Unsupervised dehazing method for remote sensing images with non-uniform haze

doi:10.11772/j.issn.1001-9081.2025060755

Journal of Computer Applications ›› 2026, Vol. 46 ›› Issue (7): 2297-2306.DOI: 10.11772/j.issn.1001-9081.2025060755

• Multimedia computing and computer simulation • Previous Articles

Unsupervised dehazing method for remote sensing images with non-uniform haze

Wenling LIU¹, Yong LI²(), Jiahui LI¹, Houkang ZHANG¹

^1.College of Computer Science and Cyber Security，Chengdu University of Technology，Chengdu Sichuan 610059，China
^2.College of Geophysics，Chengdu University of Technology，Chengdu Sichuan 610059，China

Received:2025-07-11 Revised:2025-09-22 Accepted:2025-09-29 Online:2025-10-13 Published:2026-07-10
Contact: Yong LI
About author:LIU Wenling， born in 2001， M. S. candidate. Her research interests include image processing.
LI Jiahui， born in 2002， M. S. candidate. Her research interests include image processing.
ZHANG Houkang， born in 1999， M. S. candidate. His research interests include deep learning， stochastic resonance.
Supported by:
Science and Technology Program of Sichuan(2020YFG0157)

面向不均匀雾霾遥感图像的无监督去雾方法

刘雯玲¹, 李勇²(), 李佳慧¹, 张厚康¹

^1.成都理工大学计算机与网络安全学院，成都 610059
^2.成都理工大学地球物理学院，成都 610059

通讯作者: 李勇
作者简介:刘雯玲（2001—），女，四川成都人，硕士研究生，主要研究方向：图像处理
李佳慧（2002—），女，河南民权人，硕士研究生，主要研究方向：图像处理
张厚康（1999—），男，湖北黄冈人，硕士研究生，主要研究方向：深度学习、随机共振。
基金资助:
四川省科技计划项目(2020YFG0157)

Abstract

Abstract:

To address the problem that the existing dehazing methods are difficult to suppress artifact generation and insufficient texture detail recovery caused by non-uniform haze distribution in real remote sensing images effectively， an unsupervised dehazing method for remote sensing images with non-uniform haze was proposed. First， based on Cycle-consistent Generative Adversarial Network （CycleGAN）， a Residual Multi-scale Attention Mechanism （RMAM） was designed in the generator to expand the receptive field and enhance the extraction ability of multi-scale texture and structural information， thereby effectively restoring realistic texture details. Second， a Haze Distribution Enhancement Module （HDEM） was designed to explicitly enhance the expression of haze features， and combined with a dual-branch fusion strategy， the network was guided to accurately identify and process non-uniform haze， thereby alleviating the artifact issue caused by insufficient haze distribution perception. Finally， a Feature Attention （FA） mechanism was embedded in the discriminator to strengthen its ability to distinguish the authenticity of local structures and textures in the image， thereby improving its ability to restore dehazed images. Experimental results on the synthetic remote sensing datasets SateHaze 1k and RICE showed that the proposed method outperformed the best-performing baseline method DedustGAN by 4.20% and 2.44%， respectively， in Peak Signal-to-Noise Ratio （PSNR）， and by 0.96% and 0.51%， respectively， in Structural Similarity Index Measure （SSIM）. Experimental results on the real-world dataset RRSD300 showed that the proposed method outperformed the best-performing baseline method Cycle-SNSPGAN by 2.04% and 0.45% in Natural Image Quality Evaluator （NIQE） and Integrated Local NIQE （IL-NIQE）， respectively. The proposed method effectively removes non-uniform haze， suppresses artifact generation， and restores texture details in remote sensing images.

Key words: image dehazing, remote sensing image, unsupervised method, attention mechanism, feature enhancement

