Phenotypic prediction is a promising strategy for accelerating plant breeding.Data from multiple sources(called multi-view data)can provide complementary information to characterize a biological object from various as...Phenotypic prediction is a promising strategy for accelerating plant breeding.Data from multiple sources(called multi-view data)can provide complementary information to characterize a biological object from various aspects.By integrating multi-view information into phenotypic prediction,a multi-view best linear unbiased prediction(MVBLUP)method is proposed in this paper.To measure the importance of multiple data views,the differential evolution algorithm with an early stopping mechanism is used,by which we obtain a multi-view kinship matrix and then incorporate it into the BLUP model for phenotypic prediction.To further illustrate the characteristics of MVBLUP,we perform the empirical experiments on four multi-view datasets in different crops.Compared to the single-view method,the prediction accuracy of the MVBLUP method has improved by 0.038–0.201 on average.The results demonstrate that the MVBLUP is an effective integrative prediction method for multi-view data.展开更多
In dynamic scenarios,visual simultaneous localization and mapping(SLAM)algorithms often incorrectly incorporate dynamic points during camera pose computation,leading to reduced accuracy and robustness.This paper prese...In dynamic scenarios,visual simultaneous localization and mapping(SLAM)algorithms often incorrectly incorporate dynamic points during camera pose computation,leading to reduced accuracy and robustness.This paper presents a dynamic SLAM algorithm that leverages object detection and regional dynamic probability.Firstly,a parallel thread employs the YOLOX object detectionmodel to gather 2D semantic information and compensate for missed detections.Next,an improved K-means++clustering algorithm clusters bounding box regions,adaptively determining the threshold for extracting dynamic object contours as dynamic points change.This process divides the image into low dynamic,suspicious dynamic,and high dynamic regions.In the tracking thread,the dynamic point removal module assigns dynamic probability weights to the feature points in these regions.Combined with geometric methods,it detects and removes the dynamic points.The final evaluation on the public TUM RGB-D dataset shows that the proposed dynamic SLAM algorithm surpasses most existing SLAM algorithms,providing better pose estimation accuracy and robustness in dynamic environments.展开更多
The morphological description of wear particles in lubricating oil is crucial for wear state monitoring and fault diagnosis in aero-engines.Accurately and comprehensively acquiring three-dimensional(3D)morphological d...The morphological description of wear particles in lubricating oil is crucial for wear state monitoring and fault diagnosis in aero-engines.Accurately and comprehensively acquiring three-dimensional(3D)morphological data of these particles has became a key focus in wear debris analysis.Herein,we develop a novel multi-view polarization-sensitive optical coherence tomography(PS-OCT)method to achieve accurate 3D morphology detection and reconstruction of aero-engine lubricant wear particles,effectively resolving occlusion-induced information loss while enabling material-specific characterization.The particle morphology is captured by multi-view imaging,followed by filtering,sharpening,and contour recognition.The method integrates advanced registration algorithms with Poisson reconstruction to generate high-precision 3D models.This approach not only provides accurate 3D morphological reconstruction but also mitigates information loss caused by particle occlusion,ensuring model completeness.Furthermore,by collecting polarization characteristics of typical metals and their oxides in aero-engine lubricants,this work comprehensively characterizes and comparatively analyzes particle polarization properties using Stokes vectors,polarization uniformity,and cumulative phase retardation,and obtains a three-dimensional model containing polarization information.Ultimately,the proposed method enables multidimensional information acquisition for the reliable identification of abrasive particle types.展开更多
With the upgrading of tourism consumption patterns,the traditional renovation models of waterfront recreational spaces centered on landscape design can no longer meet the commercial and humanistic demands of modern cu...With the upgrading of tourism consumption patterns,the traditional renovation models of waterfront recreational spaces centered on landscape design can no longer meet the commercial and humanistic demands of modern cultural and tourism development.Based on scene theory as the analytical framework and taking the Xuan en Night Banquet Project in Enshi as a case study,this paper explores the design pathway for transforming waterfront areas in tourism cities from"spatial reconstruction"to"scene construction".The study argues that waterfront space renewal should transcend mere physical renovation.By implementing three core strategies:spatial narrative framework,ecological industry creation,and cultural empowerment,it is possible to construct integrated scenarios that blend cultural value,consumption spaces,and lifestyle elements.This approach ultimately fosters sustained vitality in waterfront areas and promotes the high-quality development of cultural and tourism industry.展开更多
