《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (12): 3978-3986.DOI: 10.11772/j.issn.1001-9081.2024111684
范宇, 陈纯毅, 胡小娟, 李延风, 于海洋, 张日培, 刘云彪
收稿日期:2024-12-02
修回日期:2025-03-23
接受日期:2025-04-01
发布日期:2025-04-08
出版日期:2025-12-10
通讯作者:
陈纯毅
作者简介:范宇(1994—),女,内蒙古阿尔山人,博士研究生,主要研究方向:计算机视觉、图像处理基金资助:Yu FAN, Chunyi CHEN, Xiaojuan HU, Yanfeng LI, Haiyang YU, Ripei ZHANG, Yunbiao LIU
Received:2024-12-02
Revised:2025-03-23
Accepted:2025-04-01
Online:2025-04-08
Published:2025-12-10
Contact:
Chunyi CHEN
About author:FAN Yu, born in 1994, Ph. D. candidate. Her research interests include computer vision, image processing.Supported by:摘要:
全景图像因投影形式特殊,存在严重的几何扭曲。现有2D图像超分辨率网络未考虑全景图像的几何扭曲特性,因此并不适用于全景图像的超分辨重建。与2D超分辨网络不同,全景图像超分辨模型需要关注不同纬度区域的特征差异,而且需要解决对不同尺度特征捕获不足和上下文信息未充分学习等问题。针对上述问题,提出一种基于信息补偿的全景图像超分辨率重建网络(ICPSnet)。首先,根据全景图像的几何特性引入位置感知机制,通过计算每个像素在纬度方向上的位置权重增强模型对不同纬度区域的关注;其次,为了解决不同尺度特征捕获不足的问题,设计一种跨尺度协同注意力(CSCA)模块,该模块利用不同感受野的多核卷积注意力机制获取丰富的跨尺度特征;此外,设计信息补偿(IC)块,通过改进空洞空间金字塔池化(ASPP),增强网络的上下文信息学习能力,从而提高重建图像质量。在2种基准数据集ODI-SR和SUN360上的实验结果表明,在放大因子为4倍、8倍时,ICPSnet的加权球面均匀信噪比(WS-PSNR)比当前最先进的OSRT(Omnidirectional image Super-Resolution Transformer)分别提高了0.14 dB、0.64 dB和0.25 dB、0.26 dB。可见,相较于其他网络,ICPSnet在视觉效果上表现更加优异,它重建的图像能够更好地展现高纬度区域的纹理细节。
中图分类号:
范宇, 陈纯毅, 胡小娟, 李延风, 于海洋, 张日培, 刘云彪. 基于信息补偿的全景图像超分辨率重建网络[J]. 计算机应用, 2025, 45(12): 3978-3986.
Yu FAN, Chunyi CHEN, Xiaojuan HU, Yanfeng LI, Haiyang YU, Ripei ZHANG, Yunbiao LIU. Information compensation-based panoramic image super-resolution reconstruction network[J]. Journal of Computer Applications, 2025, 45(12): 3978-3986.
| 网络 | ODI-SR数据集 | SUN360数据集 | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 放大因子为4倍 | 放大因子为8倍 | 放大因子为4倍 | 放大因子为8倍 | |||||||||||||
PSNR/ dB | SSIM | WS-PSNR/dB | WS-SSIM | PSNR/dB | SSIM | WS-PSNR/dB | WS-SSIM | PSNR/ dB | SSIM | WS-PSNR/dB | WS-SSIM | PSNR/dB | SSIM | WS-PSNR/dB | WS- SSIM | |
| Bicubic | 25.32 | 0.706 9 | 24.62 | 0.655 5 | 19.87 | 0.600 4 | 19.64 | 0.590 8 | 25.48 | 0.714 5 | 24.61 | 0.645 9 | 20.50 | 0.605 9 | 19.72 | 0.540 3 |
| SRCNN[ | 26.18 | 0.747 9 | 25.02 | 0.690 4 | 20.10 | 0.612 0 | 20.08 | 0.611 2 | 26.26 | 0.759 1 | 26.30 | 0.701 2 | 20.67 | 0.618 0 | 19.46 | 0.570 1 |
| VDSR[ | 26.51 | 0.748 4 | 25.92 | 0.700 9 | 21.43 | 0.647 3 | 21.19 | 0.633 4 | 26.14 | 0.762 8 | 26.36 | 0.705 7 | 21.27 | 0.624 2 | 21.60 | 0.609 1 |
| LapSRN[ | 26.73 | 0.755 9 | 25.87 | 0.694 5 | 21.98 | 0.642 4 | 20.72 | 0.621 4 | 26.73 | 0.761 4 | 26.31 | 0.700 0 | 22.11 | 0.637 4 | 20.05 | 0.599 8 |
| MemNet[ | 26.39 | 0.756 2 | 25.39 | 0.696 7 | 22.24 | 0.646 4 | 21.73 | 0.628 4 | 27.06 | 0.760 7 | 25.69 | 0.699 9 | 22.75 | 0.630 6 | 21.08 | 0.601 5 |