摘要：

针对现有的去雾方法在真实遥感图像中难以有效抑制由不均匀雾霾分布引发的伪影生成及纹理细节恢复不足的问题，提出一种面向不均匀雾霾遥感图像的无监督去雾方法。首先，基于循环生成对抗网络（CycleGAN），在生成器中设计残差多尺度注意力机制（RMAM），扩大感受野并增强对多尺度纹理与结构信息的提取能力，从而有效恢复真实的纹理细节信息；其次，设计雾霾分布增强模块（HDEM），显式地增强雾霾特征的表达，并结合双分支融合策略引导网络精准识别和处理不均匀雾霾，缓解因雾霾分布感知不足造成的伪影；最后，在判别器中嵌入特征注意力（FA）机制，强化对图像局部结构与纹理真实性的判别能力，提高去雾图像的细节还原能力。在合成遥感图像数据集SateHaze 1k和RICE上的实验结果表明，本文方法与最优的基线方法DedustGAN相比在峰值信噪比（PSNR）上分别提高了4.20%和2.44%，在结构相似度（SSIM）上分别提高了0.96%和0.51%；在真实数据集RRSD300上的实验结果表明，本文方法与最优的基线方法Cycle-SNSPGAN相比在自然图像质量评价（NIQE）和综合局部自然图像质量评价（IL-NIQE）上分别降低了2.04%和0.45%。本文方法能够有效去除不均匀雾霾、抑制伪影生成并恢复遥感图像中的纹理细节。

关键词: 图像去雾, 遥感图像, 无监督方法, 注意力机制, 特征增强

CLC Number:

TP751

Wenling LIU, Yong LI, Jiahui LI, Houkang ZHANG. Unsupervised dehazing method for remote sensing images with non-uniform haze[J]. Journal of Computer Applications, 2026, 46(7): 2297-2306.

刘雯玲, 李勇, 李佳慧, 张厚康. 面向不均匀雾霾遥感图像的无监督去雾方法[J]. 《计算机应用》唯一官方网站, 2026, 46(7): 2297-2306.