Multi-view clustering is a critical research area in computer science aimed at effectively extracting meaningful patterns from complex,high-dimensional data that single-view methods cannot capture.Traditional fuzzy cl...Multi-view clustering is a critical research area in computer science aimed at effectively extracting meaningful patterns from complex,high-dimensional data that single-view methods cannot capture.Traditional fuzzy clustering techniques,such as Fuzzy C-Means(FCM),face significant challenges in handling uncertainty and the dependencies between different views.To overcome these limitations,we introduce a new multi-view fuzzy clustering approach that integrates picture fuzzy sets with a dual-anchor graph method for multi-view data,aiming to enhance clustering accuracy and robustness,termed Multi-view Picture Fuzzy Clustering(MPFC).In particular,the picture fuzzy set theory extends the capability to represent uncertainty by modeling three membership levels:membership degrees,neutral degrees,and refusal degrees.This allows for a more flexible representation of uncertain and conflicting data than traditional fuzzy models.Meanwhile,dual-anchor graphs exploit the similarity relationships between data points and integrate information across views.This combination improves stability,scalability,and robustness when handling noisy and heterogeneous data.Experimental results on several benchmark datasets demonstrate significant improvements in clustering accuracy and efficiency,outperforming traditional methods.Specifically,the MPFC algorithm demonstrates outstanding clustering performance on a variety of datasets,attaining a Purity(PUR)score of 0.6440 and an Accuracy(ACC)score of 0.6213 for the 3 Sources dataset,underscoring its robustness and efficiency.The proposed approach significantly contributes to fields such as pattern recognition,multi-view relational data analysis,and large-scale clustering problems.Future work will focus on extending the method for semi-supervised multi-view clustering,aiming to enhance adaptability,scalability,and performance in real-world applications.展开更多
Scene graph prediction has emerged as a critical task in computer vision,focusing on transforming complex visual scenes into structured representations by identifying objects,their attributes,and the relationships amo...Scene graph prediction has emerged as a critical task in computer vision,focusing on transforming complex visual scenes into structured representations by identifying objects,their attributes,and the relationships among them.Extending this to 3D semantic scene graph(3DSSG)prediction introduces an additional layer of complexity because it requires the processing of point-cloud data to accurately capture the spatial and volumetric characteristics of a scene.A significant challenge in 3DSSG is the long-tailed distribution of object and relationship labels,causing certain classes to be severely underrepresented and suboptimal performance in these rare categories.To address this,we proposed a fusion prototypical network(FPN),which combines the strengths of conventional neural networks for 3DSSG with a Prototypical Network.The former are known for their ability to handle complex scene graph predictions while the latter excels in few-shot learning scenarios.By leveraging this fusion,our approach enhances the overall prediction accuracy and substantially improves the handling of underrepresented labels.Through extensive experiments using the 3DSSG dataset,we demonstrated that the FPN achieves state-of-the-art performance in 3D scene graph prediction as a single model and effectively mitigates the impact of the long-tailed distribution,providing a more balanced and comprehensive understanding of complex 3D environments.展开更多
Crime scene investigation(CSI)is an important link in the criminal justice system as it serves as a bridge between establishing the happenings during an incident and possibly identifying the accountable persons,provid...Crime scene investigation(CSI)is an important link in the criminal justice system as it serves as a bridge between establishing the happenings during an incident and possibly identifying the accountable persons,providing light in the dark.The International Organization for Standardization(ISO)and the International Electrotechnical Commission(IEC)collaborated to develop the ISO/IEC 17020:2012 standard to govern the quality of CSI,a branch of inspection activity.These protocols include the impartiality and competence of the crime scene investigators involved,contemporary recording of scene observations and data obtained,the correct use of resources during scene processing,forensic evidence collection and handling procedures,and the confidentiality and integrity of any scene information obtained from other parties etc.The preparatory work,the accreditation processes involved and the implementation of new quality measures to the existing quality management system in order to achieve the ISO/IE 17020:2012 accreditation at the Forensic Science Division of the Government Laboratory in Hong Kong are discussed in this paper.展开更多
