Fusing hand-based features in multi-modal biometric recognition enhances anti-spoofing capabilities.Additionally,it leverages inter-modal correlation to enhance recognition performance.Concurrently,the robustness and ...Fusing hand-based features in multi-modal biometric recognition enhances anti-spoofing capabilities.Additionally,it leverages inter-modal correlation to enhance recognition performance.Concurrently,the robustness and recognition performance of the system can be enhanced through judiciously leveraging the correlation among multimodal features.Nevertheless,two issues persist in multi-modal feature fusion recognition:Firstly,the enhancement of recognition performance in fusion recognition has not comprehensively considered the inter-modality correlations among distinct modalities.Secondly,during modal fusion,improper weight selection diminishes the salience of crucial modal features,thereby diminishing the overall recognition performance.To address these two issues,we introduce an enhanced DenseNet multimodal recognition network founded on feature-level fusion.The information from the three modalities is fused akin to RGB,and the input network augments the correlation between modes through channel correlation.Within the enhanced DenseNet network,the Efficient Channel Attention Network(ECA-Net)dynamically adjusts the weight of each channel to amplify the salience of crucial information in each modal feature.Depthwise separable convolution markedly reduces the training parameters and further enhances the feature correlation.Experimental evaluations were conducted on four multimodal databases,comprising six unimodal databases,including multispectral palmprint and palm vein databases from the Chinese Academy of Sciences.The Equal Error Rates(EER)values were 0.0149%,0.0150%,0.0099%,and 0.0050%,correspondingly.In comparison to other network methods for palmprint,palm vein,and finger vein fusion recognition,this approach substantially enhances recognition performance,rendering it suitable for high-security environments with practical applicability.The experiments in this article utilized amodest sample database comprising 200 individuals.The subsequent phase involves preparing for the extension of the method to larger databases.展开更多
Multi-modal fusion technology gradually become a fundamental task in many fields,such as autonomous driving,smart healthcare,sentiment analysis,and human-computer interaction.It is rapidly becoming the dominant resear...Multi-modal fusion technology gradually become a fundamental task in many fields,such as autonomous driving,smart healthcare,sentiment analysis,and human-computer interaction.It is rapidly becoming the dominant research due to its powerful perception and judgment capabilities.Under complex scenes,multi-modal fusion technology utilizes the complementary characteristics of multiple data streams to fuse different data types and achieve more accurate predictions.However,achieving outstanding performance is challenging because of equipment performance limitations,missing information,and data noise.This paper comprehensively reviews existing methods based onmulti-modal fusion techniques and completes a detailed and in-depth analysis.According to the data fusion stage,multi-modal fusion has four primary methods:early fusion,deep fusion,late fusion,and hybrid fusion.The paper surveys the three majormulti-modal fusion technologies that can significantly enhance the effect of data fusion and further explore the applications of multi-modal fusion technology in various fields.Finally,it discusses the challenges and explores potential research opportunities.Multi-modal tasks still need intensive study because of data heterogeneity and quality.Preserving complementary information and eliminating redundant information between modalities is critical in multi-modal technology.Invalid data fusion methods may introduce extra noise and lead to worse results.This paper provides a comprehensive and detailed summary in response to these challenges.展开更多
The unsupervised multi-modal image translation is an emerging domain of computer vision whose goal is to transform an image from the source domain into many diverse styles in the target domain.However,the multi-genera...The unsupervised multi-modal image translation is an emerging domain of computer vision whose goal is to transform an image from the source domain into many diverse styles in the target domain.However,the multi-generator mechanism is employed among the advanced approaches available to model different domain mappings,which results in inefficient training of neural networks and pattern collapse,leading to inefficient generation of image diversity.To address this issue,this paper introduces a multi-modal unsupervised image translation framework that uses a generator to perform multi-modal image translation.Specifically,firstly,the domain code is introduced in this paper to explicitly control the different generation tasks.Secondly,this paper brings in the squeeze-and-excitation(SE)mechanism and feature attention(FA)module.Finally,the model integrates multiple optimization objectives to ensure efficient multi-modal translation.This paper performs qualitative and quantitative experiments on multiple non-paired benchmark image translation datasets while demonstrating the benefits of the proposed method over existing technologies.Overall,experimental results have shown that the proposed method is versatile and scalable.展开更多
In geometry processing,symmetry research benefits from global geo-metric features of complete shapes,but the shape of an object captured in real-world applications is often incomplete due to the limited sensor resoluti...In geometry processing,symmetry research benefits from global geo-metric features of complete shapes,but the shape of an object captured in real-world applications is often incomplete due to the limited sensor resolution,single viewpoint,and occlusion.Different from the existing works predicting symmetry from the complete shape,we propose a learning approach for symmetry predic-tion based on a single RGB-D image.Instead of directly predicting the symmetry from incomplete shapes,our method consists of two modules,i.e.,the multi-mod-al feature fusion module and the detection-by-reconstruction module.Firstly,we build a channel-transformer network(CTN)to extract cross-fusion features from the RGB-D as the multi-modal feature fusion module,which helps us aggregate features from the color and the depth separately.Then,our self-reconstruction net-work based on a 3D variational auto-encoder(3D-VAE)takes the global geo-metric features as input,followed by a prediction symmetry network to detect the symmetry.Our experiments are conducted on three public datasets:ShapeNet,YCB,and ScanNet,we demonstrate that our method can produce reliable and accurate results.展开更多