| MSRN[ | 26.47 | 0.764 4 | 25.51 | 0.700 3 | 23.50 | 0.657 4 | 23.34 | 0.649 6 | 27.07 | 0.761 2 | 25.91 | 0.705 1 | 23.29 | 0.644 0 | 23.19 | 0.647 7 |
| EDSR[ | 27.05 | 0.767 5 | 25.69 | 0.695 4 | 23.44 | 0.656 1 | 23.97 | 0.648 3 | 27.16 | 0.766 1 | 26.18 | 0.701 2 | 23.74 | 0.658 6 | 23.79 | 0.647 2 |
| D-DBPN[ | 26.85 | 0.764 6 | 25.50 | 0.693 2 | 23.61 | 0.659 4 | 24.15 | 0.657 3 | 27.21 | 0.762 7 | 25.92 | 0.698 7 | 23.75 | 0.650 9 | 23.70 | 0.642 1 |
| RCAN[ | 27.08 | 0.763 7 | 26.23 | 0.699 5 | 23.88 | 0.668 1 | 24.26 | 0.655 4 | 27.27 | 0.766 9 | 26.61 | 0.706 5 | 24.23 | 0.655 2 | 23.88 | 0.654 2 |
| DRN[ | 26.95 | 0.770 5 | 26.24 | 0.699 6 | 24.14 | 0.667 9 | 24.32 | 0.657 1 | 27.39 | 0.765 6 | 26.65 | 0.707 9 | 24.61 | 0.667 4 | 24.25 | 0.660 2 |
| 360-SS[ | 27.07 | 0.770 2 | 25.98 | 0.697 3 | 24.52 | 0.669 6 | 24.14 | 0.653 9 | 27.49 | 0.771 0 | 26.38 | 0.701 5 | 24.83 | 0.671 8 | 24.19 | 0.653 6 |
| LAU-Net[ | 27.21 | 0.772 8 | 26.34 | 0.705 2 | 24.71 | 0.670 5 | 0.660 2 | 27.51 | 0.775 9 | 26.48 | 0.706 2 | 25.04 | 24.24 | 0.670 8 | ||
| SPCR[ | 27.24 | 0.773 5 | 26.31 | 0.702 9 | 24.80 | 0.671 7 | 24.22 | 27.64 | 0.773 3 | 26.40 | 0.707 5 | 0.684 5 | 24.31 | 0.672 4 | ||
| OSRT[ | 25.19 | 24.25 | 0.658 9 | 27.82 | 25.01 | 0.681 3 | ||||||||||
| ICPSnet | 27.36 | 0.776 4 | 26.68 | 0.713 8 | 0.680 9 | 24.89 | 0.675 2 | 0.777 2 | 26.98 | 0.711 8 | 25.42 | 0.689 6 | 24.66 | 0.683 9 | ||
表1 不同放大因子时在2个数据集上的测试结果
Tab. 1 Test results of different amplification factors on two datasets
| 网络 | ODI-SR数据集 | SUN360数据集 | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 放大因子为4倍 | 放大因子为8倍 | 放大因子为4倍 | 放大因子为8倍 | |||||||||||||
PSNR/ dB | SSIM | WS-PSNR/dB | WS-SSIM | PSNR/dB | SSIM | WS-PSNR/dB | WS-SSIM | PSNR/ dB | SSIM | WS-PSNR/dB | WS-SSIM | PSNR/dB | SSIM | WS-PSNR/dB | WS- SSIM | |
| Bicubic | 25.32 | 0.706 9 | 24.62 | 0.655 5 | 19.87 | 0.600 4 | 19.64 | 0.590 8 | 25.48 | 0.714 5 | 24.61 | 0.645 9 | 20.50 | 0.605 9 | 19.72 | 0.540 3 |
| SRCNN[ | 26.18 | 0.747 9 | 25.02 | 0.690 4 | 20.10 | 0.612 0 | 20.08 | 0.611 2 | 26.26 | 0.759 1 | 26.30 | 0.701 2 | 20.67 | 0.618 0 | 19.46 | 0.570 1 |
| VDSR[ | 26.51 | 0.748 4 | 25.92 | 0.700 9 | 21.43 | 0.647 3 | 21.19 | 0.633 4 | 26.14 | 0.762 8 | 26.36 | 0.705 7 | 21.27 | 0.624 2 | 21.60 | 0.609 1 |
| LapSRN[ | 26.73 | 0.755 9 | 25.87 | 0.694 5 | 21.98 | 0.642 4 | 20.72 | 0.621 4 | 26.73 | 0.761 4 | 26.31 | 0.700 0 | 22.11 | 0.637 4 | 20.05 | 0.599 8 |
| MemNet[ | 26.39 | 0.756 2 | 25.39 | 0.696 7 | 22.24 | 0.646 4 | 21.73 | 0.628 4 | 27.06 | 0.760 7 | 25.69 | 0.699 9 | 22.75 | 0.630 6 | 21.08 | 0.601 5 |
| MSRN[ | 26.47 | 0.764 4 | 25.51 | 0.700 3 | 23.50 | 0.657 4 | 23.34 | 0.649 6 | 27.07 | 0.761 2 | 25.91 | 0.705 1 | 23.29 | 0.644 0 | 23.19 | 0.647 7 |
