Query：
所有字段：(空)
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
为解决生成对抗网络训练过程中因损失简单加权导致的图像感知质量下降问题,提出损失自适应调整的生成对抗超分辨率网络(LA-GAN).首先,该方法设计通过计算角点分布的相关强度大小,区分规则纹理区域与不规则纹理区域.其次,基于不同区域,设计了区域自适应生成对抗学习框架.在该框架中,网络只在不规则纹理区域中进行对抗学习,提高感知质量.此外,基于下采样图像和图像块相似性的重组图像取代训练集中的高分辨率图像,实现平均绝对损失在不规则纹理区域弱约束网络,在规则纹理区域强约束网络,保证图像信号保真度.最后,通过实验证明经过优化的网络在信号保真度和感知质量方面皆有提升.
Keyword ：
区域自适应 区域自适应 损失函数 损失函数 生成对抗网络 生成对抗网络 超分辨率 超分辨率
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 林旭锋 , 吴丽君 , 陈志聪 et al. 损失自适应的高感知质量生成对抗超分辨率网络 [J]. | 福州大学学报（自然科学版） , 2025 , 53 (1) : 26-34 . |
| MLA | 林旭锋 et al. "损失自适应的高感知质量生成对抗超分辨率网络" . | 福州大学学报（自然科学版） 53 . 1 (2025) : 26-34 . |
| APA | 林旭锋 , 吴丽君 , 陈志聪 , 林培杰 , 程树英 . 损失自适应的高感知质量生成对抗超分辨率网络 . | 福州大学学报（自然科学版） , 2025 , 53 (1) , 26-34 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In the field of image super-resolution (SR), deep learning-based models have achieved remarkable success. However, these models often face compatibility issues with low-power devices due to their computational and memory constraints. To address this challenge, numerous lightweight and efficient models have been proposed. While these models typically employ smaller convolutional kernels and shallower architectures to reduce parameter counts and computational complexity, they often neglect the importance of capturing global receptive fields. In this paper, we propose a simple yet effective deep network, termed the dilated-convolutional feature modulation network (DCFMN), to tackle these limitations. Specifically, we introduce a dilated separable modulation unit (DSMU) to aggregate spatial information from diverse large receptive fields. To complement the DSMU, which processes features from a long-range perspective, we further design a local feature enhancement module (LFEM) to extract local contextual information for effective channel fusion. Additionally, by leveraging reparameterization techniques, we ensure that the model incurs no additional computational overhead during inference. Extensive experimental results demonstrate that our DCFMN achieves competitive performance among existing efficient SR methods, while maintaining a compact model size and low computational complexity.
Keyword ：
Deep learning Deep learning Image super-resolution Image super-resolution Lightweight Lightweight Reparameterization Reparameterization
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wu, Lijun , Li, Shan , Chen, Zhicong . Dilated-convolutional feature modulation network for efficient image super-resolution [J]. | JOURNAL OF REAL-TIME IMAGE PROCESSING , 2025 , 22 (2) . |
| MLA | Wu, Lijun et al. "Dilated-convolutional feature modulation network for efficient image super-resolution" . | JOURNAL OF REAL-TIME IMAGE PROCESSING 22 . 2 (2025) . |
| APA | Wu, Lijun , Li, Shan , Chen, Zhicong . Dilated-convolutional feature modulation network for efficient image super-resolution . | JOURNAL OF REAL-TIME IMAGE PROCESSING , 2025 , 22 (2) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Recently, CNN-Transformer hybrid network has been proposed to resolve either the heavy computational burden of CNN or the difficulty encountered during training the Transformer-based networks. In this work, we design an efficient and effective CNN-Transformer hybrid network for human pose estimation, namely CTHPose. Specifically, Polarized CNN Module is employed to extract the feature with plentiful visual semantic clues, which is beneficial for the convergence of the subsequent Transformer encoders. Pyramid Transformer Module is utilized to build the long-term relationship between human body parts with lightweight structure and less computational complexity. To establish long-term relationship, large field of view is necessary in Transformer, which leads to a large computational workload. Hence, instead of the entire feature map, we introduced a reorganized small sliding window to provide the required large field of view. Finally, Heatmap Generator is designed to reconstruct the 2D heatmaps from the 1D keypoint representation, which balances parameters and FLOPs while obtaining accurate prediction. According to quantitative comparison experiments with CNN estimators, CTHPose significantly reduces the number of network parameters and GFLOPs, while also providing better detection accuracy. Compared with mainstream pure Transformer networks and state-of-the-art CNN-Transformer hybrid networks, this network also has competitive performance, and is more robust to the clothing pattern interference and overlapping limbs from the visual perspective.
