An improved model based on you only look once version 8(YOLOv8)is proposed to solve the problem of low detection accuracy due to the diversity of object sizes in optical remote sensing images.Firstly,the feature pyram...An improved model based on you only look once version 8(YOLOv8)is proposed to solve the problem of low detection accuracy due to the diversity of object sizes in optical remote sensing images.Firstly,the feature pyramid network(FPN)structure of the original YOLOv8 mode is replaced by the generalized-FPN(GFPN)structure in GiraffeDet to realize the"cross-layer"and"cross-scale"adaptive feature fusion,to enrich the semantic information and spatial information on the feature map to improve the target detection ability of the model.Secondly,a pyramid-pool module of multi atrous spatial pyramid pooling(MASPP)is designed by using the idea of atrous convolution and feature pyramid structure to extract multi-scale features,so as to improve the processing ability of the model for multi-scale objects.The experimental results show that the detection accuracy of the improved YOLOv8 model on DIOR dataset is 92%and mean average precision(mAP)is 87.9%,respectively 3.5%and 1.7%higher than those of the original model.It is proved the detection and classification ability of the proposed model on multi-dimensional optical remote sensing target has been improved.展开更多
To address the challenge of missing modal information in entity alignment and to mitigate information loss or bias arising frommodal heterogeneity during fusion,while also capturing shared information acrossmodalities...To address the challenge of missing modal information in entity alignment and to mitigate information loss or bias arising frommodal heterogeneity during fusion,while also capturing shared information acrossmodalities,this paper proposes a Multi-modal Pre-synergistic Entity Alignmentmodel based on Cross-modalMutual Information Strategy Optimization(MPSEA).The model first employs independent encoders to process multi-modal features,including text,images,and numerical values.Next,a multi-modal pre-synergistic fusion mechanism integrates graph structural and visual modal features into the textual modality as preparatory information.This pre-fusion strategy enables unified perception of heterogeneous modalities at the model’s initial stage,reducing discrepancies during the fusion process.Finally,using cross-modal deep perception reinforcement learning,the model achieves adaptive multilevel feature fusion between modalities,supporting learningmore effective alignment strategies.Extensive experiments on multiple public datasets show that the MPSEA method achieves gains of up to 7% in Hits@1 and 8.2% in MRR on the FBDB15K dataset,and up to 9.1% in Hits@1 and 7.7% in MRR on the FBYG15K dataset,compared to existing state-of-the-art methods.These results confirm the effectiveness of the proposed model.展开更多
Multi-modal Named Entity Recognition(MNER)aims to better identify meaningful textual entities by integrating information from images.Previous work has focused on extracting visual semantics at a fine-grained level,or ...Multi-modal Named Entity Recognition(MNER)aims to better identify meaningful textual entities by integrating information from images.Previous work has focused on extracting visual semantics at a fine-grained level,or obtaining entity related external knowledge from knowledge bases or Large Language Models(LLMs).However,these approaches ignore the poor semantic correlation between visual and textual modalities in MNER datasets and do not explore different multi-modal fusion approaches.In this paper,we present MMAVK,a multi-modal named entity recognition model with auxiliary visual knowledge and word-level fusion,which aims to leverage the Multi-modal Large Language Model(MLLM)as an implicit knowledge base.It also extracts vision-based auxiliary knowledge from the image formore accurate and effective recognition.Specifically,we propose vision-based auxiliary knowledge generation,which guides the MLLM to extract external knowledge exclusively derived from images to aid entity recognition by designing target-specific prompts,thus avoiding redundant recognition and cognitive confusion caused by the simultaneous processing of image-text pairs.Furthermore,we employ a word-level multi-modal fusion mechanism to fuse the extracted external knowledge with each word-embedding embedded from the transformerbased encoder.Extensive experimental results demonstrate that MMAVK outperforms or equals the state-of-the-art methods on the two classical MNER datasets,even when the largemodels employed have significantly fewer parameters than other baselines.展开更多
As the number and complexity of sensors in autonomous vehicles continue to rise,multimodal fusionbased object detection algorithms are increasingly being used to detect 3D environmental information,significantly advan...As the number and complexity of sensors in autonomous vehicles continue to rise,multimodal fusionbased object detection algorithms are increasingly being used to detect 3D environmental information,significantly advancing the development of perception technology in autonomous driving.To further promote the development of fusion algorithms and improve detection performance,this paper discusses the advantages and recent advancements of multimodal fusion-based object detection algorithms.Starting fromsingle-modal sensor detection,the paper provides a detailed overview of typical sensors used in autonomous driving and introduces object detection methods based on images and point clouds.For image-based detection methods,they are categorized into monocular detection and binocular detection based on different input types.For point cloud-based detection methods,they are classified into projection-based,voxel-based,point cluster-based,pillar-based,and graph structure-based approaches based on the technical pathways for processing point cloud features.Additionally,multimodal fusion algorithms are divided into Camera-LiDAR fusion,Camera-Radar fusion,Camera-LiDAR-Radar fusion,and other sensor fusion methods based on the types of sensors involved.Furthermore,the paper identifies five key future research directions in this field,aiming to provide insights for researchers engaged in multimodal fusion-based object detection algorithms and to encourage broader attention to the research and application of multimodal fusion-based object detection.展开更多
The sixth generation(6G)of mobile communication system is witnessing a new paradigm shift,i.e.,integrated sensing-communication system.A comprehensive dataset is a prerequisite for 6G integrated sensing-communication ...The sixth generation(6G)of mobile communication system is witnessing a new paradigm shift,i.e.,integrated sensing-communication system.A comprehensive dataset is a prerequisite for 6G integrated sensing-communication research.This paper develops a novel simulation dataset,named M3SC,for mixed multi-modal(MMM)sensing-communication integration,and the generation framework of the M3SC dataset is further given.To obtain multimodal sensory data in physical space and communication data in electromagnetic space,we utilize Air-Sim and WaveFarer to collect multi-modal sensory data and exploit Wireless InSite to collect communication data.Furthermore,the in-depth integration and precise alignment of AirSim,WaveFarer,andWireless InSite are achieved.The M3SC dataset covers various weather conditions,multiplex frequency bands,and different times of the day.Currently,the M3SC dataset contains 1500 snapshots,including 80 RGB images,160 depth maps,80 LiDAR point clouds,256 sets of mmWave waveforms with 8 radar point clouds,and 72 channel impulse response(CIR)matrices per snapshot,thus totaling 120,000 RGB images,240,000 depth maps,120,000 LiDAR point clouds,384,000 sets of mmWave waveforms with 12,000 radar point clouds,and 108,000 CIR matrices.The data processing result presents the multi-modal sensory information and communication channel statistical properties.Finally,the MMM sensing-communication application,which can be supported by the M3SC dataset,is discussed.展开更多