With the rapid spread of Internet information and the spread of fake news,the detection of fake news becomes more and more important.Traditional detection methods often rely on a single emotional or semantic feature t...With the rapid spread of Internet information and the spread of fake news,the detection of fake news becomes more and more important.Traditional detection methods often rely on a single emotional or semantic feature to identify fake news,but these methods have limitations when dealing with news in specific domains.In order to solve the problem of weak feature correlation between data from different domains,a model for detecting fake news by integrating domain-specific emotional and semantic features is proposed.This method makes full use of the attention mechanism,grasps the correlation between different features,and effectively improves the effect of feature fusion.The algorithm first extracts the semantic features of news text through the Bi-LSTM(Bidirectional Long Short-Term Memory)layer to capture the contextual relevance of news text.Senta-BiLSTM is then used to extract emotional features and predict the probability of positive and negative emotions in the text.It then uses domain features as an enhancement feature and attention mechanism to fully capture more fine-grained emotional features associated with that domain.Finally,the fusion features are taken as the input of the fake news detection classifier,combined with the multi-task representation of information,and the MLP and Softmax functions are used for classification.The experimental results show that on the Chinese dataset Weibo21,the F1 value of this model is 0.958,4.9% higher than that of the sub-optimal model;on the English dataset FakeNewsNet,the F1 value of the detection result of this model is 0.845,1.8% higher than that of the sub-optimal model,which is advanced and feasible.展开更多
With the rapid development of the mobile communication and the Internet,the previous web anomaly detectionand identificationmodels were built relying on security experts’empirical knowledge and attack features.Althou...With the rapid development of the mobile communication and the Internet,the previous web anomaly detectionand identificationmodels were built relying on security experts’empirical knowledge and attack features.Althoughthis approach can achieve higher detection performance,it requires huge human labor and resources to maintainthe feature library.In contrast,semantic feature engineering can dynamically discover new semantic featuresand optimize feature selection by automatically analyzing the semantic information contained in the data itself,thus reducing dependence on prior knowledge.However,current semantic features still have the problem ofsemantic expression singularity,as they are extracted from a single semantic mode such as word segmentation,character segmentation,or arbitrary semantic feature extraction.This paper extracts features of web requestsfrom dual semantic granularity,and proposes a semantic feature fusion method to solve the above problems.Themethod first preprocesses web requests,and extracts word-level and character-level semantic features of URLs viaconvolutional neural network(CNN),respectively.By constructing three loss functions to reduce losses betweenfeatures,labels and categories.Experiments on the HTTP CSIC 2010,Malicious URLs and HttpParams datasetsverify the proposedmethod.Results show that compared withmachine learning,deep learningmethods and BERTmodel,the proposed method has better detection performance.And it achieved the best detection rate of 99.16%in the dataset HttpParams.展开更多
Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series data.Due to the challenges associated with annotating anomaly events,time series reconst...Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series data.Due to the challenges associated with annotating anomaly events,time series reconstruction has become a prevalent approach for unsupervised anomaly detection.However,effectively learning representations and achieving accurate detection results remain challenging due to the intricate temporal patterns and dependencies in real-world time series.In this paper,we propose a cross-dimension attentive feature fusion network for time series anomaly detection,referred to as CAFFN.Specifically,a series and feature mixing block is introduced to learn representations in 1D space.Additionally,a fast Fourier transform is employed to convert the time series into 2D space,providing the capability for 2D feature extraction.Finally,a cross-dimension attentive feature fusion mechanism is designed that adaptively integrates features across different dimensions for anomaly detection.Experimental results on real-world time series datasets demonstrate that CAFFN performs better than other competing methods in time series anomaly detection.展开更多
The degradation of optical remote sensing images due to atmospheric haze poses a significant obstacle,profoundly impeding their effective utilization across various domains.Dehazing methodologies have emerged as pivot...The degradation of optical remote sensing images due to atmospheric haze poses a significant obstacle,profoundly impeding their effective utilization across various domains.Dehazing methodologies have emerged as pivotal components of image preprocessing,fostering an improvement in the quality of remote sensing imagery.This enhancement renders remote sensing data more indispensable,thereby enhancing the accuracy of target iden-tification.Conventional defogging techniques based on simplistic atmospheric degradation models have proven inadequate for mitigating non-uniform haze within remotely sensed images.In response to this challenge,a novel UNet Residual Attention Network(URA-Net)is proposed.This paradigmatic approach materializes as an end-to-end convolutional neural network distinguished by its utilization of multi-scale dense feature fusion clusters and gated jump connections.The essence of our methodology lies in local feature fusion within dense residual clusters,enabling the extraction of pertinent features from both preceding and current local data,depending on contextual demands.The intelligently orchestrated gated structures facilitate the propagation of these features to the decoder,resulting in superior outcomes in haze removal.Empirical validation through a plethora of experiments substantiates the efficacy of URA-Net,demonstrating its superior performance compared to existing methods when applied to established datasets for remote sensing image defogging.On the RICE-1 dataset,URA-Net achieves a Peak Signal-to-Noise Ratio(PSNR)of 29.07 dB,surpassing the Dark Channel Prior(DCP)by 11.17 dB,the All-in-One Network for Dehazing(AOD)by 7.82 dB,the Optimal Transmission Map and Adaptive Atmospheric Light For Dehazing(OTM-AAL)by 5.37 dB,the Unsupervised Single Image Dehazing(USID)by 8.0 dB,and the Superpixel-based Remote Sensing Image Dehazing(SRD)by 8.5 dB.Particularly noteworthy,on the SateHaze1k dataset,URA-Net attains preeminence in overall performance,yielding defogged images characterized by consistent visual quality.This underscores the contribution of the research to the advancement of remote sensing technology,providing a robust and efficient solution for alleviating the adverse effects of haze on image quality.展开更多
