When employing penetration ammunition to strike multi-story buildings,the detection methods using acceleration sensors suffer from signal aliasing,while magnetic detection methods are susceptible to interference from ...When employing penetration ammunition to strike multi-story buildings,the detection methods using acceleration sensors suffer from signal aliasing,while magnetic detection methods are susceptible to interference from ferromagnetic materials,thereby posing challenges in accurately determining the number of layers.To address this issue,this research proposes a layer counting method for penetration fuze that incorporates multi-source information fusion,utilizing both the temporal convolutional network(TCN)and the long short-term memory(LSTM)recurrent network.By leveraging the strengths of these two network structures,the method extracts temporal and high-dimensional features from the multi-source physical field during the penetration process,establishing a relationship between the multi-source physical field and the distance between the fuze and the target plate.A simulation model is developed to simulate the overload and magnetic field of a projectile penetrating multiple layers of target plates,capturing the multi-source physical field signals and their patterns during the penetration process.The analysis reveals that the proposed multi-source fusion layer counting method reduces errors by 60% and 50% compared to single overload layer counting and single magnetic anomaly signal layer counting,respectively.The model's predictive performance is evaluated under various operating conditions,including different ratios of added noise to random sample positions,penetration speeds,and spacing between target plates.The maximum errors in fuze penetration time predicted by the three modes are 0.08 ms,0.12 ms,and 0.16 ms,respectively,confirming the robustness of the proposed model.Moreover,the model's predictions indicate that the fitting degree for large interlayer spacings is superior to that for small interlayer spacings due to the influence of stress waves.展开更多
The precise and automatic segmentation of prostate magnetic resonance imaging(MRI)images is vital for assisting doctors in diagnosing prostate diseases.In recent years,many advanced methods have been applied to prosta...The precise and automatic segmentation of prostate magnetic resonance imaging(MRI)images is vital for assisting doctors in diagnosing prostate diseases.In recent years,many advanced methods have been applied to prostate segmentation,but due to the variability caused by prostate diseases,automatic segmentation of the prostate presents significant challenges.In this paper,we propose an attention-guided multi-scale feature fusion network(AGMSF-Net)to segment prostate MRI images.We propose an attention mechanism for extracting multi-scale features,and introduce a 3D transformer module to enhance global feature representation by adding it during the transition phase from encoder to decoder.In the decoder stage,a feature fusion module is proposed to obtain global context information.We evaluate our model on MRI images of the prostate acquired from a local hospital.The relative volume difference(RVD)and dice similarity coefficient(DSC)between the results of automatic prostate segmentation and ground truth were 1.21%and 93.68%,respectively.To quantitatively evaluate prostate volume on MRI,which is of significant clinical significance,we propose a unique AGMSF-Net.The essential performance evaluation and validation experiments have demonstrated the effectiveness of our method in automatic prostate segmentation.展开更多
The task of food image recognition,a nuanced subset of fine-grained image recognition,grapples with substantial intra-class variation and minimal inter-class differences.These challenges are compounded by the irregula...The task of food image recognition,a nuanced subset of fine-grained image recognition,grapples with substantial intra-class variation and minimal inter-class differences.These challenges are compounded by the irregular and multi-scale nature of food images.Addressing these complexities,our study introduces an advanced model that leverages multiple attention mechanisms and multi-stage local fusion,grounded in the ConvNeXt architecture.Our model employs hybrid attention(HA)mechanisms to pinpoint critical discriminative regions within images,substantially mitigating the influence of background noise.Furthermore,it introduces a multi-stage local fusion(MSLF)module,fostering long-distance dependencies between feature maps at varying stages.This approach facilitates the assimilation of complementary features across scales,significantly bolstering the model’s capacity for feature extraction.Furthermore,we constructed a dataset named Roushi60,which consists of 60 different categories of common meat dishes.Empirical evaluation of the ETH Food-101,ChineseFoodNet,and Roushi60 datasets reveals that our model achieves recognition accuracies of 91.12%,82.86%,and 92.50%,respectively.These figures not only mark an improvement of 1.04%,3.42%,and 1.36%over the foundational ConvNeXt network but also surpass the performance of most contemporary food image recognition methods.Such advancements underscore the efficacy of our proposed model in navigating the intricate landscape of food image recognition,setting a new benchmark for the field.展开更多
Recently,deep learning-based image inpainting methods have made great strides in reconstructing damaged regions.However,these methods often struggle to produce satisfactory results when dealing with missing images wit...Recently,deep learning-based image inpainting methods have made great strides in reconstructing damaged regions.However,these methods often struggle to produce satisfactory results when dealing with missing images with large holes,leading to distortions in the structure and blurring of textures.To address these problems,we combine the advantages of transformers and convolutions to propose an image inpainting method that incorporates edge priors and attention mechanisms.The proposed method aims to improve the results of inpainting large holes in images by enhancing the accuracy of structure restoration and the ability to recover texture details.This method divides the inpainting task into two phases:edge prediction and image inpainting.Specifically,in the edge prediction phase,a transformer architecture is designed to combine axial attention with standard self-attention.This design enhances the extraction capability of global structural features and location awareness.It also balances the complexity of self-attention operations,resulting in accurate prediction of the edge structure in the defective region.In the image inpainting phase,a multi-scale fusion attention module is introduced.This module makes full use of multi-level distant features and enhances local pixel continuity,thereby significantly improving the quality of image inpainting.To evaluate the performance of our method.comparative experiments are conducted on several datasets,including CelebA,Places2,and Facade.Quantitative experiments show that our method outperforms the other mainstream methods.Specifically,it improves Peak Signal-to-Noise Ratio(PSNR)and Structure Similarity Index Measure(SSIM)by 1.141~3.234 db and 0.083~0.235,respectively.Moreover,it reduces Learning Perceptual Image Patch Similarity(LPIPS)and Mean Absolute Error(MAE)by 0.0347~0.1753 and 0.0104~0.0402,respectively.Qualitative experiments reveal that our method excels at reconstructing images with complete structural information and clear texture details.Furthermore,our model exhibits impressive performance in terms of the number of parameters,memory cost,and testing time.展开更多