Iced transmission line galloping poses a significant threat to the safety and reliability of power systems,leading directly to line tripping,disconnections,and power outages.Existing early warning methods of iced tran...Iced transmission line galloping poses a significant threat to the safety and reliability of power systems,leading directly to line tripping,disconnections,and power outages.Existing early warning methods of iced transmission line galloping suffer from issues such as reliance on a single data source,neglect of irregular time series,and lack of attention-based closed-loop feedback,resulting in high rates of missed and false alarms.To address these challenges,we propose an Internet of Things(IoT)empowered early warning method of transmission line galloping that integrates time series data from optical fiber sensing and weather forecast.Initially,the method applies a primary adaptive weighted fusion to the IoT empowered optical fiber real-time sensing data and weather forecast data,followed by a secondary fusion based on a Back Propagation(BP)neural network,and uses the K-medoids algorithm for clustering the fused data.Furthermore,an adaptive irregular time series perception adjustment module is introduced into the traditional Gated Recurrent Unit(GRU)network,and closed-loop feedback based on attentionmechanism is employed to update network parameters through gradient feedback of the loss function,enabling closed-loop training and time series data prediction of the GRU network model.Subsequently,considering various types of prediction data and the duration of icing,an iced transmission line galloping risk coefficient is established,and warnings are categorized based on this coefficient.Finally,using an IoT-driven realistic dataset of iced transmission line galloping,the effectiveness of the proposed method is validated through multi-dimensional simulation scenarios.展开更多
In China, accelerating industrialization and urbanization followinghigh-speed economic development and population increases have greatly impacted land use/coverchanges, making it imperative to obtain accurate and up t...In China, accelerating industrialization and urbanization followinghigh-speed economic development and population increases have greatly impacted land use/coverchanges, making it imperative to obtain accurate and up to date iufbimation on changes soas toevaluate their environmental effects. The major purpose of this study was to develop a new method tofuse lower spatial resolution multispectral satellite images with higher spatial resolutionpanchromatic ones to assist in land use/cover mapping.An algorithm of a new fusion method known asedge enhancement intensity modulation (EEIM) was proposed to merge two optical image data sets ofdifferent spectral ranges. The results showed that the EEIM image was quite similar in color tolower resolution multispectral images, and the fused product was better able to preserve spectralinformation. Thus, compared to conventional approaches, the spectral distortion of the fused imageswas markedly reduced. Therefore, the EEIM fusion method could be utilized to fuse remote sensingdata from the same or different sensors, including TM images and SPOT5 panchromatic images,providing high quality land use/cover images.展开更多
Image registration is an indispensable component in multi-source remote sensing image processing. In this paper, we put forward a remote sensing image registration method by including an improved multi-scale and multi...Image registration is an indispensable component in multi-source remote sensing image processing. In this paper, we put forward a remote sensing image registration method by including an improved multi-scale and multi-direction Harris algorithm and a novel compound feature. Multi-scale circle Gaussian combined invariant moments and multi-direction gray level co-occurrence matrix are extracted as features for image matching. The proposed algorithm is evaluated on numerous multi-source remote sensor images with noise and illumination changes. Extensive experimental studies prove that our proposed method is capable of receiving stable and even distribution of key points as well as obtaining robust and accurate correspondence matches. It is a promising scheme in multi-source remote sensing image registration.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
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
Current works of environmental perception for connected autonomous electrified vehicles(CAEVs)mainly focus on the object detection task in good weather and illumination conditions,they often perform poorly in adverse ...Current works of environmental perception for connected autonomous electrified vehicles(CAEVs)mainly focus on the object detection task in good weather and illumination conditions,they often perform poorly in adverse scenarios and have a vague scene parsing ability.This paper aims to develop an end-to-end sharpening mixture of experts(SMoE)fusion framework to improve the robustness and accuracy of the perception systems for CAEVs in complex illumination and weather conditions.Three original contributions make our work distinctive from the existing relevant literature.The Complex KITTI dataset is introduced which consists of 7481 pairs of modified KITTI RGB images and the generated LiDAR dense depth maps,and this dataset is fine annotated in instance-level with the proposed semi-automatic annotation method.The SMoE fusion approach is devised to adaptively learn the robust kernels from complementary modalities.Comprehensive comparative experiments are implemented,and the results show that the proposed SMoE framework yield significant improvements over the other fusion techniques in adverse environmental conditions.This research proposes a SMoE fusion framework to improve the scene parsing ability of the perception systems for CAEVs in adverse conditions.展开更多
In mobile machinery,hydro-mechanical pumps are increasingly replaced by electronically controlled pumps to improve the automation level,but diversified control functions(e.g.,power limitation and pressure cut-off)are ...In mobile machinery,hydro-mechanical pumps are increasingly replaced by electronically controlled pumps to improve the automation level,but diversified control functions(e.g.,power limitation and pressure cut-off)are integrated into the electronic controller only from the pump level,leading to the potential instability of the overall system.To solve this problem,a multi-mode electrohydraulic load sensing(MELS)control scheme is proposed especially considering the switching stability from the system level,which includes four working modes of flow control,load sensing,power limitation,and pressure control.Depending on the actual working requirements,the switching rules for the different modes and the switching direction(i.e.,the modes can be switched bilaterally or unilaterally)are defined.The priority of different modes is also defined,from high to low:pressure control,power limitation,load sensing,and flow control.When multiple switching rules are satisfied at the same time,the system switches to the control mode with the highest priority.In addition,the switching stability between flow control and pressure control modes is analyzed,and the controller parameters that guarantee the switching stability are obtained.A comparative study is carried out based on a test rig with a 2-ton hydraulic excavator.The results show that the MELS controller can achieve the control functions of proper flow supplement,power limitation,and pressure cut-off,which has good stability performance when switching between different control modes.This research proposes the MELS control method that realizes the stability of multi-mode switching of the hydraulic system of mobile machinery under different working conditions.展开更多