| EDSR[ | 27.05 | 0.767 5 | 25.69 | 0.695 4 | 23.44 | 0.656 1 | 23.97 | 0.648 3 | 27.16 | 0.766 1 | 26.18 | 0.701 2 | 23.74 | 0.658 6 | 23.79 | 0.647 2 |
| D-DBPN[ | 26.85 | 0.764 6 | 25.50 | 0.693 2 | 23.61 | 0.659 4 | 24.15 | 0.657 3 | 27.21 | 0.762 7 | 25.92 | 0.698 7 | 23.75 | 0.650 9 | 23.70 | 0.642 1 |
| RCAN[ | 27.08 | 0.763 7 | 26.23 | 0.699 5 | 23.88 | 0.668 1 | 24.26 | 0.655 4 | 27.27 | 0.766 9 | 26.61 | 0.706 5 | 24.23 | 0.655 2 | 23.88 | 0.654 2 |
| DRN[ | 26.95 | 0.770 5 | 26.24 | 0.699 6 | 24.14 | 0.667 9 | 24.32 | 0.657 1 | 27.39 | 0.765 6 | 26.65 | 0.707 9 | 24.61 | 0.667 4 | 24.25 | 0.660 2 |
| 360-SS[ | 27.07 | 0.770 2 | 25.98 | 0.697 3 | 24.52 | 0.669 6 | 24.14 | 0.653 9 | 27.49 | 0.771 0 | 26.38 | 0.701 5 | 24.83 | 0.671 8 | 24.19 | 0.653 6 |
| LAU-Net[ | 27.21 | 0.772 8 | 26.34 | 0.705 2 | 24.71 | 0.670 5 | 0.660 2 | 27.51 | 0.775 9 | 26.48 | 0.706 2 | 25.04 | 24.24 | 0.670 8 | ||
| SPCR[ | 27.24 | 0.773 5 | 26.31 | 0.702 9 | 24.80 | 0.671 7 | 24.22 | 27.64 | 0.773 3 | 26.40 | 0.707 5 | 0.684 5 | 24.31 | 0.672 4 | ||
| OSRT[ | 25.19 | 24.25 | 0.658 9 | 27.82 | 25.01 | 0.681 3 | ||||||||||
| ICPSnet | 27.36 | 0.776 4 | 26.68 | 0.713 8 | 0.680 9 | 24.89 | 0.675 2 | 0.777 2 | 26.98 | 0.711 8 | 25.42 | 0.689 6 | 24.66 | 0.683 9 | ||
| CSCA | IC | AF | ODI-SR数据集 | SUN360数据集 | ||
|---|---|---|---|---|---|---|
| WS-PSNR/dB | WS-SSIM | WS-PSNR/dB | WS-SSIM | |||
| × | √ | √ | 25.97 | 0.709 4 | 26.33 | 0.700 6 |
| √ | × | √ | 25.84 | 0.705 5 | 26.52 | 0.708 9 |
| √ | √ | × | 26.61 | 0.711 4 | 26.82 | 0.705 0 |
| √ | √ | √ | 26.68 | 0.713 8 | 26.98 | 0.711 8 |
表2 4倍放大时的消融实验结果
Tab.2 Ablation experimental results at 4× amplification
| CSCA | IC | AF | ODI-SR数据集 | SUN360数据集 | ||
|---|---|---|---|---|---|---|
| WS-PSNR/dB | WS-SSIM | WS-PSNR/dB | WS-SSIM | |||
| × | √ | √ | 25.97 | 0.709 4 | 26.33 | 0.700 6 |
| √ | × | √ | 25.84 | 0.705 5 | 26.52 | 0.708 9 |
| √ | √ | × | 26.61 | 0.711 4 | 26.82 | 0.705 0 |
| √ | √ | √ | 26.68 | 0.713 8 | 26.98 | 0.711 8 |
| 序列 | ODI-SR数据集 | SUN360数据集 | ||
|---|---|---|---|---|
| WS-PSNR/dB | WS-SSIM | WS-PSNR/dB | WS-SSIM | |
| 1-3-5 | 24.89 | 0.675 2 | 24.40 | 0.681 6 |
| 1-3-7 | 24.59 | 0.677 3 | 24.15 | 0.682 7 |
| 3-5-7 | 24.37 | 0.678 5 | 24.33 | 0.680 8 |
表3 8倍放大时CSCA模块中不同核序列的性能比较
Tab.3 Performance comparison of different kernel sequences in CSCA module at 8× amplification
| 序列 | ODI-SR数据集 | SUN360数据集 | ||
|---|---|---|---|---|
| WS-PSNR/dB | WS-SSIM | WS-PSNR/dB | WS-SSIM | |
| 1-3-5 | 24.89 | 0.675 2 | 24.40 | 0.681 6 |
| 1-3-7 | 24.59 | 0.677 3 | 24.15 | 0.682 7 |
| 3-5-7 | 24.37 | 0.678 5 | 24.33 | 0.680 8 |
| 网络 | 参数量/MB | GFLOPs | 运行时间/s |
