为解决自然条件下人脸表情识别易受角度、光线、遮挡物的影响以及人脸表情数据集各类表情数量不均衡等问题,提出基于Res2Net的人脸表情识别方法。使用Res2Net50作为特征提取的主干网络,在预处理阶段对图像随机翻转、缩放、裁剪进行数据...为解决自然条件下人脸表情识别易受角度、光线、遮挡物的影响以及人脸表情数据集各类表情数量不均衡等问题,提出基于Res2Net的人脸表情识别方法。使用Res2Net50作为特征提取的主干网络,在预处理阶段对图像随机翻转、缩放、裁剪进行数据增强,提升模型的泛化性。引入广义平均池化(generalized mean pooling, GeM)方式,关注图像中比较显著的区域,增强模型的鲁棒性;选用Focal Loss损失函数,针对表情类别不平衡和错误分类问题,提高较难识别表情的识别率。该方法在FER2013数据集上准确率达到了70.41%,相较于原Res2Net50网络提高了1.53%。结果表明,在自然条件下对人脸表情识别具有更好的准确性。展开更多
Micro-expressions,fleeting involuntary facial cues lasting under half a second,reveal genuine emotions and are valuable in clinical diagnosis and psychotherapy.Real-time recognition on resource-constrained embedded de...Micro-expressions,fleeting involuntary facial cues lasting under half a second,reveal genuine emotions and are valuable in clinical diagnosis and psychotherapy.Real-time recognition on resource-constrained embedded devices remains challenging,as current methods struggle to balance performance and efficiency.This study introduces a semi-lightweight multifunctional network that enhances real-time deployment and accuracy.Unlike prior simplistic feature fusion techniques,our novel multi-feature fusion strategy leverages temporal,spatial,and differential features to better capture dynamic changes.Enhanced by Residual Network(ResNet)architecture with channel and spatial attention mechanisms,the model improves feature representation while maintaining a lightweight design.Evaluations on SMIC,CASME II,SAMM,and their composite dataset show superior performance in Unweighted F1 Score(UF1)and Unweighted Average Recall(UAR),alongside faster detection speeds compared to existing algorithms.展开更多
A novel image fusion network framework with an autonomous encoder and decoder is suggested to increase thevisual impression of fused images by improving the quality of infrared and visible light picture fusion. The ne...A novel image fusion network framework with an autonomous encoder and decoder is suggested to increase thevisual impression of fused images by improving the quality of infrared and visible light picture fusion. The networkcomprises an encoder module, fusion layer, decoder module, and edge improvementmodule. The encoder moduleutilizes an enhanced Inception module for shallow feature extraction, then combines Res2Net and Transformerto achieve deep-level co-extraction of local and global features from the original picture. An edge enhancementmodule (EEM) is created to extract significant edge features. A modal maximum difference fusion strategy isintroduced to enhance the adaptive representation of information in various regions of the source image, therebyenhancing the contrast of the fused image. The encoder and the EEM module extract features, which are thencombined in the fusion layer to create a fused picture using the decoder. Three datasets were chosen to test thealgorithmproposed in this paper. The results of the experiments demonstrate that the network effectively preservesbackground and detail information in both infrared and visible images, yielding superior outcomes in subjectiveand objective evaluations.展开更多
Water purification systems based on transition metal dichalcogenides face significant challenges,including lack of reactivity under dark conditions,scarcity of catalytically active sites,and rapid recombination of pho...Water purification systems based on transition metal dichalcogenides face significant challenges,including lack of reactivity under dark conditions,scarcity of catalytically active sites,and rapid recombination of photogenerated charge carriers.Simultaneously increasing the number of active sites and improving charge separation efficiency has proven difficult.In this study,we present a novel approach combining molybdenum(Mo) monoatomic doping and size engineering to produce a series of Mo-ReS_(2) quantum dots(MR QDs) with controllable dimensions.High-resolution structural characterization,first-principle calculations,and piezo force microscopy reveal that Mo monoatomic doping enhances the lattice asymmetry,thereby improving the piezoelectric properties.The resulting piezoelectric polarization and the generated built-in electric field significantly improve charge separation efficiency,leading to optimized photocatalytic performance.Additionally,the doping strategy increases the number of active sites and improves the adsorption of intermediate radicals,substantially boosting photo-sterilization efficiency.Our results demonstrate the elimination of 99.95% of Escherichia coli and 100.00% of Staphylococcus aureus within 30 min.Furthermore,we developed a self-purification system simulating water drainage,utilizing low-frequency water streams to trigger the piezoelectric behavior of MR QDs,achieving piezoelectric synergistic photodegradation.This innovative approach provides a more environmentally friendly and economical method for water self-purification,paving the way for advanced water treatment technologies.展开更多
Model-driven and data-driven inversions are two prominent methods for obtaining P-wave impedance,which is significant in reservoir description and identification.Based on proper initial models,most model-driven method...Model-driven and data-driven inversions are two prominent methods for obtaining P-wave impedance,which is significant in reservoir description and identification.Based on proper initial models,most model-driven methods primarily use the limited frequency bandwidth information of seismic data and can invert P-wave impedance with high accuracy,but not high resolution.Conventional data-driven methods mainly employ the information from well-log data and can provide high-accuracy and highresolution P-wave impedance owing to the superior nonlinear curve fitting capacity of neural networks.However,these methods require a significant number of training samples,which are frequently insufficient.To obtain P-wave impedance with both high accuracy and high resolution,we propose a model-data-driven inversion method using Res Nets and the normalized zero-lag cross-correlation objective function which is effective for avoiding local minima and suppressing random noise.By using initial models and training samples,the proposed model-data-driven method can invert P-wave impedance with satisfactory accuracy and resolution.Tests on synthetic and field data demonstrate the proposed method’s efficacy and practicability.展开更多