Gliomas have the highest mortality rate of all brain tumors.Correctly classifying the glioma risk period can help doctors make reasonable treatment plans and improve patients’survival rates.This paper proposes a hier...Gliomas have the highest mortality rate of all brain tumors.Correctly classifying the glioma risk period can help doctors make reasonable treatment plans and improve patients’survival rates.This paper proposes a hierarchical multi-scale attention feature fusion medical image classification network(HMAC-Net),which effectively combines global features and local features.The network framework consists of three parallel layers:The global feature extraction layer,the local feature extraction layer,and the multi-scale feature fusion layer.A linear sparse attention mechanism is designed in the global feature extraction layer to reduce information redundancy.In the local feature extraction layer,a bilateral local attention mechanism is introduced to improve the extraction of relevant information between adjacent slices.In the multi-scale feature fusion layer,a channel fusion block combining convolutional attention mechanism and residual inverse multi-layer perceptron is proposed to prevent gradient disappearance and network degradation and improve feature representation capability.The double-branch iterative multi-scale classification block is used to improve the classification performance.On the brain glioma risk grading dataset,the results of the ablation experiment and comparison experiment show that the proposed HMAC-Net has the best performance in both qualitative analysis of heat maps and quantitative analysis of evaluation indicators.On the dataset of skin cancer classification,the generalization experiment results show that the proposed HMAC-Net has a good generalization effect.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
Olive trees are susceptible to a variety of diseases that can cause significant crop damage and economic losses.Early detection of these diseases is essential for effective management.We propose a novel transformed wa...Olive trees are susceptible to a variety of diseases that can cause significant crop damage and economic losses.Early detection of these diseases is essential for effective management.We propose a novel transformed wavelet,feature-fused,pre-trained deep learning model for detecting olive leaf diseases.The proposed model combines wavelet transforms with pre-trained deep-learning models to extract discriminative features from olive leaf images.The model has four main phases:preprocessing using data augmentation,three-level wavelet transformation,learning using pre-trained deep learning models,and a fused deep learning model.In the preprocessing phase,the image dataset is augmented using techniques such as resizing,rescaling,flipping,rotation,zooming,and contrasting.In wavelet transformation,the augmented images are decomposed into three frequency levels.Three pre-trained deep learning models,EfficientNet-B7,DenseNet-201,and ResNet-152-V2,are used in the learning phase.The models were trained using the approximate images of the third-level sub-band of the wavelet transform.In the fused phase,the fused model consists of a merge layer,three dense layers,and two dropout layers.The proposed model was evaluated using a dataset of images of healthy and infected olive leaves.It achieved an accuracy of 99.72%in the diagnosis of olive leaf diseases,which exceeds the accuracy of other methods reported in the literature.This finding suggests that our proposed method is a promising tool for the early detection of olive leaf diseases.展开更多
In the multi-radar networking system,aiming at the problem of locating long-distance targets synergistically with difficulty and low accuracy,a dual-station joint positioning method based on the target measurement err...In the multi-radar networking system,aiming at the problem of locating long-distance targets synergistically with difficulty and low accuracy,a dual-station joint positioning method based on the target measurement error feature complementarity is proposed.For dual-station joint positioning,by constructing the target positioning error distribution model and using the complementarity of spatial measurement errors of the same long-distance target,the area with high probability of target existence can be obtained.Then,based on the target distance information,the midpoint of the intersection between the target positioning sphere and the positioning tangent plane can be solved to acquire the target's optimal positioning result.The simulation demonstrates that this method greatly improves the positioning accuracy of target in azimuth direction.Compared with the traditional the dynamic weighted fusion(DWF)algorithm and the filter-based dynamic weighted fusion(FBDWF)algorithm,it not only effectively eliminates the influence of systematic error in the azimuth direction,but also has low computational complexity.Furthermore,for the application scenarios of multi-radar collaborative positioning and multi-sensor data compression filtering in centralized information fusion,it is recommended that using radar with higher ranging accuracy and the lengths of baseline between radars are 20–100 km.展开更多
With the popularisation of intelligent power,power devices have different shapes,numbers and specifications.This means that the power data has distributional variability,the model learning process cannot achieve suffi...With the popularisation of intelligent power,power devices have different shapes,numbers and specifications.This means that the power data has distributional variability,the model learning process cannot achieve sufficient extraction of data features,which seriously affects the accuracy and performance of anomaly detection.Therefore,this paper proposes a deep learning-based anomaly detection model for power data,which integrates a data alignment enhancement technique based on random sampling and an adaptive feature fusion method leveraging dimension reduction.Aiming at the distribution variability of power data,this paper developed a sliding window-based data adjustment method for this model,which solves the problem of high-dimensional feature noise and low-dimensional missing data.To address the problem of insufficient feature fusion,an adaptive feature fusion method based on feature dimension reduction and dictionary learning is proposed to improve the anomaly data detection accuracy of the model.In order to verify the effectiveness of the proposed method,we conducted effectiveness comparisons through elimination experiments.The experimental results show that compared with the traditional anomaly detection methods,the method proposed in this paper not only has an advantage in model accuracy,but also reduces the amount of parameter calculation of the model in the process of feature matching and improves the detection speed.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
The widespread availability of digital multimedia data has led to a new challenge in digital forensics.Traditional source camera identification algorithms usually rely on various traces in the capturing process.Howeve...The widespread availability of digital multimedia data has led to a new challenge in digital forensics.Traditional source camera identification algorithms usually rely on various traces in the capturing process.However,these traces have become increasingly difficult to extract due to wide availability of various image processing algorithms.Convolutional Neural Networks(CNN)-based algorithms have demonstrated good discriminative capabilities for different brands and even different models of camera devices.However,their performances is not ideal in case of distinguishing between individual devices of the same model,because cameras of the same model typically use the same optical lens,image sensor,and image processing algorithms,that result in minimal overall differences.In this paper,we propose a camera forensics algorithm based on multi-scale feature fusion to address these issues.The proposed algorithm extracts different local features from feature maps of different scales and then fuses them to obtain a comprehensive feature representation.This representation is then fed into a subsequent camera fingerprint classification network.Building upon the Swin-T network,we utilize Transformer Blocks and Graph Convolutional Network(GCN)modules to fuse multi-scale features from different stages of the backbone network.Furthermore,we conduct experiments on established datasets to demonstrate the feasibility and effectiveness of the proposed approach.展开更多