Pose-invariant facial expression recognition(FER)is an active but challenging research topic in computer vision.Especially with the involvement of diverse observation angles,FER makes the training parameter models inc...Pose-invariant facial expression recognition(FER)is an active but challenging research topic in computer vision.Especially with the involvement of diverse observation angles,FER makes the training parameter models inconsistent from one view to another.This study develops a deep global multiple-scale and local patches attention(GMS-LPA)dual-branch network for pose-invariant FER to weaken the influence of pose variation and selfocclusion on recognition accuracy.In this research,the designed GMS-LPA network contains four main parts,i.e.,the feature extraction module,the global multiple-scale(GMS)module,the local patches attention(LPA)module,and the model-level fusion model.The feature extraction module is designed to extract and normalize texture information to the same size.The GMS model can extract deep global features with different receptive fields,releasing the sensitivity of deeper convolution layers to pose-variant and self-occlusion.The LPA module is built to force the network to focus on local salient features,which can lower the effect of pose variation and self-occlusion on recognition results.Subsequently,the extracted features are fused with a model-level strategy to improve recognition accuracy.Extensive experimentswere conducted on four public databases,and the recognition results demonstrated the feasibility and validity of the proposed methods.展开更多
Recently,multimodal sentiment analysis has increasingly attracted attention with the popularity of complementary data streams,which has great potential to surpass unimodal sentiment analysis.One challenge of multimoda...Recently,multimodal sentiment analysis has increasingly attracted attention with the popularity of complementary data streams,which has great potential to surpass unimodal sentiment analysis.One challenge of multimodal sentiment analysis is how to design an efficient multimodal feature fusion strategy.Unfortunately,existing work always considers feature-level fusion or decision-level fusion,and few research works focus on hybrid fusion strategies that contain feature-level fusion and decision-level fusion.To improve the performance of multimodal sentiment analysis,we present a novel multimodal sentiment analysis model using BiGRU and attention-based hybrid fusion strategy(BAHFS).Firstly,we apply BiGRU to learn the unimodal features of text,audio and video.Then we fuse the unimodal features into bimodal features using the bimodal attention fusion module.Next,BAHFS feeds the unimodal features and bimodal features into the trimodal attention fusion module and the trimodal concatenation fusion module simultaneously to get two sets of trimodal features.Finally,BAHFS makes a classification with the two sets of trimodal features respectively and gets the final analysis results with decision-level fusion.Based on the CMU-MOSI and CMU-MOSEI datasets,extensive experiments have been carried out to verify BAHFS’s superiority.展开更多
Regular inspection of bridge cracks is crucial to bridge maintenance and repair.The traditional manual crack detection methods are timeconsuming,dangerous and subjective.At the same time,for the existing mainstream vi...Regular inspection of bridge cracks is crucial to bridge maintenance and repair.The traditional manual crack detection methods are timeconsuming,dangerous and subjective.At the same time,for the existing mainstream vision-based automatic crack detection algorithms,it is challenging to detect fine cracks and balance the detection accuracy and speed.Therefore,this paper proposes a new bridge crack segmentationmethod based on parallel attention mechanism and multi-scale features fusion on top of the DeeplabV3+network framework.First,the improved lightweight MobileNetv2 network and dilated separable convolution are integrated into the original DeeplabV3+network to improve the original backbone network Xception and atrous spatial pyramid pooling(ASPP)module,respectively,dramatically reducing the number of parameters in the network and accelerates the training and prediction speed of the model.Moreover,we introduce the parallel attention mechanism into the encoding and decoding stages.The attention to the crack regions can be enhanced from the aspects of both channel and spatial parts and significantly suppress the interference of various noises.Finally,we further improve the detection performance of the model for fine cracks by introducing a multi-scale features fusion module.Our research results are validated on the self-made dataset.The experiments show that our method is more accurate than other methods.Its intersection of union(IoU)and F1-score(F1)are increased to 77.96%and 87.57%,respectively.In addition,the number of parameters is only 4.10M,which is much smaller than the original network;also,the frames per second(FPS)is increased to 15 frames/s.The results prove that the proposed method fits well the requirements of rapid and accurate detection of bridge cracks and is superior to other methods.展开更多