Existing multi-view deep subspace clustering methods aim to learn a unified representation from multi-view data,while the learned representation is difficult to maintain the underlying structure hidden in the origin s...Existing multi-view deep subspace clustering methods aim to learn a unified representation from multi-view data,while the learned representation is difficult to maintain the underlying structure hidden in the origin samples,especially the high-order neighbor relationship between samples.To overcome the above challenges,this paper proposes a novel multi-order neighborhood fusion based multi-view deep subspace clustering model.We creatively integrate the multi-order proximity graph structures of different views into the self-expressive layer by a multi-order neighborhood fusion module.By this design,the multi-order Laplacian matrix supervises the learning of the view-consistent self-representation affinity matrix;then,we can obtain an optimal global affinity matrix where each connected node belongs to one cluster.In addition,the discriminative constraint between views is designed to further improve the clustering performance.A range of experiments on six public datasets demonstrates that the method performs better than other advanced multi-view clustering methods.The code is available at https://github.com/songzuolong/MNF-MDSC(accessed on 25 December 2024).展开更多
Remote sensing scene image classification is a prominent research area within remote sensing.Deep learningbased methods have been extensively utilized and have shown significant advancements in this field.Recent progr...Remote sensing scene image classification is a prominent research area within remote sensing.Deep learningbased methods have been extensively utilized and have shown significant advancements in this field.Recent progress in these methods primarily focuses on enhancing feature representation capabilities to improve performance.The challenge lies in the limited spatial resolution of small-sized remote sensing images,as well as image blurring and sparse data.These factors contribute to lower accuracy in current deep learning models.Additionally,deeper networks with attention-based modules require a substantial number of network parameters,leading to high computational costs and memory usage.In this article,we introduce ERSNet,a lightweight novel attention-guided network for remote sensing scene image classification.ERSNet is constructed using a deep separable convolutional network and incorporates an attention mechanism.It utilizes spatial attention,channel attention,and channel self-attention to enhance feature representation and accuracy,while also reducing computational complexity and memory usage.Experimental results indicate that,compared to existing state-of-the-art methods,ERSNet has a significantly lower parameter count of only 1.2 M and reduced Flops.It achieves the highest classification accuracy of 99.14%on the EuroSAT dataset,demonstrating its suitability for application on mobile terminal devices.Furthermore,experimental results from the UCMerced land use dataset and the Brazilian coffee scene also confirm the strong generalization ability of this method.展开更多
The increasing prevalence of multi-view data has made multi-view clustering a crucial technique for discovering latent structures from heterogeneous representations.However,traditional fuzzy clustering algorithms show...The increasing prevalence of multi-view data has made multi-view clustering a crucial technique for discovering latent structures from heterogeneous representations.However,traditional fuzzy clustering algorithms show limitations with the inherent uncertainty and imprecision of such data,as they rely on a single-dimensional membership value.To overcome these limitations,we propose an auto-weighted multi-view neutrosophic fuzzy clustering(AW-MVNFC)algorithm.Our method leverages the neutrosophic framework,an extension of fuzzy sets,to explicitly model imprecision and ambiguity through three membership degrees.The core novelty of AWMVNFC lies in a hierarchical weighting strategy that adaptively learns the contributions of both individual data views and the importance of each feature within a view.Through a unified objective function,AW-MVNFC jointly optimizes the neutrosophic membership assignments,cluster centers,and the distributions of view and feature weights.Comprehensive experiments conducted on synthetic and real-world datasets demonstrate that our algorithm achieves more accurate and stable clustering than existing methods,demonstrating its effectiveness in handling the complexities of multi-view data.展开更多