Due to the data acquired by most optical earth observation satellite such as IKONOS, QuickBird-2 and GF-1 consist of a panchromatic image with high spatial resolution and multiple multispectral images with low spatial...Due to the data acquired by most optical earth observation satellite such as IKONOS, QuickBird-2 and GF-1 consist of a panchromatic image with high spatial resolution and multiple multispectral images with low spatial resolution. Many image fusion techniques have been developed to produce high resolution multispectral image. Considering panchromatic image and multispectral images contain the same spatial information with different accuracy, using the least square theory could estimate optimal spatial information. Compared with previous spatial details injection mode, this mode is more accurate and robust. In this paper, an image fusion method using Bidimensional Empirical Mode Decomposition (BEMD) and the least square theory is proposed to merge multispectral images and panchromatic image. After multi-spectral images were transformed from RGB space into IHS space, next I component and Panchromatic are decomposed by BEMD, then using the least squares theory to evaluate optimal spatial information and inject spatial information, finally completing fusion through inverse BEMD and inverse intensity-hue-saturation transform. Two data sets are used to evaluate the proposed fusion method, GF-1 images and QuickBird-2 images. The fusion images were evaluated visually and statistically. The evaluation results show the method proposed in this paper achieves the best performance compared with the conventional method.展开更多
For the analysis of spinal and disc diseases,automated tissue segmentation of the lumbar spine is vital.Due to the continuous and concentrated location of the target,the abundance of edge features,and individual diffe...For the analysis of spinal and disc diseases,automated tissue segmentation of the lumbar spine is vital.Due to the continuous and concentrated location of the target,the abundance of edge features,and individual differences,conventional automatic segmentation methods perform poorly.Since the success of deep learning in the segmentation of medical images has been shown in the past few years,it has been applied to this task in a number of ways.The multi-scale and multi-modal features of lumbar tissues,however,are rarely explored by methodologies of deep learning.Because of the inadequacies in medical images availability,it is crucial to effectively fuse various modes of data collection for model training to alleviate the problem of insufficient samples.In this paper,we propose a novel multi-modality hierarchical fusion network(MHFN)for improving lumbar spine segmentation by learning robust feature representations from multi-modality magnetic resonance images.An adaptive group fusion module(AGFM)is introduced in this paper to fuse features from various modes to extract cross-modality features that could be valuable.Furthermore,to combine features from low to high levels of cross-modality,we design a hierarchical fusion structure based on AGFM.Compared to the other feature fusion methods,AGFM is more effective based on experimental results on multi-modality MR images of the lumbar spine.To further enhance segmentation accuracy,we compare our network with baseline fusion structures.Compared to the baseline fusion structures(input-level:76.27%,layer-level:78.10%,decision-level:79.14%),our network was able to segment fractured vertebrae more accurately(85.05%).展开更多
Laser cleaning is a highly nonlinear physical process for solving poor single-modal(e.g., acoustic or vision)detection performance and low inter-information utilization. In this study, a multi-modal feature fusion net...Laser cleaning is a highly nonlinear physical process for solving poor single-modal(e.g., acoustic or vision)detection performance and low inter-information utilization. In this study, a multi-modal feature fusion network model was constructed based on a laser paint removal experiment. The alignment of heterogeneous data under different modals was solved by combining the piecewise aggregate approximation and gramian angular field. Moreover, the attention mechanism was introduced to optimize the dual-path network and dense connection network, enabling the sampling characteristics to be extracted and integrated. Consequently, the multi-modal discriminant detection of laser paint removal was realized. According to the experimental results, the verification accuracy of the constructed model on the experimental dataset was 99.17%, which is 5.77% higher than the optimal single-modal detection results of the laser paint removal. The feature extraction network was optimized by the attention mechanism, and the model accuracy was increased by 3.3%. Results verify the improved classification performance of the constructed multi-modal feature fusion model in detecting laser paint removal, the effective integration of acoustic data and visual image data, and the accurate detection of laser paint removal.展开更多
To improve the monitoring precision of lake chlorophyll a (Chl-a), this paper presents a fusion method based on Choquet Fuzzy Integral (CFI) to estimate the Chl-a concentration. A group of BPNN models are designed. Th...To improve the monitoring precision of lake chlorophyll a (Chl-a), this paper presents a fusion method based on Choquet Fuzzy Integral (CFI) to estimate the Chl-a concentration. A group of BPNN models are designed. The output of multiple BPNN model is fused by the CFI. Meanwhile, to resolve the over-fitting problem caused by a small number of training sets, we design an algorithm that fully considers neighbor sampling information. A classification experiment of the Chl-a concentration of the Taihu Lake is conducted. The result shows that, the proposed approach is superior to the classification using a single neural network classifier, and the CFI fusion method has higher identification accuracy.展开更多
Multi-modal knowledge graph completion(MMKGC)aims to complete missing entities or relations in multi-modal knowledge graphs,thereby discovering more previously unknown triples.Due to the continuous growth of data and ...Multi-modal knowledge graph completion(MMKGC)aims to complete missing entities or relations in multi-modal knowledge graphs,thereby discovering more previously unknown triples.Due to the continuous growth of data and knowledge and the limitations of data sources,the visual knowledge within the knowledge graphs is generally of low quality,and some entities suffer from the issue of missing visual modality.Nevertheless,previous studies of MMKGC have primarily focused on how to facilitate modality interaction and fusion while neglecting the problems of low modality quality and modality missing.In this case,mainstream MMKGC models only use pre-trained visual encoders to extract features and transfer the semantic information to the joint embeddings through modal fusion,which inevitably suffers from problems such as error propagation and increased uncertainty.To address these problems,we propose a Multi-modal knowledge graph Completion model based on Super-resolution and Detailed Description Generation(MMCSD).Specifically,we leverage a pre-trained residual network to enhance the resolution and improve the quality of the visual modality.Moreover,we design multi-level visual semantic extraction and entity description generation,thereby further extracting entity semantics from structural triples and visual images.Meanwhile,we train a variational multi-modal auto-encoder and utilize a pre-trained multi-modal language model to complement the missing visual features.We conducted experiments on FB15K-237 and DB13K,and the results showed that MMCSD can effectively perform MMKGC and achieve state-of-the-art performance.展开更多