The diagnosis of COVID-19 requires chest computed tomography(CT).High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease,so it is of clinical importance to study s...The diagnosis of COVID-19 requires chest computed tomography(CT).High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease,so it is of clinical importance to study super-resolution(SR)algorithms applied to CT images to improve the reso-lution of CT images.However,most of the existing SR algorithms are studied based on natural images,which are not suitable for medical images;and most of these algorithms improve the reconstruction quality by increasing the network depth,which is not suitable for machines with limited resources.To alleviate these issues,we propose a residual feature attentional fusion network for lightweight chest CT image super-resolution(RFAFN).Specifically,we design a contextual feature extraction block(CFEB)that can extract CT image features more efficiently and accurately than ordinary residual blocks.In addition,we propose a feature-weighted cascading strategy(FWCS)based on attentional feature fusion blocks(AFFB)to utilize the high-frequency detail information extracted by CFEB as much as possible via selectively fusing adjacent level feature information.Finally,we suggest a global hierarchical feature fusion strategy(GHFFS),which can utilize the hierarchical features more effectively than dense concatenation by progressively aggregating the feature information at various levels.Numerous experiments show that our method performs better than most of the state-of-the-art(SOTA)methods on the COVID-19 chest CT dataset.In detail,the peak signal-to-noise ratio(PSNR)is 0.11 dB and 0.47 dB higher on CTtest1 and CTtest2 at×3 SR compared to the suboptimal method,but the number of parameters and multi-adds are reduced by 22K and 0.43G,respectively.Our method can better recover chest CT image quality with fewer computational resources and effectively assist in COVID-19.展开更多
针对烟草领域中问句意图识别存在的特征稀疏、术语繁多和捕捉文本内部的语义关联困难等问题,提出了一种基于SBERT-Attention-LDA(Sentence-bidirectional encoder representational from transformers-Attention mechanism-Latent diric...针对烟草领域中问句意图识别存在的特征稀疏、术语繁多和捕捉文本内部的语义关联困难等问题,提出了一种基于SBERT-Attention-LDA(Sentence-bidirectional encoder representational from transformers-Attention mechanism-Latent dirichlet allocation)与ML-LSTM(Multi layers-Long short term memory)特征融合的问句意图识别方法。该方法首先基于SBERT预训练模型和Attention机制对烟草问句进行动态编码,转换为富含语义信息的特征向量,同时利用LDA模型建模出问句的主题向量,捕捉问句中的主题信息;然后通过更改后的模型级特征融合方法ML-LSTM获得具有更为完整、准确问句语义的联合特征表示;再使用3通道的卷积神经网络(Convolutional neural network,CNN)提取问句混合语义表示中隐藏特征,输入到全连接层和Softmax函数中实现对问句意图的分类。基于烟草行业权威网站上获取的数据集开展了实验验证,实验结果表明,所提方法相比其他几种深度学习结合注意力机制的方法精确率、召回率和F1值上有显著提升,与BERT和ERNIE(Enhanced representation through knowledge integration and embedding)-CNN模型相比提升明显,F1值分别提升2.07、2.88个百分点。展开更多
针对自动驾驶路面上目标漏检和错检的问题,提出一种基于改进Centerfusion的自动驾驶3D目标检测模型。该模型通过将相机信息和雷达特征融合,构成多通道特征数据输入,从而增强目标检测网络的鲁棒性,减少漏检问题;为了能够得到更加准确丰富...针对自动驾驶路面上目标漏检和错检的问题,提出一种基于改进Centerfusion的自动驾驶3D目标检测模型。该模型通过将相机信息和雷达特征融合,构成多通道特征数据输入,从而增强目标检测网络的鲁棒性,减少漏检问题;为了能够得到更加准确丰富的3D目标检测信息,引入了改进的注意力机制,用于增强视锥网格中的雷达点云和视觉信息融合;使用改进的损失函数优化边框预测的准确度。在Nuscenes数据集上进行模型验证和对比,实验结果表明,相较于传统的Centerfusion模型,提出的模型平均检测精度均值(mean Average Precision,mAP)提高了1.3%,Nuscenes检测分数(Nuscenes Detection Scores,NDS)提高了1.2%。展开更多
Aiming at the problem that the existing models have a poor segmentation effect on imbalanced data sets with small-scale samples,a bilateral U-Net network model with a spatial attention mechanism is designed.The model ...Aiming at the problem that the existing models have a poor segmentation effect on imbalanced data sets with small-scale samples,a bilateral U-Net network model with a spatial attention mechanism is designed.The model uses the lightweight MobileNetV2 as the backbone network for feature hierarchical extraction and proposes an Attentive Pyramid Spatial Attention(APSA)module compared to the Attenuated Spatial Pyramid module,which can increase the receptive field and enhance the information,and finally adds the context fusion prediction branch that fuses high-semantic and low-semantic prediction results,and the model effectively improves the segmentation accuracy of small data sets.The experimental results on the CamVid data set show that compared with some existing semantic segmentation networks,the algorithm has a better segmentation effect and segmentation accuracy,and its mIOU reaches 75.85%.Moreover,to verify the generality of the model and the effectiveness of the APSA module,experiments were conducted on the VOC 2012 data set,and the APSA module improved mIOU by about 12.2%.展开更多
In traditional medicine and ethnomedicine,medicinal plants have long been recognized as the basis for materials in therapeutic applications worldwide.In particular,the remarkable curative effect of traditional Chinese...In traditional medicine and ethnomedicine,medicinal plants have long been recognized as the basis for materials in therapeutic applications worldwide.In particular,the remarkable curative effect of traditional Chinese medicine during corona virus disease 2019(COVID-19)pandemic has attracted extensive attention globally.Medicinal plants have,therefore,become increasingly popular among the public.However,with increasing demand for and profit with medicinal plants,commercial fraudulent events such as adulteration or counterfeits sometimes occur,which poses a serious threat to the clinical outcomes and interests of consumers.With rapid advances in artificial intelligence,machine learning can be used to mine information on various medicinal plants to establish an ideal resource database.We herein present a review that mainly introduces common machine learning algorithms and discusses their application in multi-source data analysis of medicinal plants.The combination of machine learning algorithms and multi-source data analysis facilitates a comprehensive analysis and aids in the effective evaluation of the quality of medicinal plants.The findings of this review provide new possibilities for promoting the development and utilization of medicinal plants.展开更多
Medical image segmentation is an important application field of computer vision in medical image processing.Due to the close location and high similarity of different organs in medical images,the current segmentation ...Medical image segmentation is an important application field of computer vision in medical image processing.Due to the close location and high similarity of different organs in medical images,the current segmentation algorithms have problems with mis-segmentation and poor edge segmentation.To address these challenges,we propose a medical image segmentation network(AF-Net)based on attention mechanism and feature fusion,which can effectively capture global information while focusing the network on the object area.In this approach,we add dual attention blocks(DA-block)to the backbone network,which comprises parallel channels and spatial attention branches,to adaptively calibrate and weigh features.Secondly,the multi-scale feature fusion block(MFF-block)is proposed to obtain feature maps of different receptive domains and get multi-scale information with less computational consumption.Finally,to restore the locations and shapes of organs,we adopt the global feature fusion blocks(GFF-block)to fuse high-level and low-level information,which can obtain accurate pixel positioning.We evaluate our method on multiple datasets(the aorta and lungs dataset),and the experimental results achieve 94.0%in mIoU and 96.3%in DICE,showing that our approach performs better than U-Net and other state-of-art methods.展开更多