|---|---|---|---|
| SRCNN[ | 8.13 | 6.75 | 0.158 |
| VDSR[ | 1.15 | 612.60 | 0.326 |
| LapSRN[ | 1.30 | 23.00 | 0.049 |
| MemNet[ | 2.30 | 45.00 | 0.085 |
| MSRN[ | 6.20 | 294.80 | 0.078 |
| EDSR[ | 45.50 | 2 473.40 | 2.231 |
| D-DBPN[ | 23.20 | 766.40 | 0.682 |
| RCAN[ | 16.00 | 617.90 | 0.416 |
| DRN[ | 22.40 | 825.60 | 0.184 |
| 360-SS[ | 1.60 | 15.00 | 0.010 |
| LAU-Net[ | 9.40 | 342.80 | 0.352 |
| SPCR[ | 7.80 | 372.00 | 0.312 |
| OSRT[ | 12.10 | 423.70 | 0.842 |
| ICPSnet | 14.50 | 446.20 | 0.671 |
表4 不同网络的复杂度
Tab.4 Complexity of different networks
| 网络 | 参数量/MB | GFLOPs | 运行时间/s |
|---|---|---|---|
| SRCNN[ | 8.13 | 6.75 | 0.158 |
| VDSR[ | 1.15 | 612.60 | 0.326 |
| LapSRN[ | 1.30 | 23.00 | 0.049 |
| MemNet[ | 2.30 | 45.00 | 0.085 |
| MSRN[ | 6.20 | 294.80 | 0.078 |
| EDSR[ | 45.50 | 2 473.40 | 2.231 |
| D-DBPN[ | 23.20 | 766.40 | 0.682 |
| RCAN[ | 16.00 | 617.90 | 0.416 |
| DRN[ | 22.40 | 825.60 | 0.184 |
| 360-SS[ | 1.60 | 15.00 | 0.010 |
| LAU-Net[ | 9.40 | 342.80 | 0.352 |
| SPCR[ | 7.80 | 372.00 | 0.312 |
| OSRT[ | 12.10 | 423.70 | 0.842 |
| ICPSnet | 14.50 | 446.20 | 0.671 |
| [1] | WANG J, SHI R, LI X, et al. Omnidirectional virtual visual acuity: a user-centric visual clarity metric for virtual reality head-mounted displays and environments[J]. IEEE Transactions on Visualization and Computer Graphics, 2024, 30(5): 2033-2043. |
| [2] | WANG X, WANG S, LI J, et al. Omnidirectional image super-resolution via position attention network[J]. Neural Networks, 2024, 178: No.106464. |
| [3] | AGRAHARI BANIYA A, LEE T K, EKLUND P W, et al. Omnidirectional video super-resolution using deep learning[J]. IEEE Transactions on Multimedia, 2024, 26: 540-554. |
| [4] | FAN Y, CHEN C. OmiQnet: multiscale feature aggregation convolutional neural network for omnidirectional image assessment[J]. Applied Intelligence, 2024, 54(7): 5711-5727. |
| [5] | DENG X, WANG H, XU M, et al. LAU-Net: latitude adaptive upscaling network for omnidirectional image super-resolution[C]// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 9185-9194. |
| [6] | YU F, WANG X, CAO M, et al. OSRT: omnidirectional image super-resolution with distortion-aware transformer[C]// Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 13283-13292. |
| [7] | DONG C, LOY C C, HE K, et al. Image super-resolution using deep convolutional networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2): 295-307. |
| [8] | KIM J, LEE J K, LEE K M. Accurate image super-resolution using very deep convolutional networks[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 1646-1654. |