Integrating multiple medical imaging techniques,including Magnetic Resonance Imaging(MRI),Computed Tomography,Positron Emission Tomography(PET),and ultrasound,provides a comprehensive view of the patient health status...Integrating multiple medical imaging techniques,including Magnetic Resonance Imaging(MRI),Computed Tomography,Positron Emission Tomography(PET),and ultrasound,provides a comprehensive view of the patient health status.Each of these methods contributes unique diagnostic insights,enhancing the overall assessment of patient condition.Nevertheless,the amalgamation of data from multiple modalities presents difficulties due to disparities in resolution,data collection methods,and noise levels.While traditional models like Convolutional Neural Networks(CNNs)excel in single-modality tasks,they struggle to handle multi-modal complexities,lacking the capacity to model global relationships.This research presents a novel approach for examining multi-modal medical imagery using a transformer-based system.The framework employs self-attention and cross-attention mechanisms to synchronize and integrate features across various modalities.Additionally,it shows resilience to variations in noise and image quality,making it adaptable for real-time clinical use.To address the computational hurdles linked to transformer models,particularly in real-time clinical applications in resource-constrained environments,several optimization techniques have been integrated to boost scalability and efficiency.Initially,a streamlined transformer architecture was adopted to minimize the computational load while maintaining model effectiveness.Methods such as model pruning,quantization,and knowledge distillation have been applied to reduce the parameter count and enhance the inference speed.Furthermore,efficient attention mechanisms such as linear or sparse attention were employed to alleviate the substantial memory and processing requirements of traditional self-attention operations.For further deployment optimization,researchers have implemented hardware-aware acceleration strategies,including the use of TensorRT and ONNX-based model compression,to ensure efficient execution on edge devices.These optimizations allow the approach to function effectively in real-time clinical settings,ensuring viability even in environments with limited resources.Future research directions include integrating non-imaging data to facilitate personalized treatment and enhancing computational efficiency for implementation in resource-limited environments.This study highlights the transformative potential of transformer models in multi-modal medical imaging,offering improvements in diagnostic accuracy and patient care outcomes.展开更多
The multi-modal characteristics of mineral particles play a pivotal role in enhancing the classification accuracy,which is critical for obtaining a profound understanding of the Earth's composition and ensuring ef...The multi-modal characteristics of mineral particles play a pivotal role in enhancing the classification accuracy,which is critical for obtaining a profound understanding of the Earth's composition and ensuring effective exploitation utilization of its resources.However,the existing methods for classifying mineral particles do not fully utilize these multi-modal features,thereby limiting the classification accuracy.Furthermore,when conventional multi-modal image classification methods are applied to planepolarized and cross-polarized sequence images of mineral particles,they encounter issues such as information loss,misaligned features,and challenges in spatiotemporal feature extraction.To address these challenges,we propose a multi-modal mineral particle polarization image classification network(MMGC-Net)for precise mineral particle classification.Initially,MMGC-Net employs a two-dimensional(2D)backbone network with shared parameters to extract features from two types of polarized images to ensure feature alignment.Subsequently,a cross-polarized intra-modal feature fusion module is designed to refine the spatiotemporal features from the extracted features of the cross-polarized sequence images.Ultimately,the inter-modal feature fusion module integrates the two types of modal features to enhance the classification precision.Quantitative and qualitative experimental results indicate that when compared with the current state-of-the-art multi-modal image classification methods,MMGC-Net demonstrates marked superiority in terms of mineral particle multi-modal feature learning and four classification evaluation metrics.It also demonstrates better stability than the existing models.展开更多
The primary objective of Chinese spelling correction(CSC)is to detect and correct erroneous characters in Chinese text,which can result from various factors,such as inaccuracies in pinyin representation,character rese...The primary objective of Chinese spelling correction(CSC)is to detect and correct erroneous characters in Chinese text,which can result from various factors,such as inaccuracies in pinyin representation,character resemblance,and semantic discrepancies.However,existing methods often struggle to fully address these types of errors,impacting the overall correction accuracy.This paper introduces a multi-modal feature encoder designed to efficiently extract features from three distinct modalities:pinyin,semantics,and character morphology.Unlike previous methods that rely on direct fusion or fixed-weight summation to integrate multi-modal information,our approach employs a multi-head attention mechanism to focuse more on relevant modal information while dis-regarding less pertinent data.To prevent issues such as gradient explosion or vanishing,the model incorporates a residual connection of the original text vector for fine-tuning.This approach ensures robust model performance by maintaining essential linguistic details throughout the correction process.Experimental evaluations on the SIGHAN benchmark dataset demonstrate that the pro-posed model outperforms baseline approaches across various metrics and datasets,confirming its effectiveness and feasibility.展开更多
基金supported by the National Natural Science Foundation of China(No.62241109)the Tianjin Science and Technology Commissioner Project(No.20YDTPJC01110)。
文摘An improved model based on you only look once version 8(YOLOv8)is proposed to solve the problem of low detection accuracy due to the diversity of object sizes in optical remote sensing images.Firstly,the feature pyramid network(FPN)structure of the original YOLOv8 mode is replaced by the generalized-FPN(GFPN)structure in GiraffeDet to realize the"cross-layer"and"cross-scale"adaptive feature fusion,to enrich the semantic information and spatial information on the feature map to improve the target detection ability of the model.Secondly,a pyramid-pool module of multi atrous spatial pyramid pooling(MASPP)is designed by using the idea of atrous convolution and feature pyramid structure to extract multi-scale features,so as to improve the processing ability of the model for multi-scale objects.The experimental results show that the detection accuracy of the improved YOLOv8 model on DIOR dataset is 92%and mean average precision(mAP)is 87.9%,respectively 3.5%and 1.7%higher than those of the original model.It is proved the detection and classification ability of the proposed model on multi-dimensional optical remote sensing target has been improved.
