FCMdepth： monocular depth estimation framework with multi-scale feature optimization

doi:10.11772/j.issn.1001-9081.2025070890

Journal of Computer Applications ›› 2026, Vol. 46 ›› Issue (8): 2603-2611.DOI: 10.11772/j.issn.1001-9081.2025070890

• Multimedia computing and computer simulation • Previous Articles Next Articles

FCMdepth： monocular depth estimation framework with multi-scale feature optimization

Fengchun LIU¹^,²^,³^,⁴^,⁵^,⁶, Xinying SHAO⁷, Chunying ZHANG¹^,³^,⁴^,⁵^,⁶(), Liya WANG¹^,³^,⁴^,⁵^,⁶, Jing REN¹^,³^,⁴^,⁵^,⁶

^1.College of Sciences，North China University of Science and Technology，Tangshan Hebei 063210，China
^2.Qing Gong College，North China University of Science and Technology，Tangshan Hebei 063210，China
^3.Hebei Engineering Research Center for the Intelligentization of Iron Ore Optimization and Ironmaking Raw Materials Preparation Processes （North China University of Science and Technology），Tangshan Hebei 063210，China
^4.Hebei Provincial Key Laboratory of Data Science and Application （North China University of Science and Technology），Tangshan Hebei 063210，China
^5.Tangshan Key Laboratory of Engineering Computing，North China University of Science and Technology，Tangshan Hebei 063210，China
^6.Tangshan Intelligent Industry and Image Processing Technology Innovation Center，North China University of Science and Technology，Tangshan Hebei 063210，China
^7.College of Artificial Intelligence，North China University of Science and Technology，Tangshan Hebei 063210，China

Received:2025-08-05 Revised:2025-10-15 Accepted:2025-10-15 Online:2025-11-05 Published:2026-08-10
Contact: Chunying ZHANG
About author:LIU Fengchun， born in 1976， M. S.， professor. His research interests include deep learning， data mining， big data security， privacy protection.
SHAO Xinying， born in 1999， M. S. candidate. Her research interests include image processing.
WANG Liya， born in 1987， M. S.， associate professor. Her research interests include machine learning， big data analysis.
REN Jing， born in 1995， M. S.， lecturer. Her research interests include data mining， machine learning， rough set.
Supported by:
Fundamental Research Funds for Provincial Universities(JJC2024036);Tangshan Science and Technology Program(24140202C)

多尺度特征优化的单目深度估计框架FCMdepth

刘凤春¹^,²^,³^,⁴^,⁵^,⁶, 邵馨莹⁷, 张春英¹^,³^,⁴^,⁵^,⁶(), 王立亚¹^,³^,⁴^,⁵^,⁶, 任静¹^,³^,⁴^,⁵^,⁶

^1.华北理工大学理学院，河北唐山 063210
^2.华北理工大学轻工学院，河北唐山 063210
^3.铁矿石优选与铁前工艺智能化河北省工程研究中心（华北理工大学），河北唐山 063210
^4.河北省数据科学与应用重点实验室（华北理工大学），河北唐山 063210
^5.华北理工大学唐山市工程计算重点实验室，河北唐山 063210
^6.华北理工大学唐山市智能工业与图像处理技术创新中心，河北唐山 063210
^7.华北理工大学人工智能学院，河北唐山 063210

通讯作者: 张春英
作者简介:刘凤春（1976—），男，辽宁丹东人，教授，硕士，CCF会员，主要研究方向：深度学习、数据挖掘、大数据安全、隐私保护
邵馨莹（1999—），女，河北迁安人，硕士研究生，主要研究方向：图像处理
张春英（1969—），女，河北迁安人，教授，博士，CCF会员，主要研究方向：深度学习、计算机视觉
王立亚（1987—），女，河北唐山人，副教授，硕士，主要研究方向：机器学习、大数据分析
任静（1995—），女，河南焦作人，讲师，硕士，主要研究方向：数据挖掘、机器学习、粗糙集。
基金资助:
省属高校基本科研业务费资助项目(JJC2024036);唐山市科技计划项目(24140202C)

Abstract

Abstract:

To address the issues of insufficient feature extraction and inadequate context modeling in monocular depth estimation， we proposed a multi-scale feature fused monocular depth estimation optimization framework， FCMdepth， to enhance prediction performance. FCMdepth adopted an Encoder-Decoder （ED） structure， where the encoder， FC-Net， consists of MobileNetV3-F and CDBlock， and optimized features through multi-scale features and dilated convolutions， while the decoder， LapMA-Net， combined the Laplacian pyramid with an Efficient Multi-scale Attention （EMA） module to enhance cross-scale feature fusion and output accurate depth maps. Experimental results on the KITTI datasets show that， compared to Lapdepth， FCMdepth achieves lower values for the three error metrics： Root Mean Square Error （RMSE）， Root Mean Square Logarithmic Error （Log_RMSE），and Square Relative error （Sq_Rel）， with reductions of 0.831， 0.009， and 0.145， respectively， and improves three accuracy metrics by of 0.4， 0.8， and 0.3 percentage points， respectively. It can be seen that FCMdepth has superior performance compared to other models in most metrics and provides an effective reference for monocular depth estimation and 3D reconstruction in complex scenes.

Key words: monocular depth estimation, multi-scale attention mechanism, deep learning, encoder-decoder structure, multi-scale feature

摘要：

针对单目深度估计中特征提取不足和上下文建模不充分的问题，提出一种融合多尺度特征的单目深度估计框架FCMdepth，以提升预测性能。FCMdepth采用编码器-解码器（ED）结构，编码器FC-Net由MobileNetV3-F与CDBlock组成，通过多尺度特征及空洞卷积优化特征；解码器LapMA-Net结合拉普拉斯金字塔与高效多尺度注意力（EMA）模块，以增强跨尺度特征融合，并输出准确深度图。在KITTI数据集上的实验结果表明，FCMdepth相较于Lapdepth，均方根误差（RMSE）、对数均方根误差（Log_RMSE）和平方相对误差（Sq_Rel）这3项误差指标分别低0.831、0.009和0.145，3项准确率指标的均值分别提高0.4、0.8和0.3个百分点。可见，FCMdepth在多数指标上优于对比模型，为单目深度估计和复杂场景的三维重建提供了有效参考。

关键词: 单目深度估计, 多尺度注意力机制, 深度学习, 编码器-解码器结构, 多尺度特征

CLC Number:

TP391.41

Fengchun LIU, Xinying SHAO, Chunying ZHANG, Liya WANG, Jing REN. FCMdepth： monocular depth estimation framework with multi-scale feature optimization[J]. Journal of Computer Applications, 2026, 46(8): 2603-2611.

刘凤春, 邵馨莹, 张春英, 王立亚, 任静. 多尺度特征优化的单目深度估计框架FCMdepth[J]. 《计算机应用》唯一官方网站, 2026, 46(8): 2603-2611.