In the dynamic scene of autonomous vehicles,the depth estimation of monocular cameras often faces the problem of inaccurate edge depth estimation.To solve this problem,we propose an unsupervised monocular depth estima...In the dynamic scene of autonomous vehicles,the depth estimation of monocular cameras often faces the problem of inaccurate edge depth estimation.To solve this problem,we propose an unsupervised monocular depth estimation model based on edge enhancement,which is specifically aimed at the depth perception challenge in dynamic scenes.The model consists of two core networks:a deep prediction network and a motion estimation network,both of which adopt an encoder-decoder architecture.The depth prediction network is based on the U-Net structure of ResNet18,which is responsible for generating the depth map of the scene.The motion estimation network is based on the U-Net structure of Flow-Net,focusing on the motion estimation of dynamic targets.In the decoding stage of the motion estimation network,we innovatively introduce an edge-enhanced decoder,which integrates a convolutional block attention module(CBAM)in the decoding process to enhance the recognition ability of the edge features of moving objects.In addition,we also designed a strip convolution module to improve the model’s capture efficiency of discrete moving targets.To further improve the performance of the model,we propose a novel edge regularization method based on the Laplace operator,which effectively accelerates the convergence process of themodel.Experimental results on the KITTI and Cityscapes datasets show that compared with the current advanced dynamic unsupervised monocular model,the proposed model has a significant improvement in depth estimation accuracy and convergence speed.Specifically,the rootmean square error(RMSE)is reduced by 4.8%compared with the DepthMotion algorithm,while the training convergence speed is increased by 36%,which shows the superior performance of the model in the depth estimation task in dynamic scenes.展开更多
This paper presents a comprehensive framework that enables communication scene recognition through deep learning and multi-sensor fusion.This study aims to address the challenge of current communication scene recognit...This paper presents a comprehensive framework that enables communication scene recognition through deep learning and multi-sensor fusion.This study aims to address the challenge of current communication scene recognition methods that struggle to adapt in dynamic environments,as they typically rely on post-response mechanisms that fail to detect scene changes before users experience latency.The proposed framework leverages data from multiple smartphone sensors,including acceleration sensors,gyroscopes,magnetic field sensors,and orientation sensors,to identify different communication scenes,such as walking,running,cycling,and various modes of transportation.Extensive experimental comparative analysis with existing methods on the open-source SHL-2018 dataset confirmed the superior performance of our approach in terms of F1 score and processing speed.Additionally,tests using a Microsoft Surface Pro tablet and a self-collected Beijing-2023 dataset have validated the framework's efficiency and generalization capability.The results show that our framework achieved an F1 score of 95.15%on SHL-2018and 94.6%on Beijing-2023,highlighting its robustness across different datasets and conditions.Furthermore,the levels of computational complexity and power consumption associated with the algorithm are moderate,making it suitable for deployment on mobile devices.展开更多
Semantic segmentation in street scenes is a crucial technology for autonomous driving to analyze the surrounding environment.In street scenes,issues such as high image resolution caused by a large viewpoints and diffe...Semantic segmentation in street scenes is a crucial technology for autonomous driving to analyze the surrounding environment.In street scenes,issues such as high image resolution caused by a large viewpoints and differences in object scales lead to a decline in real-time performance and difficulties in multi-scale feature extraction.To address this,we propose a bilateral-branch real-time semantic segmentationmethod based on semantic information distillation(BSDNet)for street scene images.The BSDNet consists of a Feature Conversion Convolutional Block(FCB),a Semantic Information Distillation Module(SIDM),and a Deep Aggregation Atrous Convolution Pyramid Pooling(DASP).FCB reduces the semantic gap between the backbone and the semantic branch.SIDM extracts high-quality semantic information fromthe Transformer branch to reduce computational costs.DASP aggregates information lost in atrous convolutions,effectively capturingmulti-scale objects.Extensive experiments conducted on Cityscapes,CamVid,and ADE20K,achieving an accuracy of 81.7% Mean Intersection over Union(mIoU)at 70.6 Frames Per Second(FPS)on Cityscapes,demonstrate that our method achieves a better balance between accuracy and inference speed.展开更多