基金partially supported by the National Natural Science Foundation of China under Grants 62471493 and 62402257(for conceptualization and investigation)partially supported by the Natural Science Foundation of Shandong Province,China under Grants ZR2023LZH017,ZR2024MF066,and 2023QF025(for formal analysis and validation)+1 种基金partially supported by the Open Foundation of Key Laboratory of Computing Power Network and Information Security,Ministry of Education,Qilu University of Technology(Shandong Academy of Sciences)under Grant 2023ZD010(for methodology and model design)partially supported by the Russian Science Foundation(RSF)Project under Grant 22-71-10095-P(for validation and results verification).
文摘To address the challenge of missing modal information in entity alignment and to mitigate information loss or bias arising frommodal heterogeneity during fusion,while also capturing shared information acrossmodalities,this paper proposes a Multi-modal Pre-synergistic Entity Alignmentmodel based on Cross-modalMutual Information Strategy Optimization(MPSEA).The model first employs independent encoders to process multi-modal features,including text,images,and numerical values.Next,a multi-modal pre-synergistic fusion mechanism integrates graph structural and visual modal features into the textual modality as preparatory information.This pre-fusion strategy enables unified perception of heterogeneous modalities at the model’s initial stage,reducing discrepancies during the fusion process.Finally,using cross-modal deep perception reinforcement learning,the model achieves adaptive multilevel feature fusion between modalities,supporting learningmore effective alignment strategies.Extensive experiments on multiple public datasets show that the MPSEA method achieves gains of up to 7% in Hits@1 and 8.2% in MRR on the FBDB15K dataset,and up to 9.1% in Hits@1 and 7.7% in MRR on the FBYG15K dataset,compared to existing state-of-the-art methods.These results confirm the effectiveness of the proposed model.
基金funded by Research Project,grant number BHQ090003000X03.
文摘Multi-modal Named Entity Recognition(MNER)aims to better identify meaningful textual entities by integrating information from images.Previous work has focused on extracting visual semantics at a fine-grained level,or obtaining entity related external knowledge from knowledge bases or Large Language Models(LLMs).However,these approaches ignore the poor semantic correlation between visual and textual modalities in MNER datasets and do not explore different multi-modal fusion approaches.In this paper,we present MMAVK,a multi-modal named entity recognition model with auxiliary visual knowledge and word-level fusion,which aims to leverage the Multi-modal Large Language Model(MLLM)as an implicit knowledge base.It also extracts vision-based auxiliary knowledge from the image formore accurate and effective recognition.Specifically,we propose vision-based auxiliary knowledge generation,which guides the MLLM to extract external knowledge exclusively derived from images to aid entity recognition by designing target-specific prompts,thus avoiding redundant recognition and cognitive confusion caused by the simultaneous processing of image-text pairs.Furthermore,we employ a word-level multi-modal fusion mechanism to fuse the extracted external knowledge with each word-embedding embedded from the transformerbased encoder.Extensive experimental results demonstrate that MMAVK outperforms or equals the state-of-the-art methods on the two classical MNER datasets,even when the largemodels employed have significantly fewer parameters than other baselines.
基金funded by the Yangtze River Delta Science and Technology Innovation Community Joint Research Project(2023CSJGG1600)the Natural Science Foundation of Anhui Province(2208085MF173)Wuhu“ChiZhu Light”Major Science and Technology Project(2023ZD01,2023ZD03).
文摘As the number and complexity of sensors in autonomous vehicles continue to rise,multimodal fusionbased object detection algorithms are increasingly being used to detect 3D environmental information,significantly advancing the development of perception technology in autonomous driving.To further promote the development of fusion algorithms and improve detection performance,this paper discusses the advantages and recent advancements of multimodal fusion-based object detection algorithms.Starting fromsingle-modal sensor detection,the paper provides a detailed overview of typical sensors used in autonomous driving and introduces object detection methods based on images and point clouds.For image-based detection methods,they are categorized into monocular detection and binocular detection based on different input types.For point cloud-based detection methods,they are classified into projection-based,voxel-based,point cluster-based,pillar-based,and graph structure-based approaches based on the technical pathways for processing point cloud features.Additionally,multimodal fusion algorithms are divided into Camera-LiDAR fusion,Camera-Radar fusion,Camera-LiDAR-Radar fusion,and other sensor fusion methods based on the types of sensors involved.Furthermore,the paper identifies five key future research directions in this field,aiming to provide insights for researchers engaged in multimodal fusion-based object detection algorithms and to encourage broader attention to the research and application of multimodal fusion-based object detection.
基金This work was supported in part by the Ministry National Key Research and Development Project(Grant No.2020AAA0108101)the National Natural Science Foundation of China(Grants No.62125101,62341101,62001018,and 62301011)+1 种基金Shandong Natural Science Foundation(Grant No.ZR2023YQ058)the New Cornerstone Science Foundation through the XPLORER PRIZE.The authors would like to thank Mengyuan Lu and Zengrui Han for their help in the construction of electromagnetic space in Wireless InSite simulation platform and Weibo Wen,Qi Duan,and Yong Yu for their help in the construction of phys ical space in AirSim simulation platform.