Keyword ：
Human pose estimation Human pose estimation Long-range dependency Long-range dependency Transformer Transformer
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Danya , Wu, Lijun , Chen, Zhicong et al. CTHPose: An Efficient and Effective CNN-Transformer Hybrid Network for Human Pose Estimation [J]. | PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2023, PT V , 2024 , 14429 : 327-339 . |
| MLA | Chen, Danya et al. "CTHPose: An Efficient and Effective CNN-Transformer Hybrid Network for Human Pose Estimation" . | PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2023, PT V 14429 (2024) : 327-339 . |
| APA | Chen, Danya , Wu, Lijun , Chen, Zhicong , Lin, Xufeng . CTHPose: An Efficient and Effective CNN-Transformer Hybrid Network for Human Pose Estimation . | PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2023, PT V , 2024 , 14429 , 327-339 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
To address the problem of incomplete segmentation of large objects and miss-segmentation of tiny objects that is universally existing in semantic segmentation algorithms, PACAMNet, a real-time segmentation network based on short-term dense concatenate of parallel atrous convolution and fusion of attentional features is proposed, called PACAMNet. First, parallel atrous convolution is introduced to improve the short-term dense concatenate module. By adjusting the size of the atrous factor, multi-scale semantic information is obtained to ensure that the last layer of the module can also obtain rich input feature maps. Second, attention feature fusion module is proposed to align the receptive fields of deep and shallow feature maps via depth-separable convolutions with different sizes, and the channel attention mechanism is used to generate weights to effectively fuse the deep and shallow feature maps. Finally, experiments are carried out based on both Cityscapes and CamVid datasets, and the segmentation accuracy achieve 77.4% and 74.0% at the inference speeds of 98.7 FPS and 134.6 FPS, respectively. Compared with other methods, PACAMNet improves the inference speed of the model while ensuring higher segmentation accuracy, so PACAMNet achieve a better balance between segmentation accuracy and inference speed.
Keyword ：
Atrous convolution Atrous convolution Attention mechanism Attention mechanism Feature fusion Feature fusion Real-time semantic segmentation Real-time semantic segmentation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wu, Lijun , Qiu, Shangdong , Chen, Zhicong . Real-time semantic segmentation network based on parallel atrous convolution for short-term dense concatenate and attention feature fusion [J]. | JOURNAL OF REAL-TIME IMAGE PROCESSING , 2024 , 21 (3) . |
| MLA | Wu, Lijun et al. "Real-time semantic segmentation network based on parallel atrous convolution for short-term dense concatenate and attention feature fusion" . | JOURNAL OF REAL-TIME IMAGE PROCESSING 21 . 3 (2024) . |
| APA | Wu, Lijun , Qiu, Shangdong , Chen, Zhicong . Real-time semantic segmentation network based on parallel atrous convolution for short-term dense concatenate and attention feature fusion . | JOURNAL OF REAL-TIME IMAGE PROCESSING , 2024 , 21 (3) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
为提高户外光伏电站现场退化评估的准确性和可靠性,提出一种物理和数据驱动的光伏组件性能退化模型.研究户外光伏组件受静态温度、循环温度、相对湿度和紫外线影响的特性,并综合动态应力函数,利用累积损失模型对多应力下光伏电站性能退化进行建模.此外,退化模型的未知参数通过遗传算法来提取.使用美国国家太阳辐射数据库的长期数据对该模型进行训练和测试.将性能退化实际值和模型计算值进行对比,结果表明,本研究所提出模型的相对误差更低,验证了该方法的可行性.
Keyword ：
优化算法 优化算法 光伏电站 光伏电站 光伏退化 光伏退化 数据驱动 数据驱动
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 王宇钖 , 陈志聪 , 吴丽君 et al. 利用物理和数据驱动的光伏性能退化建模方法 [J]. | 福州大学学报（自然科学版） , 2024 , 52 (5) : 513-519 . |
| MLA | 王宇钖 et al. "利用物理和数据驱动的光伏性能退化建模方法" . | 福州大学学报（自然科学版） 52 . 5 (2024) : 513-519 . |
| APA | 王宇钖 , 陈志聪 , 吴丽君 , 俞金玲 , 程树英 , 林培杰 . 利用物理和数据驱动的光伏性能退化建模方法 . | 福州大学学报（自然科学版） , 2024 , 52 (5) , 513-519 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
提出一种基于图注意力网络(graph attention network,GAT)的光伏阵列故障诊断模型,以解决光伏阵列中因故障导致的发电效率降低、正常运行受阻等问题.通过离散小波变换和滑窗算法截取故障后稳态时序信号并将其分割成子区间,将子区间视为图节点.使用K邻近构图法将故障后稳态电压、电流数据转变成图结构,构建节点级GAT模型.通过多头注意力机制自动提取电压、电流图结构的故障特征.通过实验室光伏阵列获取实验数据集,对所提模型进行测试.结果表明,本模型能准确诊断光伏阵列的不同故障状态,平均准确率达到99.790％,效果优于所对比的其他网络模型.
