AccessAdvanced SpikingYOLOX: Extending Spiking Neural Network on Object Detection with Spike-based Partial Self-Attention and 2D-Spiking Transformer
- Open Access
Hybrid Spiking Vision Transformer for Object Detection with Event Cameras
Event-based object detection has gained increasing attention due to its advantages such as high temporal resolution, wide dynamic range, and asynchronous address-event representation. Leveraging these advantages, Spiking Neural Networks (SNNs) have emerged as a promising approach, offering low energy consumption and rich spatiotemporal dynamics. To further enhance the performance of event-based object detection, this study proposes a novel hybrid spike vision Transformer (HsVT) model. The HsVT model integrates a spatial feature extraction module to capture local and global features, and a temporal feature extraction module to model time dependencies and long-term patterns in event sequences. This combination enables HsVT to capture spatiotemporal features, improving its capability to handle complex event-based object detection tasks. To support research in this area, we developed and publicly released The Fall Detection Dataset as a benchmark for event-based object detection tasks. This dataset, captured using an event-based camera, ensures facial privacy protection and reduces memory usage due to the event representation format. We evaluated the HsVT model on GEN1 and Fall Detection datasets across various model sizes. Experimental results demonstrate that HsVT achieves significant performance improvements in event detection with fewer parameters.
Open AccessHybrid Spiking Vision Transformer for Object Detection with Event Cameras
Event-based object detection has gained increasing attention due to its advantages such as high temporal resolution, wide dynamic range, and asynchronous address-event representation. Leveraging these advantages, Spiking Neural Networks (SNNs) have emerged as a promising approach, offering low energy consumption and rich spatiotemporal dynamics. To further enhance the performance of event-based object detection, this study proposes a novel hybrid spike vision Transformer (HsVT) model. The HsVT model integrates a spatial feature extraction module to capture local and global features, and a temporal feature extraction module to model time dependencies and long-term patterns in event sequences. This combination enables HsVT to capture spatiotemporal features, improving its capability to handle complex event-based object detection tasks. To support research in this area, we developed and publicly released The Fall Detection Dataset as a benchmark for event-based object detection tasks. This dataset, captured using an event-based camera, ensures facial privacy protection and reduces memory usage due to the event representation format. We evaluated the HsVT model on GEN1 and Fall Detection datasets across various model sizes. Experimental results demonstrate that HsVT achieves significant performance improvements in event detection with fewer parameters.