文摘The sixth generation(6G)of mobile communication system is witnessing a new paradigm shift,i.e.,integrated sensing-communication system.A comprehensive dataset is a prerequisite for 6G integrated sensing-communication research.This paper develops a novel simulation dataset,named M3SC,for mixed multi-modal(MMM)sensing-communication integration,and the generation framework of the M3SC dataset is further given.To obtain multimodal sensory data in physical space and communication data in electromagnetic space,we utilize Air-Sim and WaveFarer to collect multi-modal sensory data and exploit Wireless InSite to collect communication data.Furthermore,the in-depth integration and precise alignment of AirSim,WaveFarer,andWireless InSite are achieved.The M3SC dataset covers various weather conditions,multiplex frequency bands,and different times of the day.Currently,the M3SC dataset contains 1500 snapshots,including 80 RGB images,160 depth maps,80 LiDAR point clouds,256 sets of mmWave waveforms with 8 radar point clouds,and 72 channel impulse response(CIR)matrices per snapshot,thus totaling 120,000 RGB images,240,000 depth maps,120,000 LiDAR point clouds,384,000 sets of mmWave waveforms with 12,000 radar point clouds,and 108,000 CIR matrices.The data processing result presents the multi-modal sensory information and communication channel statistical properties.Finally,the MMM sensing-communication application,which can be supported by the M3SC dataset,is discussed.
基金research was funded by Science and Technology Project of State Grid Corporation of China under grant number 5200-202319382A-2-3-XG.
文摘Iced transmission line galloping poses a significant threat to the safety and reliability of power systems,leading directly to line tripping,disconnections,and power outages.Existing early warning methods of iced transmission line galloping suffer from issues such as reliance on a single data source,neglect of irregular time series,and lack of attention-based closed-loop feedback,resulting in high rates of missed and false alarms.To address these challenges,we propose an Internet of Things(IoT)empowered early warning method of transmission line galloping that integrates time series data from optical fiber sensing and weather forecast.Initially,the method applies a primary adaptive weighted fusion to the IoT empowered optical fiber real-time sensing data and weather forecast data,followed by a secondary fusion based on a Back Propagation(BP)neural network,and uses the K-medoids algorithm for clustering the fused data.Furthermore,an adaptive irregular time series perception adjustment module is introduced into the traditional Gated Recurrent Unit(GRU)network,and closed-loop feedback based on attentionmechanism is employed to update network parameters through gradient feedback of the loss function,enabling closed-loop training and time series data prediction of the GRU network model.Subsequently,considering various types of prediction data and the duration of icing,an iced transmission line galloping risk coefficient is established,and warnings are categorized based on this coefficient.Finally,using an IoT-driven realistic dataset of iced transmission line galloping,the effectiveness of the proposed method is validated through multi-dimensional simulation scenarios.
基金Project supported by the Knowledge Innovation Program of Chinese Academy of Sciences (No. KZCX3-SW-427), the National Key Basic Research Support Foundation of China (NKBRSF) (No. 2002CB410810) and the China Scholarship Council (No. 2003836044).
文摘In China, accelerating industrialization and urbanization followinghigh-speed economic development and population increases have greatly impacted land use/coverchanges, making it imperative to obtain accurate and up to date iufbimation on changes soas toevaluate their environmental effects. The major purpose of this study was to develop a new method tofuse lower spatial resolution multispectral satellite images with higher spatial resolutionpanchromatic ones to assist in land use/cover mapping.An algorithm of a new fusion method known asedge enhancement intensity modulation (EEIM) was proposed to merge two optical image data sets ofdifferent spectral ranges. The results showed that the EEIM image was quite similar in color tolower resolution multispectral images, and the fused product was better able to preserve spectralinformation. Thus, compared to conventional approaches, the spectral distortion of the fused imageswas markedly reduced. Therefore, the EEIM fusion method could be utilized to fuse remote sensingdata from the same or different sensors, including TM images and SPOT5 panchromatic images,providing high quality land use/cover images.
基金supported by National Nature Science Foundation of China (Nos. 61462046 and 61762052)Natural Science Foundation of Jiangxi Province (Nos. 20161BAB202049 and 20161BAB204172)+2 种基金the Bidding Project of the Key Laboratory of Watershed Ecology and Geographical Environment Monitoring, NASG (Nos. WE2016003, WE2016013 and WE2016015)the Science and Technology Research Projects of Jiangxi Province Education Department (Nos. GJJ160741, GJJ170632 and GJJ170633)the Art Planning Project of Jiangxi Province (Nos. YG2016250 and YG2017381)
文摘Image registration is an indispensable component in multi-source remote sensing image processing. In this paper, we put forward a remote sensing image registration method by including an improved multi-scale and multi-direction Harris algorithm and a novel compound feature. Multi-scale circle Gaussian combined invariant moments and multi-direction gray level co-occurrence matrix are extracted as features for image matching. The proposed algorithm is evaluated on numerous multi-source remote sensor images with noise and illumination changes. Extensive experimental studies prove that our proposed method is capable of receiving stable and even distribution of key points as well as obtaining robust and accurate correspondence matches. It is a promising scheme in multi-source remote sensing image registration.
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Supported by National Natural Science Foundation of China(Grant Nos.51975118,52025121,51975103,51905095)National Natural Science Foundation of Jiangsu Province(Grant No.BK20180401).
文摘Current works of environmental perception for connected autonomous electrified vehicles(CAEVs)mainly focus on the object detection task in good weather and illumination conditions,they often perform poorly in adverse scenarios and have a vague scene parsing ability.This paper aims to develop an end-to-end sharpening mixture of experts(SMoE)fusion framework to improve the robustness and accuracy of the perception systems for CAEVs in complex illumination and weather conditions.Three original contributions make our work distinctive from the existing relevant literature.The Complex KITTI dataset is introduced which consists of 7481 pairs of modified KITTI RGB images and the generated LiDAR dense depth maps,and this dataset is fine annotated in instance-level with the proposed semi-automatic annotation method.The SMoE fusion approach is devised to adaptively learn the robust kernels from complementary modalities.Comprehensive comparative experiments are implemented,and the results show that the proposed SMoE framework yield significant improvements over the other fusion techniques in adverse environmental conditions.This research proposes a SMoE fusion framework to improve the scene parsing ability of the perception systems for CAEVs in adverse conditions.