Figures/Tables 14

References 51

[1]	Han W， Zhang X， Wang Y， et al. A survey of machine learning and deep learning in remote sensing of geological environment： challenges， advances， and opportunities ［J］. ISPRS Journal of Photogrammetry and Remote Sensing， 2023， 202： 87-113.
[2]	Quamar M M， Al-Ramadan B， Khan K， et al. Advancements and applications of drone-integrated geographic information system technology： a review ［J］. Remote Sensing， 2023， 15（20）： No.5039.
[3]	Qiu Z， Gong T， Liang Z， et al. Perception-oriented UAV image dehazing based on super-pixel scene prior ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2024， 62： No.5913519.
[4]	Jackson J， Agyekum K O， Sarpong S， et al. Hazy to hazy free： a comprehensive survey of multi-image， single-image， and CNN-based algorithms for dehazing ［J］. Computer Science Review， 2024， 54： No.100669.
[5]	Gui J， Cong X， Cao Y， et al. A comprehensive survey and taxonomy on single image dehazing based on deep learning ［J］. ACM Computing Surveys， 2023， 55（13s）： No.279.
[6]	Agrawal S C， Jalal A S. A comprehensive review on analysis and implementation of recent image dehazing methods ［J］. Archives of Computational Methods in Engineering， 2022， 29（7）： 4799-4850.
[7]	Zhao L， Zhang Y， Cui Y. A multi-scale U-shaped attention network-based GAN method for single image dehazing ［J］. Human-centric Computing and Information Sciences， 2021， 11： No.38.
[8]	Zhang X， Zhang L， Chu M， et al. DU-Net： a new double U-shaped network for single image dehazing ［J］. Journal of Visual Communication and Image Representation， 2024， 100： No.104132.
[9]	Chen D， He M， Fan Q， et al. Gated context aggregation network for image dehazing and deraining ［C］// WACV 2019. Piscataway： IEEE， 2019： 1375-1383.
[10]	Qin X， Wang Z， Bai Y， et al. FFA-Net： feature fusion attention network for single image dehazing ［C］// AAAI 2020. Palo Alto： AAAI Press， 2020： 11908-11915.
[11]	Wang S， Zhang L. Dynamic mutual enhancement network for single remote sensing image dehazing ［C］// ICIP 2022. Piscataway： IEEE， 2022： 3336-3340.
[12]	Lin Z， Luo Q， Jiang Y， et al. Image defogging based on multi-input and multi-scale UNet ［J］. Signal， Image and Video Processing， 2023， 17（4）： 1143-1151.
[13]	Du Y， Li J， Sheng Q， et al. Dehazing network： asymmetric UNet based on physical model ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2024， 62： No.5607412.
[14]	Ali A M， El-Rabaie E S M， Ramadan K F， et al. CLEAR-Net： a cascaded local and external attention network for enhanced dehazing of remote sensing images ［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2025： 1-20.
[15]	Zhang Y， Liu S， Dong C， et al. Multiple cycle-in-cycle generative adversarial networks for unsupervised image super-resolution ［J］. IEEE Transactions on Image Processing， 2020， 29： 1101-1112.
[16]	Gao G， Lai H， Jia Z. Unsupervised image dedusting via a cycle-consistent generative adversarial network ［J］. Remote Sensing， 2023， 15（5）： No.1311.
[17]	Engin D， GENÇ A， Ekenel H K. Cycle-Dehaze： enhanced CycleGAN for single image dehazing ［C］// CVPR Workshops 2018. Piscataway： IEEE， 2018： 938-946.
[18]	Wang Y， Yan X， Guan D， et al. Cycle-SNSPGAN： towards real-world image dehazing via cycle spectral normalized soft likelihood estimation patch GAN ［J］. IEEE Transactions on Intelligent Transportation Systems， 2022， 23（11）： 20368-20382.
[19]	Sun H， Zhang Y， Chen P， et al. Scale-free heterogeneous CycleGAN for defogging from a single image for autonomous driving in fog ［J］. Neural Computing and Applications， 2023， 35（5）： 3737-3751.
[20]	Yan B， Yang Z， Sun H， et al. ADE-CycleGAN： a detail enhanced image dehazing CycleGAN network ［J］. Sensors， 2023， 23（6）： No.3294.
[21]	Meng X， Huang J， Li Z， et al. DedustGAN： unpaired learning for image dedusting based on retinex with GANs ［J］. Expert Systems with Applications， 2024， 243： No.122844.
[22]	Li C， Zhang X， Wang H， et al. UTCR-Dehaze： U-Net and Transformer-based cycle-consistent generative adversarial network for unpaired remote sensing image dehazing ［J］. Engineering Applications of Artificial Intelligence， 2025， 158（Pt B）： No.111385.
[23]	Dwivedi P， Chakraborty S. FrTrGAN： single image dehazing using the frequency component of transmission maps in the generative adversarial network ［J］. Computer Vision and Image Understanding， 2025， 255： No.104336.
[24]	孙航，付秋月，李勃辉，等.基于跨层注意力特征交互和多尺度通道注意力的单幅图像去雾网络［J］.电子学报， 2024， 52（11）： 3711-3726.
	Sun Hang， Fu Qiuyue， Li Bohui， et al. Cross-layer attention feature interaction and multi-scale channel attention network for single image dehazing ［J］. Acta Electronica Sinica， 2024， 52（11）： 3711-3726.
[25]	Jin M， Wang P， Li Y. HyA-GAN： remote sensing image cloud removal based on hybrid attention generation adversarial network ［J］. International Journal of Remote Sensing， 2024， 45（6）： 1755-1773.
[26]	Kim N， Choi I S， Han S S， et al. DA-Net： dual attention network for haze removal in remote sensing image ［J］. IEEE Access， 2024， 12： 136297-136312.
[27]	Dong W， Wang C， Sun H， et al. End-to-end detail-enhanced dehazing network for remote sensing images ［J］. Remote Sensing， 2024， 16（2）： No.225.
[28]	Wang J， Wang S， Wu M， et al. Multi-scale adaptive detail enhancement dehazing network for autonomous driving perception images ［J］. Pattern Analysis and Applications， 2025， 28（2）： No.51.
[29]	Jiang B， Wang J， Wu Y， et al. A dehazing method for remote sensing image under nonuniform hazy weather based on deep learning network ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2023， 61： No.4101717.
[30]	Feng Y， Su Z， Ma L， et al. Bridging the gap between haze scenarios： a unified image dehazing model ［J］. IEEE Transactions on Circuits and Systems for Video Technology， 2024， 34（11）： 11070-11085.
[31]	Guo F， Yang J， Liu Z， et al. Haze removal for single image： a comprehensive review ［J］. Neurocomputing， 2023， 537： 85-109.
[32]	Wang T， Zhao L， Huang P， et al. Haze concentration adaptive network for image dehazing ［J］. Neurocomputing， 2021， 439： 75-85.
[33]	Li X， Hua Z， Li J. Attention-based adaptive feature selection for multi-stage image dehazing ［J］. The Visual Computer， 2023， 39（2）： 663-678.
[34]	Shen J， Tong L， Li S， et al. PromptHC： multi-attention prompt guided haze-weather crowd counting ［J］. Expert Systems with Applications， 2025， 286： No.128023.
[35]	Zhang X， Wang T， Wang J， et al. Pyramid channel-based feature attention network for image dehazing ［J］. Computer Vision and Image Understanding， 2020， 197/198： No.103003.
[36]	Li C， Tang Z， Qiao J， et al. Multi-scale adaptive feature network drainage pipe image dehazing method based on multiple attention ［J］. Electronics， 2024， 13（7）： No.1406.
[37]	Shen H， Zhang C， Li H， et al. A spatial-spectral adaptive haze removal method for visible remote sensing images ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2020， 58（9）： 6168-6180.
[38]	Liu X， Hsieh C J. Rob-GAN： generator， discriminator， and adversarial attacker ［C］// CVPR 2019. Piscataway： IEEE， 2019： 11226-11235.
[39]	Ma J， Xu H， Jiang J， et al. DDcGAN： a dual-discriminator conditional generative adversarial network for multi-resolution image fusion ［J］. IEEE Transactions on Image Processing， 2020， 29： 4980-4995.
[40]	Pan Z， Yu W， Wang B， et al. Loss functions of Generative Adversarial Networks （GANs）： opportunities and challenges ［J］. IEEE Transactions on Emerging Topics in Computational Intelligence， 2020， 4（4）： 500-522.
[41]	Huang B， Zhi L， Yang C， et al. Single satellite optical imagery dehazing using SAR image prior based on conditional generative adversarial networks ［C］// WACV 2020. Piscataway： IEEE， 2020： 1795-1802.
[42]	Lin D， Xu G， Wang X， et al. A remote sensing image dataset for cloud removal ［PP/OL］. arXiv （2019-01-03）［2025-04-21］. .
[43]	Zai W， Yan L. Multi-patch hierarchical transmission channel image dehazing network based on dual attention level feature fusion ［J］. Sensors， 2023， 23（16）： No.7026.
[44]	Xu Y， Zhang H， He F， et al. Enhanced CycleGAN network with adaptive dark channel prior for unpaired single-image dehazing ［J］. Entropy， 2023， 25（6）： No.856.
[45]	Wen Y， Gao T， Zhang J， et al. Encoder-free multiaxis physics-aware fusion network for remote sensing image dehazing ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2023， 61： No.4705915.
[46]	Mittal A， Soundararajan R， Bovik A C. Making a “completely blind” image quality analyzer ［J］. IEEE Signal Processing Letters， 2013， 20（3）： 209-212.
[47]	Zhang L， Zhang L， Bovik A C. A feature-enriched completely blind image quality evaluator ［J］. IEEE Transactions on Image Processing， 2015， 24（8）： 2579-2591.
[48]	Li B， Peng X， Wang Z， et al. AOD-Net： all-in-one dehazing network ［C］// ICCV 2017. Piscataway： IEEE， 2017： 4780-4788.
[49]	Xiao B， Zheng Z， Zhuang Y， et al. Single UHD image dehazing via interpretable pyramid network ［J］. Signal Processing， 2024， 214： No.109225.
[50]	Song Y， He Z， Qian H， et al. Vision Transformers for single image dehazing ［J］. IEEE Transactions on Image Processing， 2023， 32： 1927-1941.
[51]	Zhu J Y， Park T， Isola P， et al. Unpaired image-to-image translation using cycle-consistent adversarial networks ［C］// ICCV 2017. Piscataway： IEEE， 2017： 2242-2251.