Keyword ：
光伏阵列 光伏阵列 图神经网络 图神经网络 图结构 图结构 故障诊断 故障诊断 注意力机制 注意力机制
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 董浪灿 , 卢箫扬 , 林培杰 et al. 利用GAT的光伏阵列故障诊断方法 [J]. | 福州大学学报（自然科学版） , 2024 , 52 (5) : 505-512 . |
| MLA | 董浪灿 et al. "利用GAT的光伏阵列故障诊断方法" . | 福州大学学报（自然科学版） 52 . 5 (2024) : 505-512 . |
| APA | 董浪灿 , 卢箫扬 , 林培杰 , 程树英 , 陈志聪 , 吴丽君 . 利用GAT的光伏阵列故障诊断方法 . | 福州大学学报（自然科学版） , 2024 , 52 (5) , 505-512 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Super-resolution (SR) algorithms have been broadly applied to improve the visual quality of images. However, the unstable SR results and the difficulty of collecting high-resolution (HR) and low-resolution (LR) image pairs still greatly block its application in the position-sensitive downstream tasks in real world. To address these difficulties, we propose an unpaired image-based cross-domain supervised SR method for position-sensitive downstream tasks (CDS PosSR), which greatly improve the fidelity of geometric positions in the image based on the geometric consistency of the image. Since the different semantic information and root-mean-square error cannot constraint unpaired images during the degradation process, an unpaired image cross-domain supervised hierarchical degradation model is elaborated. Meanwhile, randomly distributed input is adopted, so as to alleviate the problem that the dataset cannot fully cover real-world LR images. According to the experimental results, CDS PosSR not only improves the visual and quantitative performance of the generated images but also outperforms other SR reconstruction algorithms in terms of the fidelity of feature point location and geometry, which can provide support for position-sensitive downstream tasks.
Keyword ：
Degradation learning Degradation learning geometric consistency geometric consistency unpaired image super-resolution (SR) unpaired image super-resolution (SR)
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wu, Lijun , Chen, Lanxin , Chen, Zhicong et al. CDS PosSR: Cross-Domain Supervised Unpaired Image Super-Resolution for Position-Sensitive Downstream Tasks [J]. | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT , 2024 , 73 . |
| MLA | Wu, Lijun et al. "CDS PosSR: Cross-Domain Supervised Unpaired Image Super-Resolution for Position-Sensitive Downstream Tasks" . | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 73 (2024) . |
| APA | Wu, Lijun , Chen, Lanxin , Chen, Zhicong , Cheng, Shuying , Chen, Zhaohui . CDS PosSR: Cross-Domain Supervised Unpaired Image Super-Resolution for Position-Sensitive Downstream Tasks . | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT , 2024 , 73 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Video super-resolution is capable of recovering high-resolution images from multiple low-resolution images, where loop structures are a common frame choice for video super-resolution tasks. BasicVSR employs bidirectional propagation and feature alignment to efficiently utilize information from the entire input video. In this work, we improved the performance of the network by revisiting the role of the various modules in BasicVSR and redesigning the network. Firstly, we will maintain centralized communication with the reference frame through the reference-based feature enrichment module after optical flow distortion, which is helpful for handling complex motion, and at the same time, for the selected keyframe, according to the degree of motion deviation of the adjacent frame relative to the keyframe, it is divided into two different regions, and the model with different receptive fields is adopted for feature extraction to further alleviate the accumulation of alignment errors. In the feature correction module, we modify the simple residual block stack to RIR structure, and fuse different levels of features with each other, which can make the final feature information more comprehensive and abundant. In addition, dense connection are introduced in the reconstruction module to promote the full use of hierarchical feature information for better reconstruction. Experimental verification is carried out on two public datasets: Vid4 and REDS4, and the comparative results show that compared with BasicVSR, the PSNR quantitative indexes of the proposed improved model on the two datasets are improved by 0.27dB and 0.33dB, respectively. In addition, from the point of view of visual perception, the model can effectively improve the clarity of the image and reduce artifacts.