基金National Key Research and Development Program of China(Grant No.2020YFB2009702)National Natural Science Foundation of China(Grant Nos.52075055,U21A20124 and 52111530069)Chongqing Natural Science Foundation of China(Grant No.cstc2020jcyj-msxmX0780)。
文摘In mobile machinery,hydro-mechanical pumps are increasingly replaced by electronically controlled pumps to improve the automation level,but diversified control functions(e.g.,power limitation and pressure cut-off)are integrated into the electronic controller only from the pump level,leading to the potential instability of the overall system.To solve this problem,a multi-mode electrohydraulic load sensing(MELS)control scheme is proposed especially considering the switching stability from the system level,which includes four working modes of flow control,load sensing,power limitation,and pressure control.Depending on the actual working requirements,the switching rules for the different modes and the switching direction(i.e.,the modes can be switched bilaterally or unilaterally)are defined.The priority of different modes is also defined,from high to low:pressure control,power limitation,load sensing,and flow control.When multiple switching rules are satisfied at the same time,the system switches to the control mode with the highest priority.In addition,the switching stability between flow control and pressure control modes is analyzed,and the controller parameters that guarantee the switching stability are obtained.A comparative study is carried out based on a test rig with a 2-ton hydraulic excavator.The results show that the MELS controller can achieve the control functions of proper flow supplement,power limitation,and pressure cut-off,which has good stability performance when switching between different control modes.This research proposes the MELS control method that realizes the stability of multi-mode switching of the hydraulic system of mobile machinery under different working conditions.
文摘Due to the data acquired by most optical earth observation satellite such as IKONOS, QuickBird-2 and GF-1 consist of a panchromatic image with high spatial resolution and multiple multispectral images with low spatial resolution. Many image fusion techniques have been developed to produce high resolution multispectral image. Considering panchromatic image and multispectral images contain the same spatial information with different accuracy, using the least square theory could estimate optimal spatial information. Compared with previous spatial details injection mode, this mode is more accurate and robust. In this paper, an image fusion method using Bidimensional Empirical Mode Decomposition (BEMD) and the least square theory is proposed to merge multispectral images and panchromatic image. After multi-spectral images were transformed from RGB space into IHS space, next I component and Panchromatic are decomposed by BEMD, then using the least squares theory to evaluate optimal spatial information and inject spatial information, finally completing fusion through inverse BEMD and inverse intensity-hue-saturation transform. Two data sets are used to evaluate the proposed fusion method, GF-1 images and QuickBird-2 images. The fusion images were evaluated visually and statistically. The evaluation results show the method proposed in this paper achieves the best performance compared with the conventional method.
基金supported in part by the Technology Innovation 2030 under Grant 2022ZD0211700.
文摘For the analysis of spinal and disc diseases,automated tissue segmentation of the lumbar spine is vital.Due to the continuous and concentrated location of the target,the abundance of edge features,and individual differences,conventional automatic segmentation methods perform poorly.Since the success of deep learning in the segmentation of medical images has been shown in the past few years,it has been applied to this task in a number of ways.The multi-scale and multi-modal features of lumbar tissues,however,are rarely explored by methodologies of deep learning.Because of the inadequacies in medical images availability,it is crucial to effectively fuse various modes of data collection for model training to alleviate the problem of insufficient samples.In this paper,we propose a novel multi-modality hierarchical fusion network(MHFN)for improving lumbar spine segmentation by learning robust feature representations from multi-modality magnetic resonance images.An adaptive group fusion module(AGFM)is introduced in this paper to fuse features from various modes to extract cross-modality features that could be valuable.Furthermore,to combine features from low to high levels of cross-modality,we design a hierarchical fusion structure based on AGFM.Compared to the other feature fusion methods,AGFM is more effective based on experimental results on multi-modality MR images of the lumbar spine.To further enhance segmentation accuracy,we compare our network with baseline fusion structures.Compared to the baseline fusion structures(input-level:76.27%,layer-level:78.10%,decision-level:79.14%),our network was able to segment fractured vertebrae more accurately(85.05%).
基金Project(51875491) supported by the National Natural Science Foundation of ChinaProject(2021T3069) supported by the Fujian Science and Technology Plan STS Project,China。
文摘Laser cleaning is a highly nonlinear physical process for solving poor single-modal(e.g., acoustic or vision)detection performance and low inter-information utilization. In this study, a multi-modal feature fusion network model was constructed based on a laser paint removal experiment. The alignment of heterogeneous data under different modals was solved by combining the piecewise aggregate approximation and gramian angular field. Moreover, the attention mechanism was introduced to optimize the dual-path network and dense connection network, enabling the sampling characteristics to be extracted and integrated. Consequently, the multi-modal discriminant detection of laser paint removal was realized. According to the experimental results, the verification accuracy of the constructed model on the experimental dataset was 99.17%, which is 5.77% higher than the optimal single-modal detection results of the laser paint removal. The feature extraction network was optimized by the attention mechanism, and the model accuracy was increased by 3.3%. Results verify the improved classification performance of the constructed multi-modal feature fusion model in detecting laser paint removal, the effective integration of acoustic data and visual image data, and the accurate detection of laser paint removal.
文摘To improve the monitoring precision of lake chlorophyll a (Chl-a), this paper presents a fusion method based on Choquet Fuzzy Integral (CFI) to estimate the Chl-a concentration. A group of BPNN models are designed. The output of multiple BPNN model is fused by the CFI. Meanwhile, to resolve the over-fitting problem caused by a small number of training sets, we design an algorithm that fully considers neighbor sampling information. A classification experiment of the Chl-a concentration of the Taihu Lake is conducted. The result shows that, the proposed approach is superior to the classification using a single neural network classifier, and the CFI fusion method has higher identification accuracy.