Data fusion can effectively process multi-sensor information to obtain more accurate and reliable results than a single sensor.The data of water quality in the environment comes from different sensors,thus the data mu...Data fusion can effectively process multi-sensor information to obtain more accurate and reliable results than a single sensor.The data of water quality in the environment comes from different sensors,thus the data must be fused.In our research,self-adaptive weighted data fusion method is used to respectively integrate the data from the PH value,temperature,oxygen dissolved and NH3 concentration of water quality environment.Based on the fusion,the Grubbs method is used to detect the abnormal data so as to provide data support for estimation,prediction and early warning of the water quality.展开更多
Cyber Threat Intelligence(CTI)is a valuable resource for cybersecurity defense,but it also poses challenges due to its multi-source and heterogeneous nature.Security personnel may be unable to use CTI effectively to u...Cyber Threat Intelligence(CTI)is a valuable resource for cybersecurity defense,but it also poses challenges due to its multi-source and heterogeneous nature.Security personnel may be unable to use CTI effectively to understand the condition and trend of a cyberattack and respond promptly.To address these challenges,we propose a novel approach that consists of three steps.First,we construct the attack and defense analysis of the cybersecurity ontology(ADACO)model by integrating multiple cybersecurity databases.Second,we develop the threat evolution prediction algorithm(TEPA),which can automatically detect threats at device nodes,correlate and map multisource threat information,and dynamically infer the threat evolution process.TEPA leverages knowledge graphs to represent comprehensive threat scenarios and achieves better performance in simulated experiments by combining structural and textual features of entities.Third,we design the intelligent defense decision algorithm(IDDA),which can provide intelligent recommendations for security personnel regarding the most suitable defense techniques.IDDA outperforms the baseline methods in the comparative experiment.展开更多
We present a novel sea-ice classification framework based on locality preserving fusion of multi-source images information.The locality preserving fusion arises from two-fold,i.e.,the local characterization in both sp...We present a novel sea-ice classification framework based on locality preserving fusion of multi-source images information.The locality preserving fusion arises from two-fold,i.e.,the local characterization in both spatial and feature domains.We commence by simultaneously learning a projection matrix,which preserves spatial localities,and a similarity matrix,which encodes feature similarities.We map the pixels of multi-source images by the projection matrix to a set fusion vectors that preserve spatial localities of the image.On the other hand,by applying the Laplacian eigen-decomposition to the similarity matrix,we obtain another set of fusion vectors that preserve the feature local similarities.We concatenate the fusion vectors for both spatial and feature locality preservation and obtain the fusion image.Finally,we classify the fusion image pixels by a novel sliding ensemble strategy,which enhances the locality preservation in classification.Our locality preserving fusion framework is effective in classifying multi-source sea-ice images(e.g.,multi-spectral and synthetic aperture radar(SAR)images)because it not only comprehensively captures the spatial neighboring relationships but also intrinsically characterizes the feature associations between different types of sea-ices.Experimental evaluations validate the effectiveness of our framework.展开更多
Image-anomaly detection, which is widely used in industrial fields. Previous studies that attempted to address this problem often trained convolutional neural network-based models(e.g., autoencoders and generative adv...Image-anomaly detection, which is widely used in industrial fields. Previous studies that attempted to address this problem often trained convolutional neural network-based models(e.g., autoencoders and generative adversarial networks) to reconstruct covered parts of input images and calculate the difference between the input and reconstructed images. However, convolutional operations are effective at extracting local features, making it difficult to identify larger image anomalies. Method To this end, we propose a transformer architecture based on mutual attention for image-anomaly separation. This architecture can capture long-term dependencies and fuse local and global features to facilitate better image-anomaly detection. Result Our method was extensively evaluated on several benchmarks, and experimental results showed that it improved the detection capability by 3.1% and localization capability by 1.0% compared with state-of-the-art reconstruction-based methods.展开更多
文摘When employing penetration ammunition to strike multi-story buildings,the detection methods using acceleration sensors suffer from signal aliasing,while magnetic detection methods are susceptible to interference from ferromagnetic materials,thereby posing challenges in accurately determining the number of layers.To address this issue,this research proposes a layer counting method for penetration fuze that incorporates multi-source information fusion,utilizing both the temporal convolutional network(TCN)and the long short-term memory(LSTM)recurrent network.By leveraging the strengths of these two network structures,the method extracts temporal and high-dimensional features from the multi-source physical field during the penetration process,establishing a relationship between the multi-source physical field and the distance between the fuze and the target plate.A simulation model is developed to simulate the overload and magnetic field of a projectile penetrating multiple layers of target plates,capturing the multi-source physical field signals and their patterns during the penetration process.The analysis reveals that the proposed multi-source fusion layer counting method reduces errors by 60% and 50% compared to single overload layer counting and single magnetic anomaly signal layer counting,respectively.The model's predictive performance is evaluated under various operating conditions,including different ratios of added noise to random sample positions,penetration speeds,and spacing between target plates.The maximum errors in fuze penetration time predicted by the three modes are 0.08 ms,0.12 ms,and 0.16 ms,respectively,confirming the robustness of the proposed model.Moreover,the model's predictions indicate that the fitting degree for large interlayer spacings is superior to that for small interlayer spacings due to the influence of stress waves.