| [9] | LAI W S, HUANG J B, AHUJA N, et al. Deep Laplacian pyramid networks for fast and accurate super-resolution[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 5835-5843. |
| [10] | TAI Y, YANG J, LIU X, et al. MemNet: a persistent memory network for image restoration[C]// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 4549-4557. |
| [11] | LI J, FANG F, MEI K, et al. Multi-scale residual network for image super-resolution[C]// Proceedings of the 2018 European Conference on Computer Vision, LNCS 11212. Cham: Springer, 2018: 527-542. |
| [12] | LIM B, SON S, KIM H, et al. Enhanced deep residual networks for single image super-resolution[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2017: 1132-1140. |
| [13] | HARIS M, SHAKHNAROVICH G, UKITA N. Deep back-projection networks for super-resolution[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 1664-1673. |
| [14] | ZHANG Y, LI K, LI K, et al. Image super-resolution using very deep residual channel attention networks[C]// Proceedings of the 2018 European Conference on Computer Vision, LNCS 11211. Cham: Springer, 2018: 294-310. |
| [15] | GUO Y, CHEN J, WANG J, et al. Closed-loop matters: dual regression networks for single image super-resolution[C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 5406-5415. |
| [16] | OZCINAR C, RANA A, SMOLIC A. Super-resolution of omnidirectional images using adversarial learning[C]// Proceedings of the IEEE 21st International Workshop on Multimedia Signal Processing. Piscataway: IEEE, 2019: 1-6. |
| [17] | YOON Y, CHUNG I, WANG L, et al. SphereSR: 360° image super-resolution with arbitrary projection via continuous spherical image representation[C]// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 5667-5676. |
| [18] | CHAI X, SHAO F, JIANG Q, et al. TCCL-Net: Transformer-convolution collaborative learning network for omnidirectional image super-resolution[J]. Knowledge-Based Systems, 2023, 274: No.110625. |
| [19] | QIAN L, LIU X, WU J, et al. 360-degree image super-resolution based on single image sample and progressive residual generative adversarial network[C]// Proceedings of the 7th International Conference on Image, Vision and Computing. Piscataway: IEEE, 2022: 654-661. |
| [20] | 刘子涵,周登文,刘玉铠. 基于全局依赖Transformer的图像超分辨率网络[J]. 计算机应用, 2024, 44(5): 1588-1596. |
| LIU Z H, ZHOU D W, LIU Y K. Image super-resolution network based on global dependency Transformer[J]. Journal of Computer Applications, 2024, 44(5): 1588-1596. | |
| [21] | 陈豪,夏振平,程成,等. 基于Transformer-CNN的轻量级图像超分辨率重建网络[J]. 计算机应用, 2024, 44(1): 292-299. |
| CHEN H, XIA Z P, CHENG C, et al. Lightweight image super-resolution reconstruction network based on Transformer-CNN[J]. Journal of Computer Applications, 2024, 44(1): 292-299. | |