Figures/Tables 14

References 30

[1]	Ming Y， Meng X， Fan C， et al. Deep learning for monocular depth estimation： a review［J］. Neurocomputing， 2021， 438： 14-33.
[2]	Duan Z， Chen Y， Yu H， et al. RGB-Fusion： monocular 3D reconstruction with learned depth prediction［J］. Displays， 2021， 70： No.102100.
[3]	Long X， Liu L， Li W， et al. Multi-view depth estimation using epipolar spatio-temporal networks［C］// CVPR 2021. Piscataway： IEEE， 2021： 8254-8263.
[4]	Wang H， Yang M， Zhu C， et al. RGB-guided depth map recovery by two-stage coarse-to-fine dense CRF models［J］. IEEE Transactions on Image Processing， 2023， 32： 1315-1328.
[5]	Dong X， Garratt M A， Anavatti S G， et al. Towards real-time monocular depth estimation for robotics： a survey［J］. IEEE Transactions on Intelligent Transportation Systems， 2022， 23（10）： 16940-16961.
[6]	Zhang N， Nex F， Vosselman G， et al. Lite-Mono： a lightweight CNN and Transformer architecture for self-supervised monocular depth estimation［C］// CVPR 2023. Piscataway： IEEE， 2023： 18537-18546.
[7]	Yang L， Kang B， Huang Z， et al. Depth Anything： unleashing the power of large-scale unlabeled data［C］// CVPR 2024. Piscataway： IEEE， 2024： 10371-10381.
[8]	Wang J， Liu J， Tang D， et al. Scalable autoregressive monocular depth estimation［C］// CVPR 2025. Piscataway： IEEE， 2025： 6262-6272.
[9]	李文举，李梦颖，崔柳，等. 基于金字塔分割注意力网络的单目深度估计方法［J］. 计算机应用， 2023， 43（6）： 1736-1742.
	Li Wenju， Li Mengying， Cui Liu， et al. Monocular depth estimation method based on pyramid split attention network［J］. Journal of Computer Applications， 2023， 43（6）： 1736-1742.
[10]	肖磊，胡鹏，马俊杰. 局部注意力作用下基于全局信息关联的自监督单目深度估计模型［J］. 激光与光电子学进展， 2025， 62（8）： No.0815010.
	Xiao Lei， Hu Peng， Ma Junjie. Self-supervised monocular depth estimation model based on global information correlation under influence of local attention［J］. Laser and Optoelectronics Progress， 2025， 62（8）： No.0815010.
[11]	Song M， Lim S， Kim W. Monocular depth estimation using Laplacian pyramid-based depth residuals［J］. IEEE Transactions on Circuits and Systems for Video Technology， 2021， 31（11）： 4381-4393.
[12]	Zhu Y， Ren R， Dong W， et al. TSUDepth： exploring temporal symmetry-based uncertainty for unsupervised monocular depth estimation［J］. Neurocomputing， 2024， 600： No.128165.
[13]	Lu J， Huang T， Li P， et al. Align3R： aligned monocular depth estimation for dynamic videos［C］// CVPR 2025.Piscataway： IEEE， 2025： 22820-22830.
[14]	熊炜，陈奕博，张丽真，等. 利用多帧序列影像的自监督单目深度估计［J］. 计算机应用， 2024， 44（12）： 3907-3914.
	Xiong Wei， Chen Yibo， Zhang Lizhen， et al. Self-supervised monocular depth estimation using multi-frame sequence images［J］. Journal of Computer Applications， 2024， 44（12）： 3907-3914.
[15]	Hwang S J， Park S J， Baek J H， et al. Self-supervised monocular depth estimation using hybrid Transformer encoder［J］. IEEE Sensors Journal， 2022， 22（19）： 18762-18770.
[16]	Li Z， Wang X， Liu X， et al. BinsFormer： revisiting adaptive bins for monocular depth estimation［J］. IEEE Transactions on Image Processing， 2024， 33： 3964-3976.
[17]	Zhao C， Zhang Y， Poggi M， et al. MonoViT： self-supervised monocular depth estimation with a Vision Transformer［C］// 3DV 2022. Piscataway： IEEE， 2022： 668-678.
[18]	Li Z， Chen Z， Liu X， et al. DepthFormer： exploiting long-range correlation and local information for accurate monocular depth estimation［J］. Machine Intelligence Research， 2023， 20（6）： 837-854.
[19]	Lyu X， Liu L， Wang M， et al. HR-depth： high resolution self-supervised monocular depth estimation［J］. Proceedings of the AAAI Conference on Artificial Intelligence， 2021， 35（3）： 2294-2301.
[20]	Godard C， Mac Aodha O， Firman M， et al. Digging into self-supervised monocular depth estimation［C］// ICCV 2019. Piscataway： IEEE， 2019： 3827-3837.
[21]	Spencer J， Tosi F， Poggi M， et al. The third Monocular Depth Estimation Challenge［C］// CVPRW 2024. Piscataway： IEEE， 2024： 1-14.
[22]	Lopez J， Vargas E， Arguello H. Depth estimation from a single optical encoded image using a learned colored-coded aperture［J］. IEEE Transactions on Computational Imaging， 2024， 10： 752-761.
[23]	Devanshi C， Panchal D， Patel J， et al. AI-based object measurement using MiDaS depth estimation and MobileNetV3 edge detection［J］. International Journal on Science and Technology， 2025， 16（2）： No.3924.
[24]	Zehra R， Sharma O， Vinayak， et al. MobileNet-V3： a comprehensive survey of object detection algorithms using CNN［M］// Emerging trends in computer science and its application. Boca Raton， FL： CRC Press， 2025： 362-366.
[25]	Howard A， Sandler M， Chen B， et al. Searching for MobileNetV3［C］// ICCV 2019. Piscataway： IEEE， 2019： 1314-1324.
[26]	Spencer J， Qian C S， Russell C， et al. The monocular depth estimation challenge［C］// WACVW 2023. Piscataway： IEEE， 2023： 623-632.
[27]	Arampatzakis V， Pavlidis G， Mitianoudis N， et al. Monocular depth estimation： a thorough review［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2024， 46（4）： 2396-2414.
[28]	余伟群，刘佳涛，张亚萍. 融合注意力的拉普拉斯金字塔单目深度估计［J］. 图学学报， 2023， 44（4）： 728-738.
	Yu Weiqun， Liu Jiatao， Zhang Yaping. Monocular depth estimation based on Laplacian pyramid with attention fusion［J］. Journal of Graphics， 2023， 44（4）： 728-738.
[29]	Ouyang D， He S， Zhang G， et al. Efficient multi-scale attention module with cross-spatial learning［C］// ICASSP 2023. Piscataway： IEEE， 2023： 1-5.
[30]	Shao S， Pei Z， Chen W， et al. MonoDiffusion： self-supervised monocular depth estimation using diffusion model［J］. IEEE Transactions on Circuits and Systems for Video Technology， 2025， 35（4）： 3664-3678.