监督类型	方法	SateHaze 1k-Thin		SateHaze 1k-Moderate		SateHaze 1k-Thick		SateHaze 1k-Average
监督类型	方法	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM
监督	AOD-Net^［48］	17.15	0.854	17.93	0.837	15.82	0.768	16.97	0.820
	GCA-Net^［9］	20.97	0.888	20.43	0.876	17.37	0.815	19.59	0.860
	4KDehazing^［49］	22.24	0.937	21.73	0.916	19.33	0.896	21.10	0.916
	FFA-Net^［10］	23.25	0.945	22.72	0.930	19.20	0.894	21.72	0.923
	DehazeFormer^［50］	24.56	0.953	23.12	0.934	20.84	0.904	22.82	0.930
无监督	CycleGAN^［51］	17.76	0.863	17.66	0.824	16.04	0.758	17.15	0.815
	Cycle-Dehaze^［17］	21.24	0.925	19.21	0.861	18.29	0.853	19.58	0.880
	ADE-CycleGAN^［20］	21.38	0.912	20.59	0.887	18.87	0.867	20.28	0.889
	Cycle-SNSPGAN^［18］	22.90	0.941	21.74	0.915	19.65	0.897	21.43	0.918
	DedustGAN^［21］	24.45	0.950	23.91	0.936	21.48	0.915	23.28	0.934
	本文方法	25.35	0.961	24.71	0.945	22.72	0.922	24.26	0.943