基金This work was supported in part by the National Natural Science Foundation of China(Grant#:82260362)in part by the National Key R&D Program of China(Grant#:2021ZD0111000)+1 种基金in part by the Key R&D Project of Hainan Province(Grant#:ZDYF2021SHFZ243)in part by the Major Science and Technology Project of Haikou(Grant#:2020-009).
文摘The precise and automatic segmentation of prostate magnetic resonance imaging(MRI)images is vital for assisting doctors in diagnosing prostate diseases.In recent years,many advanced methods have been applied to prostate segmentation,but due to the variability caused by prostate diseases,automatic segmentation of the prostate presents significant challenges.In this paper,we propose an attention-guided multi-scale feature fusion network(AGMSF-Net)to segment prostate MRI images.We propose an attention mechanism for extracting multi-scale features,and introduce a 3D transformer module to enhance global feature representation by adding it during the transition phase from encoder to decoder.In the decoder stage,a feature fusion module is proposed to obtain global context information.We evaluate our model on MRI images of the prostate acquired from a local hospital.The relative volume difference(RVD)and dice similarity coefficient(DSC)between the results of automatic prostate segmentation and ground truth were 1.21%and 93.68%,respectively.To quantitatively evaluate prostate volume on MRI,which is of significant clinical significance,we propose a unique AGMSF-Net.The essential performance evaluation and validation experiments have demonstrated the effectiveness of our method in automatic prostate segmentation.
基金The support of this research was by Hubei Provincial Natural Science Foundation(2022CFB449)Science Research Foundation of Education Department of Hubei Province(B2020061),are gratefully acknowledged.
文摘The task of food image recognition,a nuanced subset of fine-grained image recognition,grapples with substantial intra-class variation and minimal inter-class differences.These challenges are compounded by the irregular and multi-scale nature of food images.Addressing these complexities,our study introduces an advanced model that leverages multiple attention mechanisms and multi-stage local fusion,grounded in the ConvNeXt architecture.Our model employs hybrid attention(HA)mechanisms to pinpoint critical discriminative regions within images,substantially mitigating the influence of background noise.Furthermore,it introduces a multi-stage local fusion(MSLF)module,fostering long-distance dependencies between feature maps at varying stages.This approach facilitates the assimilation of complementary features across scales,significantly bolstering the model’s capacity for feature extraction.Furthermore,we constructed a dataset named Roushi60,which consists of 60 different categories of common meat dishes.Empirical evaluation of the ETH Food-101,ChineseFoodNet,and Roushi60 datasets reveals that our model achieves recognition accuracies of 91.12%,82.86%,and 92.50%,respectively.These figures not only mark an improvement of 1.04%,3.42%,and 1.36%over the foundational ConvNeXt network but also surpass the performance of most contemporary food image recognition methods.Such advancements underscore the efficacy of our proposed model in navigating the intricate landscape of food image recognition,setting a new benchmark for the field.
基金supported in part by the National Natural Science Foundation of China under Grant 62062061/in part by the Major Project Cultivation Fund of Xizang Minzu University under Grant 324112300447.
文摘Recently,deep learning-based image inpainting methods have made great strides in reconstructing damaged regions.However,these methods often struggle to produce satisfactory results when dealing with missing images with large holes,leading to distortions in the structure and blurring of textures.To address these problems,we combine the advantages of transformers and convolutions to propose an image inpainting method that incorporates edge priors and attention mechanisms.The proposed method aims to improve the results of inpainting large holes in images by enhancing the accuracy of structure restoration and the ability to recover texture details.This method divides the inpainting task into two phases:edge prediction and image inpainting.Specifically,in the edge prediction phase,a transformer architecture is designed to combine axial attention with standard self-attention.This design enhances the extraction capability of global structural features and location awareness.It also balances the complexity of self-attention operations,resulting in accurate prediction of the edge structure in the defective region.In the image inpainting phase,a multi-scale fusion attention module is introduced.This module makes full use of multi-level distant features and enhances local pixel continuity,thereby significantly improving the quality of image inpainting.To evaluate the performance of our method.comparative experiments are conducted on several datasets,including CelebA,Places2,and Facade.Quantitative experiments show that our method outperforms the other mainstream methods.Specifically,it improves Peak Signal-to-Noise Ratio(PSNR)and Structure Similarity Index Measure(SSIM)by 1.141~3.234 db and 0.083~0.235,respectively.Moreover,it reduces Learning Perceptual Image Patch Similarity(LPIPS)and Mean Absolute Error(MAE)by 0.0347~0.1753 and 0.0104~0.0402,respectively.Qualitative experiments reveal that our method excels at reconstructing images with complete structural information and clear texture details.Furthermore,our model exhibits impressive performance in terms of the number of parameters,memory cost,and testing time.