轮次	RMSE	Log_RMSE	Abs_Rel	Sq_Rel	Acc1/%	Acc2/%	Acc3/%
1	6.412	0.313	0.274	2.266	64.3	84.7	93.7
5	4.170	0.189	0.130	0.694	83.1	95.4	98.7
10	3.695	0.166	0.116	0.563	86.1	96.8	99.1
15	3.635	0.160	0.107	0.496	87.4	97.1	99.2
20	3.486	0.157	0.108	0.495	87.8	97.2	99.3
30	3.515	0.154	0.104	0.469	88.1	97.4	99.3
35	3.164	0.143	0.099	0.407	89.6	98.0	99.5

轮次	RMSE	Log_RMSE	Abs_Rel	Sq_Rel	Acc1/%	Acc2/%	Acc3/%
1	6.412	0.313	0.274	2.266	64.3	84.7	93.7
5	4.170	0.189	0.130	0.694	83.1	95.4	98.7
10	3.695	0.166	0.116	0.563	86.1	96.8	99.1
15	3.635	0.160	0.107	0.496	87.4	97.1	99.2
20	3.486	0.157	0.108	0.495	87.8	97.2	99.3
30	3.515	0.154	0.104	0.469	88.1	97.4	99.3
35	3.164	0.143	0.099	0.407	89.6	98.0	99.5

实验	MobileNetV3	ASPP	ASPP1	ASPP2	LP结构	MovbileNetV3-F	CDBlock	带EMA模块的LP结构	RMSE	Log_RMSE	Abs_Rel	Sq_Rel	Acc1/%	Acc2/%	Acc3/%
实验1	√	×	×	×	×	×	√	√	3.356	0.150	0.102	0.449	88.9	97.6	99.4
实验2	×	√	×	×	√	√	×	×	3.825	0.173	0.121	0.602	85.1	96.4	99.1
实验3	×	×	×	×	√	√	×	×	3.803	0.171	0.120	0.574	85.7	96.6	99.1
实验4	√	×	×	×	√	×	√	×	3.267	0.182	0.132	0.447	84.7	95.7	99.2
实验5	√	×	×	×	×	×	×	√	4.000	0.181	0.130	0.646	84.1	96.0	98.9
实验6	×	×	×	×	×	√	×	√	3.272	0.147	0.101	0.433	89.2	97.7	99.4
实验7	√	√	×	×	√	×	×	×	4.114	0.188	0.136	0.726	82.7	95.4	98.7
实验8	×	×	×	×	√	√	√	×	3.416	0.154	0.107	0.462	87.9	97.4	99.4
实验9	√	×	×	×	√	×	×	×	4.570	0.213	0.160	0.951	79.1	93.6	98.0
实验10	√	×	√	×	√	×	×	×	5.849	0.250	0.177	1.195	70.3	90.8	97.5
实验11	√	×	×	√	√	×	×	×	3.188	0.175	0.125	0.624	88.4	96.2	99.0
实验12	√	×	×	√	×	×	×	√	3.500	0.160	0.115	0.533	87.2	97.2	99.3
实验13	√	×	√	×	×	×	×	√	3.682	0.175	0.132	0.601	84.4	96.3	99.0
实验14	×	×	×	√	√	√	×	×	3.365	0.153	0.106	0.458	88.1	97.4	99.4
实验15	×	×	√	×	√	√	×	×	3.367	0.152	0.106	0.455	88.3	97.5	99.4
实验16	×	×	√	×	×	√	×	√	3.297	0.148	0.101	0.433	89.0	97.8	99.4
实验17	×	×	×	√	×	√	×	√	3.240	0.148	0.104	0.429	88.6	97.7	99.5
实验18	×	√	×	×	×	√	×	√	3.790	0.146	0.105	0.416	89.2	97.9	99.5
实验19	√	√	×	×	×	×	×	√	3.518	0.161	0.113	0.503	87.1	97.1	99.3
实验20 （FCMdepth）	×	×	×	×	×	√	√	√	3.164	0.143	0.099	0.407	89.6	98.0	99.5

