Junwei Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Junwei Zhu has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Honghui Xu
Zhejiang University of Technology, Hangzhou, China and Taizhou University, Taizhou, China
7 shared publications - Jianwei Zheng
Zhejiang University of Technology, Hangzhou, China
7 shared publications - Jiawei Jiang
College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China
5 shared publications - Wei Li
College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China
5 shared publications - Junjie Zheng
Zhejiang University of Technology, Hangzhou, China
2 shared publications - Junnan Xu
Zhejiang University of Technology, Hangzhou, China
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12535-12544
Understanding Before Fusion: Solving Spatial-Spectral Fusion via Dual-Semantic Language Guidance
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12535-12544
Open AccessUnderstanding Before Fusion: Solving Spatial-Spectral Fusion via Dual-Semantic Language Guidance
- 13 July 2026
- Published by Elsevier in Information Fusion
- Vol. 137
Semantic-Continuous Mamba for Space-Spectral Fusion
- 13 July 2026
- Published by Elsevier in Information Fusion
- Vol. 137
Semantic-Continuous Mamba for Space-Spectral Fusion
- 26 February 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 339
Subspace-frequency regularization for hyperspectral image super-resolution
- 26 February 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 339
Subspace-frequency regularization for hyperspectral image super-resolution
- 26 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 4219-4232
Arbitrary-Scale Fusion Operator for High-Resolution Hyperspectral Imaging
For high-resolution hyperspectral (HrHs) imaging, spatial-spectral fusion offers a promising alternative to expensive equipment. However, retraining multiple models for varied scaling factors is currently unavoidable, costing extra computational resource and human labor. To address this issue, we propose Arbitrary-scale Fusion Operator (AFO), a lightweight solution for HrHs fusion given arbitrary scalings, turning the retraining strategy into “training-free” ones. Specifically, AFO treats low-resolution hyperspectral (LrHs) images and high resolution multispectral (HrMs) images as light-wise degraded functions within the spectrum, which are initially embedded into a high-dimensional space to simulate the original light signals, tapping the potential of enriched prior learning. Then, a flow of kernel integration (KI) is meticulously crafted, followed by a rival step of dimension reduction for HrHs generation. For a well-behaved KI computation, an Attention-Driven Convolution Integration (ADCI) is engineered to restore the broken discretization invariance derived by convolutions, yet with the locally inductive bias preserved. In addition, we propose an Implicit Neural Functional Integration (INFI) to achieve cross domain interaction of spatial degradation functions, followed by the use of Galerkin-type Integration (GI) as a decoder to handle high-frequency information. Finally, the bonded activation functions are improved for the principle of continuous-discrete equivalence. Extensive experiments validate the superiority of our approach over cutting-edge methods. Notably, our proposal holds significantly better generalization on arbitrary scaling factors, yet requires only 0.07M parameters.
- 26 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 4219-4232
Arbitrary-Scale Fusion Operator for High-Resolution Hyperspectral Imaging
For high-resolution hyperspectral (HrHs) imaging, spatial-spectral fusion offers a promising alternative to expensive equipment. However, retraining multiple models for varied scaling factors is currently unavoidable, costing extra computational resource and human labor. To address this issue, we propose Arbitrary-scale Fusion Operator (AFO), a lightweight solution for HrHs fusion given arbitrary scalings, turning the retraining strategy into “training-free” ones. Specifically, AFO treats low-resolution hyperspectral (LrHs) images and high resolution multispectral (HrMs) images as light-wise degraded functions within the spectrum, which are initially embedded into a high-dimensional space to simulate the original light signals, tapping the potential of enriched prior learning. Then, a flow of kernel integration (KI) is meticulously crafted, followed by a rival step of dimension reduction for HrHs generation. For a well-behaved KI computation, an Attention-Driven Convolution Integration (ADCI) is engineered to restore the broken discretization invariance derived by convolutions, yet with the locally inductive bias preserved. In addition, we propose an Implicit Neural Functional Integration (INFI) to achieve cross domain interaction of spatial degradation functions, followed by the use of Galerkin-type Integration (GI) as a decoder to handle high-frequency information. Finally, the bonded activation functions are improved for the principle of continuous-discrete equivalence. Extensive experiments validate the superiority of our approach over cutting-edge methods. Notably, our proposal holds significantly better generalization on arbitrary scaling factors, yet requires only 0.07M parameters.
- 26 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 1-14
S 2 TA-Fuse: Semantic-Superpixel Tokenized Attention for Spatial–Spectral Fusion
Superpixel paradigms have long been regarded as a well-established approach of mitigating spatial redundancy in hyperspectral images, yet their reliance on non-differentiable and irreversible segmentation renders them unsuitable for end-to-end spatial–spectral fusion (SSF). To tackle this limitation, this study introduces S²TA-Fuse, a transformer-based solver named Semantic-Superpixel Tokenized Attention for Fusion, which preserves the efficiency of superpixels while removing the need for explicit segmentation. The central design lies in a semantic attention mechanism that adaptively organizes pixels into deformable and content-aware semantic groups. Pixels sharing similar latent states are softly aggregated and encoded as compact tokens, upon which attention is computed to capture intricate long-range dependencies. This formulation endows the model with an inherent ability to accommodate scale variations while maintaining linear computational complexity with respect to the number of pixels. On top of the semantic backbone, two complementary components are devised. The Local Spectral Pyramid enhances the representation of multi-scale spectral cues in the spatial domain, whereas FreqNet supplements global information by modeling frequency-dependent variations through amplitude and phase decomposition. Comprehensive experiments on widely used benchmarks for spatial–spectral fusion demonstrate that S²TA-Fuse consistently surpasses the state of the art both in quantitative accuracy and visual fidelity.
- 26 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 1-14
S 2 TA-Fuse: Semantic-Superpixel Tokenized Attention for Spatial–Spectral Fusion
Superpixel paradigms have long been regarded as a well-established approach of mitigating spatial redundancy in hyperspectral images, yet their reliance on non-differentiable and irreversible segmentation renders them unsuitable for end-to-end spatial–spectral fusion (SSF). To tackle this limitation, this study introduces S²TA-Fuse, a transformer-based solver named Semantic-Superpixel Tokenized Attention for Fusion, which preserves the efficiency of superpixels while removing the need for explicit segmentation. The central design lies in a semantic attention mechanism that adaptively organizes pixels into deformable and content-aware semantic groups. Pixels sharing similar latent states are softly aggregated and encoded as compact tokens, upon which attention is computed to capture intricate long-range dependencies. This formulation endows the model with an inherent ability to accommodate scale variations while maintaining linear computational complexity with respect to the number of pixels. On top of the semantic backbone, two complementary components are devised. The Local Spectral Pyramid enhances the representation of multi-scale spectral cues in the spatial domain, whereas FreqNet supplements global information by modeling frequency-dependent variations through amplitude and phase decomposition. Comprehensive experiments on widely used benchmarks for spatial–spectral fusion demonstrate that S²TA-Fuse consistently surpasses the state of the art both in quantitative accuracy and visual fidelity.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1607-1616
SpecSolver: Solving Spatial-Spectral Fusion via Semantic Transformer
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1607-1616
Open AccessSpecSolver: Solving Spatial-Spectral Fusion via Semantic Transformer
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1617-1626
Arbitrary-scale Fusion Neural Operator
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1617-1626
Open AccessArbitrary-scale Fusion Neural Operator