基金supported by the National Natural Science Foundation of China (No.31872399)Advantage Discipline Construction Project (PAPD,No.6-2018)of Jiangsu University。
文摘Pose-invariant facial expression recognition(FER)is an active but challenging research topic in computer vision.Especially with the involvement of diverse observation angles,FER makes the training parameter models inconsistent from one view to another.This study develops a deep global multiple-scale and local patches attention(GMS-LPA)dual-branch network for pose-invariant FER to weaken the influence of pose variation and selfocclusion on recognition accuracy.In this research,the designed GMS-LPA network contains four main parts,i.e.,the feature extraction module,the global multiple-scale(GMS)module,the local patches attention(LPA)module,and the model-level fusion model.The feature extraction module is designed to extract and normalize texture information to the same size.The GMS model can extract deep global features with different receptive fields,releasing the sensitivity of deeper convolution layers to pose-variant and self-occlusion.The LPA module is built to force the network to focus on local salient features,which can lower the effect of pose variation and self-occlusion on recognition results.Subsequently,the extracted features are fused with a model-level strategy to improve recognition accuracy.Extensive experimentswere conducted on four public databases,and the recognition results demonstrated the feasibility and validity of the proposed methods.
基金funded by the National Natural Science Foundation of China (Grant No.61872126,No.62273290)supported by the Key project of Natural Science Foundation of Shandong Province (Grant No.ZR2020KF019).
文摘Recently,multimodal sentiment analysis has increasingly attracted attention with the popularity of complementary data streams,which has great potential to surpass unimodal sentiment analysis.One challenge of multimodal sentiment analysis is how to design an efficient multimodal feature fusion strategy.Unfortunately,existing work always considers feature-level fusion or decision-level fusion,and few research works focus on hybrid fusion strategies that contain feature-level fusion and decision-level fusion.To improve the performance of multimodal sentiment analysis,we present a novel multimodal sentiment analysis model using BiGRU and attention-based hybrid fusion strategy(BAHFS).Firstly,we apply BiGRU to learn the unimodal features of text,audio and video.Then we fuse the unimodal features into bimodal features using the bimodal attention fusion module.Next,BAHFS feeds the unimodal features and bimodal features into the trimodal attention fusion module and the trimodal concatenation fusion module simultaneously to get two sets of trimodal features.Finally,BAHFS makes a classification with the two sets of trimodal features respectively and gets the final analysis results with decision-level fusion.Based on the CMU-MOSI and CMU-MOSEI datasets,extensive experiments have been carried out to verify BAHFS’s superiority.
基金This work was supported by the High-Tech Industry Science and Technology Innovation Leading Plan Project of Hunan Provincial under Grant 2020GK2026,author B.Y,http://kjt.hunan.gov.cn/.
文摘Regular inspection of bridge cracks is crucial to bridge maintenance and repair.The traditional manual crack detection methods are timeconsuming,dangerous and subjective.At the same time,for the existing mainstream vision-based automatic crack detection algorithms,it is challenging to detect fine cracks and balance the detection accuracy and speed.Therefore,this paper proposes a new bridge crack segmentationmethod based on parallel attention mechanism and multi-scale features fusion on top of the DeeplabV3+network framework.First,the improved lightweight MobileNetv2 network and dilated separable convolution are integrated into the original DeeplabV3+network to improve the original backbone network Xception and atrous spatial pyramid pooling(ASPP)module,respectively,dramatically reducing the number of parameters in the network and accelerates the training and prediction speed of the model.Moreover,we introduce the parallel attention mechanism into the encoding and decoding stages.The attention to the crack regions can be enhanced from the aspects of both channel and spatial parts and significantly suppress the interference of various noises.Finally,we further improve the detection performance of the model for fine cracks by introducing a multi-scale features fusion module.Our research results are validated on the self-made dataset.The experiments show that our method is more accurate than other methods.Its intersection of union(IoU)and F1-score(F1)are increased to 77.96%and 87.57%,respectively.In addition,the number of parameters is only 4.10M,which is much smaller than the original network;also,the frames per second(FPS)is increased to 15 frames/s.The results prove that the proposed method fits well the requirements of rapid and accurate detection of bridge cracks and is superior to other methods.
基金supported by the General Project of Natural Science Foundation of Hebei Province of China(H2019201378)the Foundation of the President of Hebei University(XZJJ201917)the Special Project for Cultivating Scientific and Technological Innovation Ability of University and Middle School Students of Hebei Province(2021H060306).
文摘The diagnosis of COVID-19 requires chest computed tomography(CT).High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease,so it is of clinical importance to study super-resolution(SR)algorithms applied to CT images to improve the reso-lution of CT images.However,most of the existing SR algorithms are studied based on natural images,which are not suitable for medical images;and most of these algorithms improve the reconstruction quality by increasing the network depth,which is not suitable for machines with limited resources.To alleviate these issues,we propose a residual feature attentional fusion network for lightweight chest CT image super-resolution(RFAFN).Specifically,we design a contextual feature extraction block(CFEB)that can extract CT image features more efficiently and accurately than ordinary residual blocks.In addition,we propose a feature-weighted cascading strategy(FWCS)based on attentional feature fusion blocks(AFFB)to utilize the high-frequency detail information extracted by CFEB as much as possible via selectively fusing adjacent level feature information.Finally,we suggest a global hierarchical feature fusion strategy(GHFFS),which can utilize the hierarchical features more effectively than dense concatenation by progressively aggregating the feature information at various levels.Numerous experiments show that our method performs better than most of the state-of-the-art(SOTA)methods on the COVID-19 chest CT dataset.In detail,the peak signal-to-noise ratio(PSNR)is 0.11 dB and 0.47 dB higher on CTtest1 and CTtest2 at×3 SR compared to the suboptimal method,but the number of parameters and multi-adds are reduced by 22K and 0.43G,respectively.Our method can better recover chest CT image quality with fewer computational resources and effectively assist in COVID-19.