Power Shell has been widely deployed in fileless malware and advanced persistent threat(APT)attacks due to its high stealthiness and live-off-theland technique.However,existing works mainly focus on deobfuscation and ...Power Shell has been widely deployed in fileless malware and advanced persistent threat(APT)attacks due to its high stealthiness and live-off-theland technique.However,existing works mainly focus on deobfuscation and malicious detection,lacking the malicious Power Shell families classification and behavior analysis.Moreover,the state-of-the-art methods fail to capture fine-grained features and semantic relationships,resulting in low robustness and accuracy.To this end,we propose Power Detector,a novel malicious Power Shell script detector based on multimodal semantic fusion and deep learning.Specifically,we design four feature extraction methods to extract key features from character,token,abstract syntax tree(AST),and semantic knowledge graph.Then,we intelligently design four embeddings(i.e.,Char2Vec,Token2Vec,AST2Vec,and Rela2Vec) and construct a multi-modal fusion algorithm to concatenate feature vectors from different views.Finally,we propose a combined model based on transformer and CNN-Bi LSTM to implement Power Shell family detection.Our experiments with five types of Power Shell attacks show that PowerDetector can accurately detect various obfuscated and stealth PowerShell scripts,with a 0.9402 precision,a 0.9358 recall,and a 0.9374 F1-score.Furthermore,through singlemodal and multi-modal comparison experiments,we demonstrate that PowerDetector’s multi-modal embedding and deep learning model can achieve better accuracy and even identify more unknown attacks.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
Manhole cover defect recognition is of significant practical importance as it can accurately identify damaged or missing covers, enabling timely replacement and maintenance. Traditional manhole cover detection techniq...Manhole cover defect recognition is of significant practical importance as it can accurately identify damaged or missing covers, enabling timely replacement and maintenance. Traditional manhole cover detection techniques primarily focus on detecting the presence of covers rather than classifying the types of defects. However, manhole cover defects exhibit small inter-class feature differences and large intra-class feature variations, which makes their recognition challenging. To improve the classification of manhole cover defect types, we propose a Progressive Dual-Branch Feature Fusion Network (PDBFFN). The baseline backbone network adopts a multi-stage hierarchical architecture design using Res-Net50 as the visual feature extractor, from which both local and global information is obtained. Additionally, a Feature Enhancement Module (FEM) and a Fusion Module (FM) are introduced to enhance the network’s ability to learn critical features. Experimental results demonstrate that our model achieves a classification accuracy of 82.6% on a manhole cover defect dataset, outperforming several state-of-the-art fine-grained image classification models.展开更多
Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware reso...Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware resources. To address this issue, the MobileNetV1 network was developed, which employs depthwise convolution to reduce network complexity. MobileNetV1 employs a stride of 2 in several convolutional layers to decrease the spatial resolution of feature maps, thereby lowering computational costs. However, this stride setting can lead to a loss of spatial information, particularly affecting the detection and representation of smaller objects or finer details in images. To maintain the trade-off between complexity and model performance, a lightweight convolutional neural network with hierarchical multi-scale feature fusion based on the MobileNetV1 network is proposed. The network consists of two main subnetworks. The first subnetwork uses a depthwise dilated separable convolution (DDSC) layer to learn imaging features with fewer parameters, which results in a lightweight and computationally inexpensive network. Furthermore, depthwise dilated convolution in DDSC layer effectively expands the field of view of filters, allowing them to incorporate a larger context. The second subnetwork is a hierarchical multi-scale feature fusion (HMFF) module that uses parallel multi-resolution branches architecture to process the input feature map in order to extract the multi-scale feature information of the input image. Experimental results on the CIFAR-10, Malaria, and KvasirV1 datasets demonstrate that the proposed method is efficient, reducing the network parameters and computational cost by 65.02% and 39.78%, respectively, while maintaining the network performance compared to the MobileNetV1 baseline.展开更多
Event extraction stands as a significant endeavor within the realm of information extraction,aspiring to automatically extract structured event information from vast volumes of unstructured text.Extracting event eleme...Event extraction stands as a significant endeavor within the realm of information extraction,aspiring to automatically extract structured event information from vast volumes of unstructured text.Extracting event elements from multi-modal data remains a challenging task due to the presence of a large number of images and overlapping event elements in the data.Although researchers have proposed various methods to accomplish this task,most existing event extraction models cannot address these challenges because they are only applicable to text scenarios.To solve the above issues,this paper proposes a multi-modal event extraction method based on knowledge fusion.Specifically,for event-type recognition,we use a meticulous pipeline approach that integrates multiple pre-trained models.This approach enables a more comprehensive capture of the multidimensional event semantic features present in military texts,thereby enhancing the interconnectedness of information between trigger words and events.For event element extraction,we propose a method for constructing a priori templates that combine event types with corresponding trigger words.This approach facilitates the acquisition of fine-grained input samples containing event trigger words,thus enabling the model to understand the semantic relationships between elements in greater depth.Furthermore,a fusion method for spatial mapping of textual event elements and image elements is proposed to reduce the category number overload and effectively achieve multi-modal knowledge fusion.The experimental results based on the CCKS 2022 dataset show that our method has achieved competitive results,with a comprehensive evaluation value F1-score of 53.4%for the model.These results validate the effectiveness of our method in extracting event elements from multi-modal data.展开更多
基金funded by the National Natural Science Foundation of China(61991413)the China Postdoctoral Science Foundation(2019M651142)+1 种基金the Natural Science Foundation of Liaoning Province(2021-KF-12-07)the Natural Science Foundations of Liaoning Province(2023-MS-322).