| [22] | QIU Y, LIU Y, CHEN Y, et al. A2SPPNet: attentive atrous spatial pyramid pooling network for salient object detection[J]. IEEE Transactions on Multimedia, 2023, 25: 1991-2006. |
| [23] | SONG X, FANG X, MENG X, et al. Real-time semantic segmentation network with an enhanced backbone based on atrous spatial pyramid pooling module[J]. Engineering Applications of Artificial Intelligence, 2024, 133(Pt A): No.107988. |
| [24] | HU Y, HUANG Y, ZHANG K. Multi-scale information distillation network for efficient image super-resolution[J]. Knowledge-Based Systems, 2023, 275: No.110718. |
| [25] | SUN Y, LU A, YU L. Weighted-to-spherically-uniform quality evaluation for omnidirectional video[J]. IEEE Signal Processing Letters, 2017, 24(9): 1408-1412. |
| [26] | ZHOU Y, YU M, MA H, et al. Weighted-to-spherically-uniform SSIM objective quality evaluation for panoramic video[C]// Proceedings of the 14th IEEE International Conference on Signal Processing. Piscataway: IEEE, 2018: 54-57. |
| [27] | CAI Q, LI M, REN D, et al. Spherical pseudo-cylindrical representation for omnidirectional image super-resolution[C]// Proceedings of the 38th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2024: 873-881. |
| [1] | 李维刚, 邵佳乐, 田志强. 基于双注意力机制和多尺度融合的点云分类与分割网络[J]. 《计算机应用》唯一官方网站, 2025, 45(9): 3003-3010. |
| [2] | 王翔, 陈志祥, 毛国君. 融合局部和全局相关性的多变量时间序列预测方法[J]. 《计算机应用》唯一官方网站, 2025, 45(9): 2806-2816. |
| [3] | 邓伊琳, 余发江. 基于LSTM和可分离自注意力机制的伪随机数生成器[J]. 《计算机应用》唯一官方网站, 2025, 45(9): 2893-2901. |
| [4] | 吕景刚, 彭绍睿, 高硕, 周金. 复频域注意力和多尺度频域增强驱动的语音增强网络[J]. 《计算机应用》唯一官方网站, 2025, 45(9): 2957-2965. |
| [5] | 敬超, 全育涛, 陈艳. 基于多层感知机-注意力模型的功耗预测算法[J]. 《计算机应用》唯一官方网站, 2025, 45(8): 2646-2655. |
| [6] | 林进浩, 罗川, 李天瑞, 陈红梅. 基于跨尺度注意力网络的胸部疾病分类方法[J]. 《计算机应用》唯一官方网站, 2025, 45(8): 2712-2719. |
| [7] | 吴海峰, 陶丽青, 程玉胜. 集成特征注意力和残差连接的偏标签回归算法[J]. 《计算机应用》唯一官方网站, 2025, 45(8): 2530-2536. |
| [8] | 周金, 李玉芝, 张徐, 高硕, 张立, 盛家川. 复杂电磁环境下的调制识别网络[J]. 《计算机应用》唯一官方网站, 2025, 45(8): 2672-2682. |
| [9] | 梁辰, 王奕森, 魏强, 杜江. 基于Transformer-GCN的源代码漏洞检测方法[J]. 《计算机应用》唯一官方网站, 2025, 45(7): 2296-2303. |
| [10] | 王艺涵, 路翀, 陈忠源. 跨模态文本信息增强的多模态情感分析模型[J]. 《计算机应用》唯一官方网站, 2025, 45(7): 2237-2244. |
| [11] | 刘皓宇, 孔鹏伟, 王耀力, 常青. 基于多视角信息的行人检测算法[J]. 《计算机应用》唯一官方网站, 2025, 45(7): 2325-2332. |
| [12] | 赵小强, 柳勇勇, 惠永永, 刘凯. 基于改进时域卷积网络与多头自注意力机制的间歇过程质量预测模型[J]. 《计算机应用》唯一官方网站, 2025, 45(7): 2245-2252. |
| [13] | 王慧斌, 胡展傲, 胡节, 徐袁伟, 文博. 基于分段注意力机制的时间序列预测模型[J]. 《计算机应用》唯一官方网站, 2025, 45(7): 2262-2268. |
| [14] | 翟社平, 黄妍, 杨晴, 杨锐. 融合三元组和文本属性的多视图实体对齐[J]. 《计算机应用》唯一官方网站, 2025, 45(6): 1793-1800. |
| [15] | 王向, 崔倩倩, 张晓明, 王建超, 王震洲, 宋佳霖. 改进ConvNeXt的无线胶囊内镜图像分类模型[J]. 《计算机应用》唯一官方网站, 2025, 45(6): 2016-2024. |
| 阅读次数 | ||||||
|
全文 |
|
|||||
|
摘要 |
|
|||||