基金funded by Research Project,grant number BHQ090003000X03。
文摘Multi-modal knowledge graph completion(MMKGC)aims to complete missing entities or relations in multi-modal knowledge graphs,thereby discovering more previously unknown triples.Due to the continuous growth of data and knowledge and the limitations of data sources,the visual knowledge within the knowledge graphs is generally of low quality,and some entities suffer from the issue of missing visual modality.Nevertheless,previous studies of MMKGC have primarily focused on how to facilitate modality interaction and fusion while neglecting the problems of low modality quality and modality missing.In this case,mainstream MMKGC models only use pre-trained visual encoders to extract features and transfer the semantic information to the joint embeddings through modal fusion,which inevitably suffers from problems such as error propagation and increased uncertainty.To address these problems,we propose a Multi-modal knowledge graph Completion model based on Super-resolution and Detailed Description Generation(MMCSD).Specifically,we leverage a pre-trained residual network to enhance the resolution and improve the quality of the visual modality.Moreover,we design multi-level visual semantic extraction and entity description generation,thereby further extracting entity semantics from structural triples and visual images.Meanwhile,we train a variational multi-modal auto-encoder and utilize a pre-trained multi-modal language model to complement the missing visual features.We conducted experiments on FB15K-237 and DB13K,and the results showed that MMCSD can effectively perform MMKGC and achieve state-of-the-art performance.
基金supported by the Deanship of Research and Graduate Studies at King Khalid University under Small Research Project grant number RGP1/139/45.
文摘Integrating multiple medical imaging techniques,including Magnetic Resonance Imaging(MRI),Computed Tomography,Positron Emission Tomography(PET),and ultrasound,provides a comprehensive view of the patient health status.Each of these methods contributes unique diagnostic insights,enhancing the overall assessment of patient condition.Nevertheless,the amalgamation of data from multiple modalities presents difficulties due to disparities in resolution,data collection methods,and noise levels.While traditional models like Convolutional Neural Networks(CNNs)excel in single-modality tasks,they struggle to handle multi-modal complexities,lacking the capacity to model global relationships.This research presents a novel approach for examining multi-modal medical imagery using a transformer-based system.The framework employs self-attention and cross-attention mechanisms to synchronize and integrate features across various modalities.Additionally,it shows resilience to variations in noise and image quality,making it adaptable for real-time clinical use.To address the computational hurdles linked to transformer models,particularly in real-time clinical applications in resource-constrained environments,several optimization techniques have been integrated to boost scalability and efficiency.Initially,a streamlined transformer architecture was adopted to minimize the computational load while maintaining model effectiveness.Methods such as model pruning,quantization,and knowledge distillation have been applied to reduce the parameter count and enhance the inference speed.Furthermore,efficient attention mechanisms such as linear or sparse attention were employed to alleviate the substantial memory and processing requirements of traditional self-attention operations.For further deployment optimization,researchers have implemented hardware-aware acceleration strategies,including the use of TensorRT and ONNX-based model compression,to ensure efficient execution on edge devices.These optimizations allow the approach to function effectively in real-time clinical settings,ensuring viability even in environments with limited resources.Future research directions include integrating non-imaging data to facilitate personalized treatment and enhancing computational efficiency for implementation in resource-limited environments.This study highlights the transformative potential of transformer models in multi-modal medical imaging,offering improvements in diagnostic accuracy and patient care outcomes.
基金supported by the National Natural Science Foundation of China(Grant Nos.62071315 and 62271336).
文摘The multi-modal characteristics of mineral particles play a pivotal role in enhancing the classification accuracy,which is critical for obtaining a profound understanding of the Earth's composition and ensuring effective exploitation utilization of its resources.However,the existing methods for classifying mineral particles do not fully utilize these multi-modal features,thereby limiting the classification accuracy.Furthermore,when conventional multi-modal image classification methods are applied to planepolarized and cross-polarized sequence images of mineral particles,they encounter issues such as information loss,misaligned features,and challenges in spatiotemporal feature extraction.To address these challenges,we propose a multi-modal mineral particle polarization image classification network(MMGC-Net)for precise mineral particle classification.Initially,MMGC-Net employs a two-dimensional(2D)backbone network with shared parameters to extract features from two types of polarized images to ensure feature alignment.Subsequently,a cross-polarized intra-modal feature fusion module is designed to refine the spatiotemporal features from the extracted features of the cross-polarized sequence images.Ultimately,the inter-modal feature fusion module integrates the two types of modal features to enhance the classification precision.Quantitative and qualitative experimental results indicate that when compared with the current state-of-the-art multi-modal image classification methods,MMGC-Net demonstrates marked superiority in terms of mineral particle multi-modal feature learning and four classification evaluation metrics.It also demonstrates better stability than the existing models.
基金Supported by the National Natural Science Foundation of China(No.61472256,61170277)the Hujiang Foundation(No.A14006).
文摘The primary objective of Chinese spelling correction(CSC)is to detect and correct erroneous characters in Chinese text,which can result from various factors,such as inaccuracies in pinyin representation,character resemblance,and semantic discrepancies.However,existing methods often struggle to fully address these types of errors,impacting the overall correction accuracy.This paper introduces a multi-modal feature encoder designed to efficiently extract features from three distinct modalities:pinyin,semantics,and character morphology.Unlike previous methods that rely on direct fusion or fixed-weight summation to integrate multi-modal information,our approach employs a multi-head attention mechanism to focuse more on relevant modal information while dis-regarding less pertinent data.To prevent issues such as gradient explosion or vanishing,the model incorporates a residual connection of the original text vector for fine-tuning.This approach ensures robust model performance by maintaining essential linguistic details throughout the correction process.Experimental evaluations on the SIGHAN benchmark dataset demonstrate that the pro-posed model outperforms baseline approaches across various metrics and datasets,confirming its effectiveness and feasibility.