监督类型	方法	SateHaze 1k-Thin		SateHaze 1k-Moderate		SateHaze 1k-Thick		SateHaze 1k-Average
监督类型	方法	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM
监督	AOD-Net^［48］	17.15	0.854	17.93	0.837	15.82	0.768	16.97	0.820
	GCA-Net^［9］	20.97	0.888	20.43	0.876	17.37	0.815	19.59	0.860
	4KDehazing^［49］	22.24	0.937	21.73	0.916	19.33	0.896	21.10	0.916
	FFA-Net^［10］	23.25	0.945	22.72	0.930	19.20	0.894	21.72	0.923
	DehazeFormer^［50］	24.56	0.953	23.12	0.934	20.84	0.904	22.82	0.930
无监督	CycleGAN^［51］	17.76	0.863	17.66	0.824	16.04	0.758	17.15	0.815
	Cycle-Dehaze^［17］	21.24	0.925	19.21	0.861	18.29	0.853	19.58	0.880
	ADE-CycleGAN^［20］	21.38	0.912	20.59	0.887	18.87	0.867	20.28	0.889
	Cycle-SNSPGAN^［18］	22.90	0.941	21.74	0.915	19.65	0.897	21.43	0.918
	DedustGAN^［21］	24.45	0.950	23.91	0.936	21.48	0.915	23.28	0.934
	本文方法	25.35	0.961	24.71	0.945	22.72	0.922	24.26	0.943

监督类型	方法	PSNR/dB	SSIM
监督	AOD-Net^［48］	20.88	0.856
	GCA-Net^［9］	23.37	0.854
	4KDehazing^［49］	26.45	0.946
	FFA-Net^［10］	31.68	0.954
	DehazeFormer^［50］	32.13	0.965
无监督	CycleGAN^［51］	20.20	0.853
	Cycle-Dehaze^［17］	24.23	0.927
	ADE-CycleGAN^［20］	24.36	0.930
	Cycle-SNSPGAN^［18］	29.21	0.959
	DedustGAN^［21］	32.74	0.967
	本文方法	33.54	0.972

监督类型	方法	PSNR/dB	SSIM
监督	AOD-Net^［48］	20.88	0.856
	GCA-Net^［9］	23.37	0.854
	4KDehazing^［49］	26.45	0.946
	FFA-Net^［10］	31.68	0.954
	DehazeFormer^［50］	32.13	0.965
无监督	CycleGAN^［51］	20.20	0.853
	Cycle-Dehaze^［17］	24.23	0.927
	ADE-CycleGAN^［20］	24.36	0.930
	Cycle-SNSPGAN^［18］	29.21	0.959
	DedustGAN^［21］	32.74	0.967
	本文方法	33.54	0.972

监督类型	方法	NIQE（↓）	IL-NIQE（↓）
监督	AOD-Net^［48］	4.38	26.93
	GCA-Net^［9］	5.35	24.95
	FFA-Net^［10］	4.08	24.40
无监督	CycleGAN^［51］	4.71	24.75
	Cycle-Dehaze^［17］	4.10	24.75
	Cycle-SNSPGAN^［18］	3.91	24.38
	本文方法	3.83	24.27

Unsupervised dehazing method for remote sensing images with non-uniform haze

面向不均匀雾霾遥感图像的无监督去雾方法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 14

References 51

Related Articles 15

Recommended Articles

Metrics

模块类型	实验编号	消融策略	PSNR/dB	SSIM
整体模块	1	Baseline	17.34	0.785
	2	Baseline+RMAM	18.20	0.877
	3	Baseline+RMAM+HDEM	20.98	0.893
	4	本文方法	22.72	0.922
HDEM	5	仅保留残差连接分支	20.45	0.897
	6	仅保留逐像素加权分支	21.69	0.915
	7	双分支结构	22.72	0.922