文摘Fusing hand-based features in multi-modal biometric recognition enhances anti-spoofing capabilities.Additionally,it leverages inter-modal correlation to enhance recognition performance.Concurrently,the robustness and recognition performance of the system can be enhanced through judiciously leveraging the correlation among multimodal features.Nevertheless,two issues persist in multi-modal feature fusion recognition:Firstly,the enhancement of recognition performance in fusion recognition has not comprehensively considered the inter-modality correlations among distinct modalities.Secondly,during modal fusion,improper weight selection diminishes the salience of crucial modal features,thereby diminishing the overall recognition performance.To address these two issues,we introduce an enhanced DenseNet multimodal recognition network founded on feature-level fusion.The information from the three modalities is fused akin to RGB,and the input network augments the correlation between modes through channel correlation.Within the enhanced DenseNet network,the Efficient Channel Attention Network(ECA-Net)dynamically adjusts the weight of each channel to amplify the salience of crucial information in each modal feature.Depthwise separable convolution markedly reduces the training parameters and further enhances the feature correlation.Experimental evaluations were conducted on four multimodal databases,comprising six unimodal databases,including multispectral palmprint and palm vein databases from the Chinese Academy of Sciences.The Equal Error Rates(EER)values were 0.0149%,0.0150%,0.0099%,and 0.0050%,correspondingly.In comparison to other network methods for palmprint,palm vein,and finger vein fusion recognition,this approach substantially enhances recognition performance,rendering it suitable for high-security environments with practical applicability.The experiments in this article utilized amodest sample database comprising 200 individuals.The subsequent phase involves preparing for the extension of the method to larger databases.
基金supported by the Natural Science Foundation of Liaoning Province(Grant No.2023-MSBA-070)the National Natural Science Foundation of China(Grant No.62302086).
文摘Multi-modal fusion technology gradually become a fundamental task in many fields,such as autonomous driving,smart healthcare,sentiment analysis,and human-computer interaction.It is rapidly becoming the dominant research due to its powerful perception and judgment capabilities.Under complex scenes,multi-modal fusion technology utilizes the complementary characteristics of multiple data streams to fuse different data types and achieve more accurate predictions.However,achieving outstanding performance is challenging because of equipment performance limitations,missing information,and data noise.This paper comprehensively reviews existing methods based onmulti-modal fusion techniques and completes a detailed and in-depth analysis.According to the data fusion stage,multi-modal fusion has four primary methods:early fusion,deep fusion,late fusion,and hybrid fusion.The paper surveys the three majormulti-modal fusion technologies that can significantly enhance the effect of data fusion and further explore the applications of multi-modal fusion technology in various fields.Finally,it discusses the challenges and explores potential research opportunities.Multi-modal tasks still need intensive study because of data heterogeneity and quality.Preserving complementary information and eliminating redundant information between modalities is critical in multi-modal technology.Invalid data fusion methods may introduce extra noise and lead to worse results.This paper provides a comprehensive and detailed summary in response to these challenges.
基金the National Natural Science Foundation of China(No.61976080)the Academic Degrees&Graduate Education Reform Project of Henan Province(No.2021SJGLX195Y)+1 种基金the Teaching Reform Research and Practice Project of Henan Undergraduate Universities(No.2022SYJXLX008)the Key Project on Research and Practice of Henan University Graduate Education and Teaching Reform(No.YJSJG2023XJ006)。
文摘The unsupervised multi-modal image translation is an emerging domain of computer vision whose goal is to transform an image from the source domain into many diverse styles in the target domain.However,the multi-generator mechanism is employed among the advanced approaches available to model different domain mappings,which results in inefficient training of neural networks and pattern collapse,leading to inefficient generation of image diversity.To address this issue,this paper introduces a multi-modal unsupervised image translation framework that uses a generator to perform multi-modal image translation.Specifically,firstly,the domain code is introduced in this paper to explicitly control the different generation tasks.Secondly,this paper brings in the squeeze-and-excitation(SE)mechanism and feature attention(FA)module.Finally,the model integrates multiple optimization objectives to ensure efficient multi-modal translation.This paper performs qualitative and quantitative experiments on multiple non-paired benchmark image translation datasets while demonstrating the benefits of the proposed method over existing technologies.Overall,experimental results have shown that the proposed method is versatile and scalable.
文摘In geometry processing,symmetry research benefits from global geo-metric features of complete shapes,but the shape of an object captured in real-world applications is often incomplete due to the limited sensor resolution,single viewpoint,and occlusion.Different from the existing works predicting symmetry from the complete shape,we propose a learning approach for symmetry predic-tion based on a single RGB-D image.Instead of directly predicting the symmetry from incomplete shapes,our method consists of two modules,i.e.,the multi-mod-al feature fusion module and the detection-by-reconstruction module.Firstly,we build a channel-transformer network(CTN)to extract cross-fusion features from the RGB-D as the multi-modal feature fusion module,which helps us aggregate features from the color and the depth separately.Then,our self-reconstruction net-work based on a 3D variational auto-encoder(3D-VAE)takes the global geo-metric features as input,followed by a prediction symmetry network to detect the symmetry.Our experiments are conducted on three public datasets:ShapeNet,YCB,and ScanNet,we demonstrate that our method can produce reliable and accurate results.
基金The authors are highly thankful to the National Social Science Foundation of China(20BXW101,18XXW015)Innovation Research Project for the Cultivation of High-Level Scientific and Technological Talents(Top-Notch Talents of theDiscipline)(ZZKY2022303)+3 种基金National Natural Science Foundation of China(Nos.62102451,62202496)Basic Frontier Innovation Project of Engineering University of People’s Armed Police(WJX202316)This work is also supported by National Natural Science Foundation of China(No.62172436)Engineering University of PAP’s Funding for Scientific Research Innovation Team,Engineering University of PAP’s Funding for Basic Scientific Research,and Engineering University of PAP’s Funding for Education and Teaching.Natural Science Foundation of Shaanxi Province(No.2023-JCYB-584).