文摘为解决自然条件下人脸表情识别易受角度、光线、遮挡物的影响以及人脸表情数据集各类表情数量不均衡等问题,提出基于Res2Net的人脸表情识别方法。使用Res2Net50作为特征提取的主干网络,在预处理阶段对图像随机翻转、缩放、裁剪进行数据增强,提升模型的泛化性。引入广义平均池化(generalized mean pooling, GeM)方式,关注图像中比较显著的区域,增强模型的鲁棒性;选用Focal Loss损失函数,针对表情类别不平衡和错误分类问题,提高较难识别表情的识别率。该方法在FER2013数据集上准确率达到了70.41%,相较于原Res2Net50网络提高了1.53%。结果表明,在自然条件下对人脸表情识别具有更好的准确性。
文摘Micro-expressions,fleeting involuntary facial cues lasting under half a second,reveal genuine emotions and are valuable in clinical diagnosis and psychotherapy.Real-time recognition on resource-constrained embedded devices remains challenging,as current methods struggle to balance performance and efficiency.This study introduces a semi-lightweight multifunctional network that enhances real-time deployment and accuracy.Unlike prior simplistic feature fusion techniques,our novel multi-feature fusion strategy leverages temporal,spatial,and differential features to better capture dynamic changes.Enhanced by Residual Network(ResNet)architecture with channel and spatial attention mechanisms,the model improves feature representation while maintaining a lightweight design.Evaluations on SMIC,CASME II,SAMM,and their composite dataset show superior performance in Unweighted F1 Score(UF1)and Unweighted Average Recall(UAR),alongside faster detection speeds compared to existing algorithms.
文摘A novel image fusion network framework with an autonomous encoder and decoder is suggested to increase thevisual impression of fused images by improving the quality of infrared and visible light picture fusion. The networkcomprises an encoder module, fusion layer, decoder module, and edge improvementmodule. The encoder moduleutilizes an enhanced Inception module for shallow feature extraction, then combines Res2Net and Transformerto achieve deep-level co-extraction of local and global features from the original picture. An edge enhancementmodule (EEM) is created to extract significant edge features. A modal maximum difference fusion strategy isintroduced to enhance the adaptive representation of information in various regions of the source image, therebyenhancing the contrast of the fused image. The encoder and the EEM module extract features, which are thencombined in the fusion layer to create a fused picture using the decoder. Three datasets were chosen to test thealgorithmproposed in this paper. The results of the experiments demonstrate that the network effectively preservesbackground and detail information in both infrared and visible images, yielding superior outcomes in subjectiveand objective evaluations.
基金financially supported by the National Natural Science Foundation of China (No.52071146)Guangdong Provincial Natural Science Foundation (No.2023A1515010989)the Science and Technology Projects in Guangzhou (No.202201000008)。
文摘Water purification systems based on transition metal dichalcogenides face significant challenges,including lack of reactivity under dark conditions,scarcity of catalytically active sites,and rapid recombination of photogenerated charge carriers.Simultaneously increasing the number of active sites and improving charge separation efficiency has proven difficult.In this study,we present a novel approach combining molybdenum(Mo) monoatomic doping and size engineering to produce a series of Mo-ReS_(2) quantum dots(MR QDs) with controllable dimensions.High-resolution structural characterization,first-principle calculations,and piezo force microscopy reveal that Mo monoatomic doping enhances the lattice asymmetry,thereby improving the piezoelectric properties.The resulting piezoelectric polarization and the generated built-in electric field significantly improve charge separation efficiency,leading to optimized photocatalytic performance.Additionally,the doping strategy increases the number of active sites and improves the adsorption of intermediate radicals,substantially boosting photo-sterilization efficiency.Our results demonstrate the elimination of 99.95% of Escherichia coli and 100.00% of Staphylococcus aureus within 30 min.Furthermore,we developed a self-purification system simulating water drainage,utilizing low-frequency water streams to trigger the piezoelectric behavior of MR QDs,achieving piezoelectric synergistic photodegradation.This innovative approach provides a more environmentally friendly and economical method for water self-purification,paving the way for advanced water treatment technologies.
基金financially supported by the Important National Science&Technology Specific Project of China(Grant No.2017ZX05018-005)
文摘Model-driven and data-driven inversions are two prominent methods for obtaining P-wave impedance,which is significant in reservoir description and identification.Based on proper initial models,most model-driven methods primarily use the limited frequency bandwidth information of seismic data and can invert P-wave impedance with high accuracy,but not high resolution.Conventional data-driven methods mainly employ the information from well-log data and can provide high-accuracy and highresolution P-wave impedance owing to the superior nonlinear curve fitting capacity of neural networks.However,these methods require a significant number of training samples,which are frequently insufficient.To obtain P-wave impedance with both high accuracy and high resolution,we propose a model-data-driven inversion method using Res Nets and the normalized zero-lag cross-correlation objective function which is effective for avoiding local minima and suppressing random noise.By using initial models and training samples,the proposed model-data-driven method can invert P-wave impedance with satisfactory accuracy and resolution.Tests on synthetic and field data demonstrate the proposed method’s efficacy and practicability.