文摘针对烟草领域中问句意图识别存在的特征稀疏、术语繁多和捕捉文本内部的语义关联困难等问题,提出了一种基于SBERT-Attention-LDA(Sentence-bidirectional encoder representational from transformers-Attention mechanism-Latent dirichlet allocation)与ML-LSTM(Multi layers-Long short term memory)特征融合的问句意图识别方法。该方法首先基于SBERT预训练模型和Attention机制对烟草问句进行动态编码,转换为富含语义信息的特征向量,同时利用LDA模型建模出问句的主题向量,捕捉问句中的主题信息;然后通过更改后的模型级特征融合方法ML-LSTM获得具有更为完整、准确问句语义的联合特征表示;再使用3通道的卷积神经网络(Convolutional neural network,CNN)提取问句混合语义表示中隐藏特征,输入到全连接层和Softmax函数中实现对问句意图的分类。基于烟草行业权威网站上获取的数据集开展了实验验证,实验结果表明,所提方法相比其他几种深度学习结合注意力机制的方法精确率、召回率和F1值上有显著提升,与BERT和ERNIE(Enhanced representation through knowledge integration and embedding)-CNN模型相比提升明显,F1值分别提升2.07、2.88个百分点。
文摘针对自动驾驶路面上目标漏检和错检的问题,提出一种基于改进Centerfusion的自动驾驶3D目标检测模型。该模型通过将相机信息和雷达特征融合,构成多通道特征数据输入,从而增强目标检测网络的鲁棒性,减少漏检问题;为了能够得到更加准确丰富的3D目标检测信息,引入了改进的注意力机制,用于增强视锥网格中的雷达点云和视觉信息融合;使用改进的损失函数优化边框预测的准确度。在Nuscenes数据集上进行模型验证和对比,实验结果表明,相较于传统的Centerfusion模型,提出的模型平均检测精度均值(mean Average Precision,mAP)提高了1.3%,Nuscenes检测分数(Nuscenes Detection Scores,NDS)提高了1.2%。
基金Ministry of Science and Technology Basic Resources Survey Special Project,Grant/Award Number:2019FY100900High-level Hospital Construction Project,Grant/Award Number:DFJH2019015+2 种基金National Natural Science Foundation of China,Grant/Award Number:61871021Guangdong Natural Science Foundation,Grant/Award Number:2019A1515011676Beijing Key Laboratory of Robotics Bionic and Functional Research。
文摘Aiming at the problem that the existing models have a poor segmentation effect on imbalanced data sets with small-scale samples,a bilateral U-Net network model with a spatial attention mechanism is designed.The model uses the lightweight MobileNetV2 as the backbone network for feature hierarchical extraction and proposes an Attentive Pyramid Spatial Attention(APSA)module compared to the Attenuated Spatial Pyramid module,which can increase the receptive field and enhance the information,and finally adds the context fusion prediction branch that fuses high-semantic and low-semantic prediction results,and the model effectively improves the segmentation accuracy of small data sets.The experimental results on the CamVid data set show that compared with some existing semantic segmentation networks,the algorithm has a better segmentation effect and segmentation accuracy,and its mIOU reaches 75.85%.Moreover,to verify the generality of the model and the effectiveness of the APSA module,experiments were conducted on the VOC 2012 data set,and the APSA module improved mIOU by about 12.2%.
基金supported by the National Natural Science Foundation of China(Grant No.:U2202213)the Special Program for the Major Science and Technology Projects of Yunnan Province,China(Grant Nos.:202102AE090051-1-01,and 202202AE090001).
文摘In traditional medicine and ethnomedicine,medicinal plants have long been recognized as the basis for materials in therapeutic applications worldwide.In particular,the remarkable curative effect of traditional Chinese medicine during corona virus disease 2019(COVID-19)pandemic has attracted extensive attention globally.Medicinal plants have,therefore,become increasingly popular among the public.However,with increasing demand for and profit with medicinal plants,commercial fraudulent events such as adulteration or counterfeits sometimes occur,which poses a serious threat to the clinical outcomes and interests of consumers.With rapid advances in artificial intelligence,machine learning can be used to mine information on various medicinal plants to establish an ideal resource database.We herein present a review that mainly introduces common machine learning algorithms and discusses their application in multi-source data analysis of medicinal plants.The combination of machine learning algorithms and multi-source data analysis facilitates a comprehensive analysis and aids in the effective evaluation of the quality of medicinal plants.The findings of this review provide new possibilities for promoting the development and utilization of medicinal plants.