文摘With the rapid spread of Internet information and the spread of fake news,the detection of fake news becomes more and more important.Traditional detection methods often rely on a single emotional or semantic feature to identify fake news,but these methods have limitations when dealing with news in specific domains.In order to solve the problem of weak feature correlation between data from different domains,a model for detecting fake news by integrating domain-specific emotional and semantic features is proposed.This method makes full use of the attention mechanism,grasps the correlation between different features,and effectively improves the effect of feature fusion.The algorithm first extracts the semantic features of news text through the Bi-LSTM(Bidirectional Long Short-Term Memory)layer to capture the contextual relevance of news text.Senta-BiLSTM is then used to extract emotional features and predict the probability of positive and negative emotions in the text.It then uses domain features as an enhancement feature and attention mechanism to fully capture more fine-grained emotional features associated with that domain.Finally,the fusion features are taken as the input of the fake news detection classifier,combined with the multi-task representation of information,and the MLP and Softmax functions are used for classification.The experimental results show that on the Chinese dataset Weibo21,the F1 value of this model is 0.958,4.9% higher than that of the sub-optimal model;on the English dataset FakeNewsNet,the F1 value of the detection result of this model is 0.845,1.8% higher than that of the sub-optimal model,which is advanced and feasible.
基金a grant from the National Natural Science Foundation of China(Nos.11905239,12005248 and 12105303).
文摘With the rapid development of the mobile communication and the Internet,the previous web anomaly detectionand identificationmodels were built relying on security experts’empirical knowledge and attack features.Althoughthis approach can achieve higher detection performance,it requires huge human labor and resources to maintainthe feature library.In contrast,semantic feature engineering can dynamically discover new semantic featuresand optimize feature selection by automatically analyzing the semantic information contained in the data itself,thus reducing dependence on prior knowledge.However,current semantic features still have the problem ofsemantic expression singularity,as they are extracted from a single semantic mode such as word segmentation,character segmentation,or arbitrary semantic feature extraction.This paper extracts features of web requestsfrom dual semantic granularity,and proposes a semantic feature fusion method to solve the above problems.Themethod first preprocesses web requests,and extracts word-level and character-level semantic features of URLs viaconvolutional neural network(CNN),respectively.By constructing three loss functions to reduce losses betweenfeatures,labels and categories.Experiments on the HTTP CSIC 2010,Malicious URLs and HttpParams datasetsverify the proposedmethod.Results show that compared withmachine learning,deep learningmethods and BERTmodel,the proposed method has better detection performance.And it achieved the best detection rate of 99.16%in the dataset HttpParams.
基金supported in part by the National Natural Science Foundation of China(Grants 62376172,62006163,62376043)in part by the National Postdoctoral Program for Innovative Talents(Grant BX20200226)in part by Sichuan Science and Technology Planning Project(Grants 2022YFSY0047,2022YFQ0014,2023ZYD0143,2022YFH0021,2023YFQ0020,24QYCX0354,24NSFTD0025).
文摘Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series data.Due to the challenges associated with annotating anomaly events,time series reconstruction has become a prevalent approach for unsupervised anomaly detection.However,effectively learning representations and achieving accurate detection results remain challenging due to the intricate temporal patterns and dependencies in real-world time series.In this paper,we propose a cross-dimension attentive feature fusion network for time series anomaly detection,referred to as CAFFN.Specifically,a series and feature mixing block is introduced to learn representations in 1D space.Additionally,a fast Fourier transform is employed to convert the time series into 2D space,providing the capability for 2D feature extraction.Finally,a cross-dimension attentive feature fusion mechanism is designed that adaptively integrates features across different dimensions for anomaly detection.Experimental results on real-world time series datasets demonstrate that CAFFN performs better than other competing methods in time series anomaly detection.
基金This project is supported by the National Natural Science Foundation of China(NSFC)(No.61902158).
文摘The degradation of optical remote sensing images due to atmospheric haze poses a significant obstacle,profoundly impeding their effective utilization across various domains.Dehazing methodologies have emerged as pivotal components of image preprocessing,fostering an improvement in the quality of remote sensing imagery.This enhancement renders remote sensing data more indispensable,thereby enhancing the accuracy of target iden-tification.Conventional defogging techniques based on simplistic atmospheric degradation models have proven inadequate for mitigating non-uniform haze within remotely sensed images.In response to this challenge,a novel UNet Residual Attention Network(URA-Net)is proposed.This paradigmatic approach materializes as an end-to-end convolutional neural network distinguished by its utilization of multi-scale dense feature fusion clusters and gated jump connections.The essence of our methodology lies in local feature fusion within dense residual clusters,enabling the extraction of pertinent features from both preceding and current local data,depending on contextual demands.The intelligently orchestrated gated structures facilitate the propagation of these features to the decoder,resulting in superior outcomes in haze removal.Empirical validation through a plethora of experiments substantiates the efficacy of URA-Net,demonstrating its superior performance compared to existing methods when applied to established datasets for remote sensing image defogging.On the RICE-1 dataset,URA-Net achieves a Peak Signal-to-Noise Ratio(PSNR)of 29.07 dB,surpassing the Dark Channel Prior(DCP)by 11.17 dB,the All-in-One Network for Dehazing(AOD)by 7.82 dB,the Optimal Transmission Map and Adaptive Atmospheric Light For Dehazing(OTM-AAL)by 5.37 dB,the Unsupervised Single Image Dehazing(USID)by 8.0 dB,and the Superpixel-based Remote Sensing Image Dehazing(SRD)by 8.5 dB.Particularly noteworthy,on the SateHaze1k dataset,URA-Net attains preeminence in overall performance,yielding defogged images characterized by consistent visual quality.This underscores the contribution of the research to the advancement of remote sensing technology,providing a robust and efficient solution for alleviating the adverse effects of haze on image quality.