实验	MobileNetV3	ASPP	ASPP1	ASPP2	LP结构	MovbileNetV3-F	CDBlock	带EMA模块的LP结构	RMSE	Log_RMSE	Abs_Rel	Sq_Rel	Acc1/%	Acc2/%	Acc3/%
实验1	√	×	×	×	×	×	√	√	3.356	0.150	0.102	0.449	88.9	97.6	99.4
实验2	×	√	×	×	√	√	×	×	3.825	0.173	0.121	0.602	85.1	96.4	99.1
实验3	×	×	×	×	√	√	×	×	3.803	0.171	0.120	0.574	85.7	96.6	99.1
实验4	√	×	×	×	√	×	√	×	3.267	0.182	0.132	0.447	84.7	95.7	99.2
实验5	√	×	×	×	×	×	×	√	4.000	0.181	0.130	0.646	84.1	96.0	98.9
实验6	×	×	×	×	×	√	×	√	3.272	0.147	0.101	0.433	89.2	97.7	99.4
实验7	√	√	×	×	√	×	×	×	4.114	0.188	0.136	0.726	82.7	95.4	98.7
实验8	×	×	×	×	√	√	√	×	3.416	0.154	0.107	0.462	87.9	97.4	99.4
实验9	√	×	×	×	√	×	×	×	4.570	0.213	0.160	0.951	79.1	93.6	98.0
实验10	√	×	√	×	√	×	×	×	5.849	0.250	0.177	1.195	70.3	90.8	97.5
实验11	√	×	×	√	√	×	×	×	3.188	0.175	0.125	0.624	88.4	96.2	99.0
实验12	√	×	×	√	×	×	×	√	3.500	0.160	0.115	0.533	87.2	97.2	99.3
实验13	√	×	√	×	×	×	×	√	3.682	0.175	0.132	0.601	84.4	96.3	99.0
实验14	×	×	×	√	√	√	×	×	3.365	0.153	0.106	0.458	88.1	97.4	99.4
实验15	×	×	√	×	√	√	×	×	3.367	0.152	0.106	0.455	88.3	97.5	99.4
实验16	×	×	√	×	×	√	×	√	3.297	0.148	0.101	0.433	89.0	97.8	99.4
实验17	×	×	×	√	×	√	×	√	3.240	0.148	0.104	0.429	88.6	97.7	99.5
实验18	×	√	×	×	×	√	×	√	3.790	0.146	0.105	0.416	89.2	97.9	99.5
实验19	√	√	×	×	×	×	×	√	3.518	0.161	0.113	0.503	87.1	97.1	99.3
实验20 （FCMdepth）	×	×	×	×	×	√	√	√	3.164	0.143	0.099	0.407	89.6	98.0	99.5

数据集名称	名称	参数量/10⁶	RMSE	Log_RMSE	Abs_Rel	Sq_Rel	lg error	Acc1/%	Acc2/%	Acc3/%
KITTI	Lapdepth^［11］	73.5	3.995	0.152	0.096	0.552		89.2	97.2	99.2
	Hr-depth^［19］	14.6	4.800	0.190	0.109	0.955		88.4	96.1	98.1
	Monodepth2^［20］	14.8	4.841	0.195	0.117	0.847		87.1	96.0	98.1
	Lite-mono^［6］	8.7	4.986	0.199	0.125	0.935		85.9	95.1	98.0
	TSUDepth^［12］	128.4	4.484	0.177	0.100	0.696		89.5	96.6	98.4
	Depth Anything^［7］	24.8	2.328	0.146	0.101	0.420		90.6	97.5	99.5
	FCMdepth	5.5	3.164	0.143	0.099	0.407		89.6	98.0	99.5
NYU-Depth V2	Lapdepth^［11］	73.5	0.439	0.054	0.111		0.055	88.1	96.8	99.2
	Hr-depth^［19］	14.6	0.572	0.060	0.151		0.076	88.4	96.1	98.1
	Monodepth2^［20］	14.8	0.731	1.131	2.121		1.256	81.6	95.3	97.2
	Lite-mono^［6］	8.7	0.457	0.049	0.118		0.093	87.8	96.3	98.8
	TSUDepth^［12］	128.4	0.433	0.064	0.147		0.083	88.9	96.6	98.4
	Depth Anything^［7］	24.8	0.384	0.035	0.105		0.069	89.1	97.3	99.0
	FCMdepth	5.5	0.367	0.031	0.101		0.047	89.2	97.5	99.1