Recognizing road scene context from a single image remains a critical challenge for intelligent autonomous driving systems,particularly in dynamic and unstructured environments.While recent advancements in deep learni...Recognizing road scene context from a single image remains a critical challenge for intelligent autonomous driving systems,particularly in dynamic and unstructured environments.While recent advancements in deep learning have significantly enhanced road scene classification,simultaneously achieving high accuracy,computational efficiency,and adaptability across diverse conditions continues to be difficult.To address these challenges,this study proposes HybridLSTM,a novel and efficient framework that integrates deep learning-based,object-based,and handcrafted feature extraction methods within a unified architecture.HybridLSTM is designed to classify four distinct road scene categories—crosswalk(CW),highway(HW),overpass/tunnel(OP/T),and parking(P)—by leveraging multiple publicly available datasets,including Places-365,BDD100K,LabelMe,and KITTI,thereby promoting domain generalization.The framework fuses object-level features extracted using YOLOv5 and VGG19,scene-level global representations obtained from a modified VGG19,and fine-grained texture features captured through eight handcrafted descriptors.This hybrid feature fusion enables the model to capture both semantic context and low-level visual cues,which are critical for robust scene understanding.To model spatial arrangements and latent sequential dependencies present even in static imagery,the combined features are processed through a Long Short-Term Memory(LSTM)network,allowing the extraction of discriminative patterns across heterogeneous feature spaces.Extensive experiments conducted on 2725 annotated road scene images,with an 80:20 training-to-testing split,validate the effectiveness of the proposed model.HybridLSTM achieves a classification accuracy of 96.3%,a precision of 95.8%,a recall of 96.1%,and an F1-score of 96.0%,outperforming several existing state-of-the-art methods.These results demonstrate the robustness,scalability,and generalization capability of HybridLSTM across varying environments and scene complexities.Moreover,the framework is optimized to balance classification performance with computational efficiency,making it highly suitable for real-time deployment in embedded autonomous driving systems.Future work will focus on extending the model to multi-class detection within a single frame and optimizing it further for edge-device deployments to reduce computational overhead in practical applications.展开更多
The autonomous landing guidance of fixed-wing aircraft in unknown structured scenes presents a substantial technological challenge,particularly regarding the effectiveness of solutions for monocular visual relative po...The autonomous landing guidance of fixed-wing aircraft in unknown structured scenes presents a substantial technological challenge,particularly regarding the effectiveness of solutions for monocular visual relative pose estimation.This study proposes a novel airborne monocular visual estimation method based on structured scene features to address this challenge.First,a multitask neural network model is established for segmentation,depth estimation,and slope estimation on monocular images.And a monocular image comprehensive three-dimensional information metric is designed,encompassing length,span,flatness,and slope information.Subsequently,structured edge features are leveraged to filter candidate landing regions adaptively.By leveraging the three-dimensional information metric,the optimal landing region is accurately and efficiently identified.Finally,sparse two-dimensional key point is used to parameterize the optimal landing region for the first time and a high-precision relative pose estimation is achieved.Additional measurement information is introduced to provide the autonomous landing guidance information between the aircraft and the optimal landing region.Experimental results obtained from both synthetic and real data demonstrate the effectiveness of the proposed method in monocular pose estimation for autonomous aircraft landing guidance in unknown structured scenes.展开更多
Drug repurposing offers a promising alternative to traditional drug development and significantly re-duces costs and timelines by identifying new therapeutic uses for existing drugs.However,the current approaches ofte...Drug repurposing offers a promising alternative to traditional drug development and significantly re-duces costs and timelines by identifying new therapeutic uses for existing drugs.However,the current approaches often rely on limited data sources and simplistic hypotheses,which restrict their ability to capture the multi-faceted nature of biological systems.This study introduces adaptive multi-view learning(AMVL),a novel methodology that integrates chemical-induced transcriptional profiles(CTPs),knowledge graph(KG)embeddings,and large language model(LLM)representations,to enhance drug repurposing predictions.AMVL incorporates an innovative similarity matrix expansion strategy and leverages multi-view learning(MVL),matrix factorization,and ensemble optimization techniques to integrate heterogeneous multi-source data.Comprehensive evaluations on benchmark datasets(Fdata-set,Cdataset,and Ydataset)and the large-scale iDrug dataset demonstrate that AMVL outperforms state-of-the-art(SOTA)methods,achieving superior accuracy in predicting drug-disease associations across multiple metrics.Literature-based validation further confirmed the model's predictive capabilities,with seven out of the top ten predictions corroborated by post-2011 evidence.To promote transparency and reproducibility,all data and codes used in this study were open-sourced,providing resources for pro-cessing CTPs,KG,and LLM-based similarity calculations,along with the complete AMVL algorithm and benchmarking procedures.By unifying diverse data modalities,AMVL offers a robust and scalable so-lution for accelerating drug discovery,fostering advancements in translational medicine and integrating multi-omics data.We aim to inspire further innovations in multi-source data integration and support the development of more precise and efficient strategies for advancing drug discovery and translational medicine.展开更多