基金Major Program of National Natural Science Foundation of China(NSFC12292980,NSFC12292984)National Key R&D Program of China(2023YFA1009000,2023YFA1009004,2020YFA0712203,2020YFA0712201)+2 种基金Major Program of National Natural Science Foundation of China(NSFC12031016)Beijing Natural Science Foundation(BNSFZ210003)Department of Science,Technology and Information of the Ministry of Education(8091B042240).
文摘Gliomas have the highest mortality rate of all brain tumors.Correctly classifying the glioma risk period can help doctors make reasonable treatment plans and improve patients’survival rates.This paper proposes a hierarchical multi-scale attention feature fusion medical image classification network(HMAC-Net),which effectively combines global features and local features.The network framework consists of three parallel layers:The global feature extraction layer,the local feature extraction layer,and the multi-scale feature fusion layer.A linear sparse attention mechanism is designed in the global feature extraction layer to reduce information redundancy.In the local feature extraction layer,a bilateral local attention mechanism is introduced to improve the extraction of relevant information between adjacent slices.In the multi-scale feature fusion layer,a channel fusion block combining convolutional attention mechanism and residual inverse multi-layer perceptron is proposed to prevent gradient disappearance and network degradation and improve feature representation capability.The double-branch iterative multi-scale classification block is used to improve the classification performance.On the brain glioma risk grading dataset,the results of the ablation experiment and comparison experiment show that the proposed HMAC-Net has the best performance in both qualitative analysis of heat maps and quantitative analysis of evaluation indicators.On the dataset of skin cancer classification,the generalization experiment results show that the proposed HMAC-Net has a good generalization effect.
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.
文摘Olive trees are susceptible to a variety of diseases that can cause significant crop damage and economic losses.Early detection of these diseases is essential for effective management.We propose a novel transformed wavelet,feature-fused,pre-trained deep learning model for detecting olive leaf diseases.The proposed model combines wavelet transforms with pre-trained deep-learning models to extract discriminative features from olive leaf images.The model has four main phases:preprocessing using data augmentation,three-level wavelet transformation,learning using pre-trained deep learning models,and a fused deep learning model.In the preprocessing phase,the image dataset is augmented using techniques such as resizing,rescaling,flipping,rotation,zooming,and contrasting.In wavelet transformation,the augmented images are decomposed into three frequency levels.Three pre-trained deep learning models,EfficientNet-B7,DenseNet-201,and ResNet-152-V2,are used in the learning phase.The models were trained using the approximate images of the third-level sub-band of the wavelet transform.In the fused phase,the fused model consists of a merge layer,three dense layers,and two dropout layers.The proposed model was evaluated using a dataset of images of healthy and infected olive leaves.It achieved an accuracy of 99.72%in the diagnosis of olive leaf diseases,which exceeds the accuracy of other methods reported in the literature.This finding suggests that our proposed method is a promising tool for the early detection of olive leaf diseases.
文摘In the multi-radar networking system,aiming at the problem of locating long-distance targets synergistically with difficulty and low accuracy,a dual-station joint positioning method based on the target measurement error feature complementarity is proposed.For dual-station joint positioning,by constructing the target positioning error distribution model and using the complementarity of spatial measurement errors of the same long-distance target,the area with high probability of target existence can be obtained.Then,based on the target distance information,the midpoint of the intersection between the target positioning sphere and the positioning tangent plane can be solved to acquire the target's optimal positioning result.The simulation demonstrates that this method greatly improves the positioning accuracy of target in azimuth direction.Compared with the traditional the dynamic weighted fusion(DWF)algorithm and the filter-based dynamic weighted fusion(FBDWF)algorithm,it not only effectively eliminates the influence of systematic error in the azimuth direction,but also has low computational complexity.Furthermore,for the application scenarios of multi-radar collaborative positioning and multi-sensor data compression filtering in centralized information fusion,it is recommended that using radar with higher ranging accuracy and the lengths of baseline between radars are 20–100 km.
文摘With the popularisation of intelligent power,power devices have different shapes,numbers and specifications.This means that the power data has distributional variability,the model learning process cannot achieve sufficient extraction of data features,which seriously affects the accuracy and performance of anomaly detection.Therefore,this paper proposes a deep learning-based anomaly detection model for power data,which integrates a data alignment enhancement technique based on random sampling and an adaptive feature fusion method leveraging dimension reduction.Aiming at the distribution variability of power data,this paper developed a sliding window-based data adjustment method for this model,which solves the problem of high-dimensional feature noise and low-dimensional missing data.To address the problem of insufficient feature fusion,an adaptive feature fusion method based on feature dimension reduction and dictionary learning is proposed to improve the anomaly data detection accuracy of the model.In order to verify the effectiveness of the proposed method,we conducted effectiveness comparisons through elimination experiments.The experimental results show that compared with the traditional anomaly detection methods,the method proposed in this paper not only has an advantage in model accuracy,but also reduces the amount of parameter calculation of the model in the process of feature matching and improves the detection speed.
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This work was funded by the National Natural Science Foundation of China(Grant No.62172132)Public Welfare Technology Research Project of Zhejiang Province(Grant No.LGF21F020014)the Opening Project of Key Laboratory of Public Security Information Application Based on Big-Data Architecture,Ministry of Public Security of Zhejiang Police College(Grant No.2021DSJSYS002).