[1]	Xiuli DU, Xing GAO, Xiaoyu ZHANG, Chengsheng PAN, Qijie ZOU. Video snapshot compressive imaging reconstruction method based on dense spatio-temporal deformable attention [J]. Journal of Computer Applications, 2026, 46(7): 2288-2296.
[2]	Guoyou ZHANG, Hongyu NIE, Lihu PAN, Rundong LEI. Point-MLPBLS： point cloud semantic segmentation network based on MLP cascaded broad learning system [J]. Journal of Computer Applications, 2026, 46(7): 2259-2266.
[3]	Jinxiao ZHANG, Chenglong LI, Xinyan GAO, Ming ZHANG. 3D human pose estimation model based on temporal-spatial feature pyramid network and multi-hypothesis interaction mechanism [J]. Journal of Computer Applications, 2026, 46(6): 1965-1972.
[4]	Yunping HE, Leichun WANG, Ruirui SONG, Xiangfeng LU, Jinxiang WEI, Xiaomeng LIU. Dual-channel multimodal sentiment analysis model based on contrast invariance and reinforcement specificity [J]. Journal of Computer Applications, 2026, 46(6): 1767-1775.
[5]	Liwan YAO, Hailong LIU, Zhangfan ZENG. Frequency-domain driven and diffusion-based fusion for sonar image enhancement algorithm [J]. Journal of Computer Applications, 2026, 46(6): 1947-1955.
[6]	Xiaoqin YU, Wuyang SHAN, Junying QIU, Yu LIN, Ronghao YANG, Mao TIAN. Image tampering localization and detection network under brightness-contrast disturbances [J]. Journal of Computer Applications, 2026, 46(6): 1893-1903.
[7]	Jun QIN, Xintao JIAO, Biqing ZENG. Non-intrusive load monitoring method combining BiLSTM-Transformer and Kolmogorov-Arnold network [J]. Journal of Computer Applications, 2026, 46(6): 2026-2033.
[8]	Yasong ZHANG, Bihui CONG, Shuang XU. Graph neural network node classification model incorporating clustering coefficients [J]. Journal of Computer Applications, 2026, 46(6): 1855-1862.
[9]	Ying JING, Ran LI, Zhuo JIANG, Ziyang FU, Jingyi DU, Qi LIU, Jihang LIU. SAM Meibomian gland unified dense segmentation method with introduction of automatic prompt encoder [J]. Journal of Computer Applications, 2026, 46(5): 1667-1676.
[10]	Jing HU, Shikun CHEN, Fang WANG, Rui ZHANG, Yong WANG. Ore image segmentation with linear deformable convolution and dual-domain synergistic dynamic attention [J]. Journal of Computer Applications, 2026, 46(5): 1692-1702.
[11]	Huijie GUO, Tianfeng DOU, Zhenlin ZHANG, Kaiyuan QI, Dong WU, Zhijian QU, Zhao LI, Chongguang REN. Time-interdependency-aware dynamic Bayesian network for traffic prediction [J]. Journal of Computer Applications, 2026, 46(5): 1507-1517.
[12]	Wen PENG, Bokai ZHANG, Jinwei LIN. Chromosome cascaded classification framework integrating image texture enhancement and super-resolution [J]. Journal of Computer Applications, 2026, 46(5): 1647-1657.
[13]	Qianfei WANG, Yang LI, Deyu LI, Suge WANG. Dual-channel feature fusion representation method for short-text clustering based on large language model [J]. Journal of Computer Applications, 2026, 46(5): 1441-1449.
[14]	Baoyuan ZHENG, Chaobo HE. Graph convolutional network enhanced by graph diffusion and dual-view feature learning [J]. Journal of Computer Applications, 2026, 46(5): 1370-1377.
[15]	Ruirui SONG, Leichun WANG, Yunping HE, Jinxiang WEI, Xiangfeng LU, Xiaomeng LIU. Long time series prediction based on hybrid self-attention and differentiated normalization [J]. Journal of Computer Applications, 2026, 46(5): 1499-1506.