FCMdepth： monocular depth estimation framework with multi-scale feature optimization

多尺度特征优化的单目深度估计框架FCMdepth

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 14

References 30

Related Articles 15

Recommended Articles

Metrics

[1]	Guanghui LI, Licheng QU. Dynamic dilated convolution and hierarchical local-global attention model based on improved Lite-Mono architecture [J]. Journal of Computer Applications, 2026, 46(8): 2567-2576.
[2]	Xiaojin GUO, Xuyang SUI, Kenan ZHOU. Channel estimation of STAR-RIS-assisted hybrid-field communication system based on deep learning [J]. Journal of Computer Applications, 2026, 46(8): 2548-2554.
[3]	Ming LIU, Dongqi SHEN, Ziyang MENG. Point cloud registration network with dual-branch multi-level feature fusion [J]. Journal of Computer Applications, 2026, 46(8): 2584-2593.
[4]	Wei LIU, Weigang LI, Zhiqiang TIAN. Representation learning method of hierarchical rotation-invariant geometric structure for point cloud classification and segmentation [J]. Journal of Computer Applications, 2026, 46(8): 2594-2602.
[5]	Xinliang LIU, Yushi XU, Dubai LI, Yanzhao REN. Survey of knowledge graph-based question answering methods [J]. Journal of Computer Applications, 2026, 46(8): 2394-2410.
[6]	Jing LIU, Shaoze ZHAO, Xingang LIU, Haozhe NIU, Haipeng JI. Cross-condition microstructure data generation method for titanium alloys based on improved CGAN [J]. Journal of Computer Applications, 2026, 46(7): 2373-2382.
[7]	Miaogen LING, Rui JING, Wei FANG. Survey of research on applications of explainable deep learning in tropical cyclone forecasting [J]. Journal of Computer Applications, 2026, 46(7): 2318-2326.
[8]	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.
[9]	Xiangyi WU, Hailiang YE, Feilong CAO. Point cloud completion method based on smooth-sharpen graph convolution [J]. Journal of Computer Applications, 2026, 46(7): 2267-2276.
[10]	Li ZHU, Lugema MI, Chunqiang ZHU, Wanru XU, Jingkai GAO, Jinqi QU. Short-term power load forecasting model based on dynamic convolution decomposition and multi-scale graph [J]. Journal of Computer Applications, 2026, 46(7): 2334-2346.
[11]	Yi DU, Mingjin XU, Jiayi KONG, Liyao WANG, Chen ZHAO. Low-rank adaptive parameter-efficient fine-tuning algorithm based on YOLOv11 [J]. Journal of Computer Applications, 2026, 46(6): 1738-1745.
[12]	Zhenkai XIONG, Mengjun XU, Yinyin SUN, Xin WANG. Maritime ship detection algorithm under complex weather environments based on enhanced YOLOv8 [J]. Journal of Computer Applications, 2026, 46(6): 1998-2006.
[13]	Lili HE, Meng CAO, Lei ZHANG, Hongjun PAN, Yi LIU, Chengxin SUN. Sign language generation model based on Kolmogorov-Arnold network and diffusion Transformer [J]. Journal of Computer Applications, 2026, 46(6): 1801-1810.
[14]	Chao LYU, Geyao MA. Lightweight human pose estimation network based on redundant feature suppression [J]. Journal of Computer Applications, 2026, 46(6): 1973-1980.
[15]	Xing SHENG, Sunxian WENG, Kuosong CHEN, Zhongping WANG, Ruifeng REN, Yong LIU. Deep learning-based patent value evaluation for power grid enterprises [J]. Journal of Computer Applications, 2026, 46(5): 1468-1474.