文摘The widespread availability of digital multimedia data has led to a new challenge in digital forensics.Traditional source camera identification algorithms usually rely on various traces in the capturing process.However,these traces have become increasingly difficult to extract due to wide availability of various image processing algorithms.Convolutional Neural Networks(CNN)-based algorithms have demonstrated good discriminative capabilities for different brands and even different models of camera devices.However,their performances is not ideal in case of distinguishing between individual devices of the same model,because cameras of the same model typically use the same optical lens,image sensor,and image processing algorithms,that result in minimal overall differences.In this paper,we propose a camera forensics algorithm based on multi-scale feature fusion to address these issues.The proposed algorithm extracts different local features from feature maps of different scales and then fuses them to obtain a comprehensive feature representation.This representation is then fed into a subsequent camera fingerprint classification network.Building upon the Swin-T network,we utilize Transformer Blocks and Graph Convolutional Network(GCN)modules to fuse multi-scale features from different stages of the backbone network.Furthermore,we conduct experiments on established datasets to demonstrate the feasibility and effectiveness of the proposed approach.
基金This work was supported by National Natural Science Foundation of China(No.62172308,No.U1626107,No.61972297,No.62172144,and No.62062019).
文摘Power Shell has been widely deployed in fileless malware and advanced persistent threat(APT)attacks due to its high stealthiness and live-off-theland technique.However,existing works mainly focus on deobfuscation and malicious detection,lacking the malicious Power Shell families classification and behavior analysis.Moreover,the state-of-the-art methods fail to capture fine-grained features and semantic relationships,resulting in low robustness and accuracy.To this end,we propose Power Detector,a novel malicious Power Shell script detector based on multimodal semantic fusion and deep learning.Specifically,we design four feature extraction methods to extract key features from character,token,abstract syntax tree(AST),and semantic knowledge graph.Then,we intelligently design four embeddings(i.e.,Char2Vec,Token2Vec,AST2Vec,and Rela2Vec) and construct a multi-modal fusion algorithm to concatenate feature vectors from different views.Finally,we propose a combined model based on transformer and CNN-Bi LSTM to implement Power Shell family detection.Our experiments with five types of Power Shell attacks show that PowerDetector can accurately detect various obfuscated and stealth PowerShell scripts,with a 0.9402 precision,a 0.9358 recall,and a 0.9374 F1-score.Furthermore,through singlemodal and multi-modal comparison experiments,we demonstrate that PowerDetector’s multi-modal embedding and deep learning model can achieve better accuracy and even identify more unknown attacks.
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.
文摘Manhole cover defect recognition is of significant practical importance as it can accurately identify damaged or missing covers, enabling timely replacement and maintenance. Traditional manhole cover detection techniques primarily focus on detecting the presence of covers rather than classifying the types of defects. However, manhole cover defects exhibit small inter-class feature differences and large intra-class feature variations, which makes their recognition challenging. To improve the classification of manhole cover defect types, we propose a Progressive Dual-Branch Feature Fusion Network (PDBFFN). The baseline backbone network adopts a multi-stage hierarchical architecture design using Res-Net50 as the visual feature extractor, from which both local and global information is obtained. Additionally, a Feature Enhancement Module (FEM) and a Fusion Module (FM) are introduced to enhance the network’s ability to learn critical features. Experimental results demonstrate that our model achieves a classification accuracy of 82.6% on a manhole cover defect dataset, outperforming several state-of-the-art fine-grained image classification models.
文摘Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware resources. To address this issue, the MobileNetV1 network was developed, which employs depthwise convolution to reduce network complexity. MobileNetV1 employs a stride of 2 in several convolutional layers to decrease the spatial resolution of feature maps, thereby lowering computational costs. However, this stride setting can lead to a loss of spatial information, particularly affecting the detection and representation of smaller objects or finer details in images. To maintain the trade-off between complexity and model performance, a lightweight convolutional neural network with hierarchical multi-scale feature fusion based on the MobileNetV1 network is proposed. The network consists of two main subnetworks. The first subnetwork uses a depthwise dilated separable convolution (DDSC) layer to learn imaging features with fewer parameters, which results in a lightweight and computationally inexpensive network. Furthermore, depthwise dilated convolution in DDSC layer effectively expands the field of view of filters, allowing them to incorporate a larger context. The second subnetwork is a hierarchical multi-scale feature fusion (HMFF) module that uses parallel multi-resolution branches architecture to process the input feature map in order to extract the multi-scale feature information of the input image. Experimental results on the CIFAR-10, Malaria, and KvasirV1 datasets demonstrate that the proposed method is efficient, reducing the network parameters and computational cost by 65.02% and 39.78%, respectively, while maintaining the network performance compared to the MobileNetV1 baseline.
基金supported by the National Natural Science Foundation of China(Grant No.81973695)Discipline with Strong Characteristics of Liaocheng University-Intelligent Science and Technology(Grant No.319462208).
文摘Event extraction stands as a significant endeavor within the realm of information extraction,aspiring to automatically extract structured event information from vast volumes of unstructured text.Extracting event elements from multi-modal data remains a challenging task due to the presence of a large number of images and overlapping event elements in the data.Although researchers have proposed various methods to accomplish this task,most existing event extraction models cannot address these challenges because they are only applicable to text scenarios.To solve the above issues,this paper proposes a multi-modal event extraction method based on knowledge fusion.Specifically,for event-type recognition,we use a meticulous pipeline approach that integrates multiple pre-trained models.This approach enables a more comprehensive capture of the multidimensional event semantic features present in military texts,thereby enhancing the interconnectedness of information between trigger words and events.For event element extraction,we propose a method for constructing a priori templates that combine event types with corresponding trigger words.This approach facilitates the acquisition of fine-grained input samples containing event trigger words,thus enabling the model to understand the semantic relationships between elements in greater depth.Furthermore,a fusion method for spatial mapping of textual event elements and image elements is proposed to reduce the category number overload and effectively achieve multi-modal knowledge fusion.The experimental results based on the CCKS 2022 dataset show that our method has achieved competitive results,with a comprehensive evaluation value F1-score of 53.4%for the model.These results validate the effectiveness of our method in extracting event elements from multi-modal data.