Keyword ：
Bidirectional propagation Bidirectional propagation Densely connected residual Densely connected residual Feature enrichment module Feature enrichment module Time difference Time difference Video super-resolution Video super-resolution
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wu, Lijun , Ma, Yong , Chen, Zhicong . Dense video super-resolution time-differential network with feature enrichment module [J]. | SIGNAL IMAGE AND VIDEO PROCESSING , 2024 , 18 (11) : 7887-7897 . |
| MLA | Wu, Lijun et al. "Dense video super-resolution time-differential network with feature enrichment module" . | SIGNAL IMAGE AND VIDEO PROCESSING 18 . 11 (2024) : 7887-7897 . |
| APA | Wu, Lijun , Ma, Yong , Chen, Zhicong . Dense video super-resolution time-differential network with feature enrichment module . | SIGNAL IMAGE AND VIDEO PROCESSING , 2024 , 18 (11) , 7887-7897 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
基于二值化网络提出了轻量二值化钢铁缺陷分类网络(Lightweight Binarized Steel Defect Classification Network,LBSDC-Net),以期实现实时高精度的钢铁缺陷自动分类.首先,基于可变阈值符号函数和组卷积的理念,设计了双阈值型组卷积模块,以在压缩网络模型的同时最小化二值组卷积引起的信息损失,将基础网络模型大小降低了31.2%,精度仅下降0.34%;其次,通过调整下采样卷积的步长并结合最大池化,降低了残差网络中捷径分支下采样时的信息损失,提升了网络的分类性能;在NEU-CLS钢铁缺陷数据集上的实验结果表明,网络模型大小为11.86 MBit时,LBSDC-Net网络在钢铁缺陷分类任务中准确率达到 99.06%.相较于基础网络Bi-Real-Net 98.73%的准确率和17.23 MBit的网络模型大小,LBSDC-Net实现了网络规模的有效压缩,还提升了分类精度.
Keyword ：
二值神经网络 二值神经网络 分类 分类 深度学习 深度学习 轻量化 轻量化 钢铁缺陷 钢铁缺陷
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 卓晨涛 , 吴丽君 . 基于轻量化二值神经网络的钢铁表面缺陷分类 [J]. | 光电子技术 , 2024 , 44 (4) : 317-323 . |
| MLA | 卓晨涛 et al. "基于轻量化二值神经网络的钢铁表面缺陷分类" . | 光电子技术 44 . 4 (2024) : 317-323 . |
| APA | 卓晨涛 , 吴丽君 . 基于轻量化二值神经网络的钢铁表面缺陷分类 . | 光电子技术 , 2024 , 44 (4) , 317-323 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
提出一种基于高效通道注意(ECA)网络和双向长短期记忆神经网络(BILSTM)的自适应智慧路灯边缘计算模型.首先,在BILSTM的基础上,融合布谷鸟算法、通道注意力机制,构建CS-ECA-BILSTM能见度预测模型,实现道路能见度预测;其次,为普通路灯控制因子单一的问题引入照度和色温因子,提高控制效率并降低路灯能耗;最后,在边缘端引入云原生理念,使用KubeEdge框架与容器技术部署路灯控制模型到边缘端,从而实现多路灯控制.实验结果表明,所提出CS-ECA-BILSTM模型的性能优于其他对比模型,可有效提高路灯能源利用率,且能实现在边缘端的运行.
Keyword ：
双向长短期记忆神经网络 双向长短期记忆神经网络 容器技术 容器技术 智慧路灯 智慧路灯 注意力机制 注意力机制 边缘计算 边缘计算
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 郭泽鑫 , 林培杰 , 程树英 et al. 基于CS-ECA-BILSTM与KubeEdge的自适应智慧路灯边缘计算模型 [J]. | 福州大学学报（自然科学版） , 2024 , 52 (6) : 667-673 . |
| MLA | 郭泽鑫 et al. "基于CS-ECA-BILSTM与KubeEdge的自适应智慧路灯边缘计算模型" . | 福州大学学报（自然科学版） 52 . 6 (2024) : 667-673 . |
| APA | 郭泽鑫 , 林培杰 , 程树英 , 陈志聪 , 吴丽君 . 基于CS-ECA-BILSTM与KubeEdge的自适应智慧路灯边缘计算模型 . | 福州大学学报（自然科学版） , 2024 , 52 (6) , 667-673 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