基金This work was supported in part by the National Natural Science Foundation of China under Grant 61772561,author J.Q,http://www.nsfc.gov.cn/in part by the Science Research Projects of Hunan Provincial Education Department under Grant 18A174,author X.X,http://kxjsc.gov.hnedu.cn/+5 种基金in part by the Science Research Projects of Hunan Provincial Education Department under Grant 19B584,author Y.T,http://kxjsc.gov.hnedu.cn/in part by the Natural Science Foundation of Hunan Province(No.2020JJ4140),author Y.T,http://kjt.hunan.gov.cn/in part by the Natural Science Foundation of Hunan Province(No.2020JJ4141),author X.X,http://kjt.hunan.gov.cn/in part by the Key Research and Development Plan of Hunan Province under Grant 2019SK2022,author Y.T,http://kjt.hunan.gov.cn/in part by the Key Research and Development Plan of Hunan Province under Grant CX20200730,author G.H,http://kjt.hunan.gov.cn/in part by the Graduate Science and Technology Innovation Fund Project of Central South University of Forestry and Technology under Grant CX20202038,author G.H,http://jwc.csuft.edu.cn/.
文摘Medical image segmentation is an important application field of computer vision in medical image processing.Due to the close location and high similarity of different organs in medical images,the current segmentation algorithms have problems with mis-segmentation and poor edge segmentation.To address these challenges,we propose a medical image segmentation network(AF-Net)based on attention mechanism and feature fusion,which can effectively capture global information while focusing the network on the object area.In this approach,we add dual attention blocks(DA-block)to the backbone network,which comprises parallel channels and spatial attention branches,to adaptively calibrate and weigh features.Secondly,the multi-scale feature fusion block(MFF-block)is proposed to obtain feature maps of different receptive domains and get multi-scale information with less computational consumption.Finally,to restore the locations and shapes of organs,we adopt the global feature fusion blocks(GFF-block)to fuse high-level and low-level information,which can obtain accurate pixel positioning.We evaluate our method on multiple datasets(the aorta and lungs dataset),and the experimental results achieve 94.0%in mIoU and 96.3%in DICE,showing that our approach performs better than U-Net and other state-of-art methods.
基金This study was supported by National Key Research and Development Project(Project No.2017YFD0301506)National Social Science Foundation(Project No.71774052)+1 种基金Hunan Education Department Scientific Research Project(Project No.17K04417A092).
文摘Data fusion can effectively process multi-sensor information to obtain more accurate and reliable results than a single sensor.The data of water quality in the environment comes from different sensors,thus the data must be fused.In our research,self-adaptive weighted data fusion method is used to respectively integrate the data from the PH value,temperature,oxygen dissolved and NH3 concentration of water quality environment.Based on the fusion,the Grubbs method is used to detect the abnormal data so as to provide data support for estimation,prediction and early warning of the water quality.
文摘Cyber Threat Intelligence(CTI)is a valuable resource for cybersecurity defense,but it also poses challenges due to its multi-source and heterogeneous nature.Security personnel may be unable to use CTI effectively to understand the condition and trend of a cyberattack and respond promptly.To address these challenges,we propose a novel approach that consists of three steps.First,we construct the attack and defense analysis of the cybersecurity ontology(ADACO)model by integrating multiple cybersecurity databases.Second,we develop the threat evolution prediction algorithm(TEPA),which can automatically detect threats at device nodes,correlate and map multisource threat information,and dynamically infer the threat evolution process.TEPA leverages knowledge graphs to represent comprehensive threat scenarios and achieves better performance in simulated experiments by combining structural and textual features of entities.Third,we design the intelligent defense decision algorithm(IDDA),which can provide intelligent recommendations for security personnel regarding the most suitable defense techniques.IDDA outperforms the baseline methods in the comparative experiment.
基金The National Natural Science Foundation of China under contract No.61671481the Qingdao Applied Fundamental Research under contract No.16-5-1-11-jchthe Fundamental Research Funds for Central Universities under contract No.18CX05014A
文摘We present a novel sea-ice classification framework based on locality preserving fusion of multi-source images information.The locality preserving fusion arises from two-fold,i.e.,the local characterization in both spatial and feature domains.We commence by simultaneously learning a projection matrix,which preserves spatial localities,and a similarity matrix,which encodes feature similarities.We map the pixels of multi-source images by the projection matrix to a set fusion vectors that preserve spatial localities of the image.On the other hand,by applying the Laplacian eigen-decomposition to the similarity matrix,we obtain another set of fusion vectors that preserve the feature local similarities.We concatenate the fusion vectors for both spatial and feature locality preservation and obtain the fusion image.Finally,we classify the fusion image pixels by a novel sliding ensemble strategy,which enhances the locality preservation in classification.Our locality preserving fusion framework is effective in classifying multi-source sea-ice images(e.g.,multi-spectral and synthetic aperture radar(SAR)images)because it not only comprehensively captures the spatial neighboring relationships but also intrinsically characterizes the feature associations between different types of sea-ices.Experimental evaluations validate the effectiveness of our framework.
基金Supported by the National Natural Science Foundation of China (No. 61772327)State Grid Gansu Electric Power Company(No. H2019-275)Shanghai Engineering Research Center on Big Data Management System (No.H2020-216)。
文摘Image-anomaly detection, which is widely used in industrial fields. Previous studies that attempted to address this problem often trained convolutional neural network-based models(e.g., autoencoders and generative adversarial networks) to reconstruct covered parts of input images and calculate the difference between the input and reconstructed images. However, convolutional operations are effective at extracting local features, making it difficult to identify larger image anomalies. Method To this end, we propose a transformer architecture based on mutual attention for image-anomaly separation. This architecture can capture long-term dependencies and fuse local and global features to facilitate better image-anomaly detection. Result Our method was extensively evaluated on several benchmarks, and experimental results showed that it improved the detection capability by 3.1% and localization capability by 1.0% compared with state-of-the-art reconstruction-based methods.