Drone swarm systems,equipped with photoelectric imaging and intelligent target perception,are essential for reconnaissance and strike missions in complex and high-risk environments.They excel in information sharing,an...Drone swarm systems,equipped with photoelectric imaging and intelligent target perception,are essential for reconnaissance and strike missions in complex and high-risk environments.They excel in information sharing,anti-jamming capabilities,and combat performance,making them critical for future warfare.However,varied perspectives in collaborative combat scenarios pose challenges to object detection,hindering traditional detection algorithms and reducing accuracy.Limited angle-prior data and sparse samples further complicate detection.This paper presents the Multi-View Collaborative Detection System,which tackles the challenges of multi-view object detection in collaborative combat scenarios.The system is designed to enhance multi-view image generation and detection algorithms,thereby improving the accuracy and efficiency of object detection across varying perspectives.First,an observation model for three-dimensional targets through line-of-sight angle transformation is constructed,and a multi-view image generation algorithm based on the Pix2Pix network is designed.For object detection,YOLOX is utilized,and a deep feature extraction network,BA-RepCSPDarknet,is developed to address challenges related to small target scale and feature extraction challenges.Additionally,a feature fusion network NS-PAFPN is developed to mitigate the issue of deep feature map information loss in UAV images.A visual attention module(BAM)is employed to manage appearance differences under varying angles,while a feature mapping module(DFM)prevents fine-grained feature loss.These advancements lead to the development of BA-YOLOX,a multi-view object detection network model suitable for drone platforms,enhancing accuracy and effectively targeting small objects.展开更多
High-resolution sub-meter satellite data play an increasingly crucial role in the 3D real-scene China construction initiative.Current research on 3D reconstruction using high-resolution satellite data primarily focuse...High-resolution sub-meter satellite data play an increasingly crucial role in the 3D real-scene China construction initiative.Current research on 3D reconstruction using high-resolution satellite data primarily focuses on two approaches:Multi-stereo fusion and multi-view matching.While algorithms based on these two methodologies for multi-view image 3D reconstruction have reached relative maturity,no systematic comparison has been conducted specifically on satellite data to evaluate the relative merits of multi-stereo fusion versus multi-view matching methods.This paper conducts a comparative analysis of the practical accuracy of both approaches using high-resolution satellite datasets from diverse geographical regions.To ensure fairness in accuracy comparison,both methodologies employ non-local dense matching for cost optimization.Results demonstrate that the multi-stereo fusion method outperforms multi-view matching in all evaluation metrics,exhibiting approximately 1.2%higher average matching accuracy and 10.7%superior elevation precision in the experimental datasets.Therefore,for 3D modeling applications using satellite data,we recommend adopting the multi-stereo fusion approach for digital surface model(DSM)product generation.展开更多
Self-supervised monocular depth estimation has emerged as a major research focus in recent years,primarily due to the elimination of ground-truth depth dependence.However,the prevailing architectures in this domain su...Self-supervised monocular depth estimation has emerged as a major research focus in recent years,primarily due to the elimination of ground-truth depth dependence.However,the prevailing architectures in this domain suffer from inherent limitations:existing pose network branches infer camera ego-motion exclusively under static-scene and Lambertian-surface assumptions.These assumptions are often violated in real-world scenarios due to dynamic objects,non-Lambertian reflectance,and unstructured background elements,leading to pervasive artifacts such as depth discontinuities(“holes”),structural collapse,and ambiguous reconstruction.To address these challenges,we propose a novel framework that integrates scene dynamic pose estimation into the conventional self-supervised depth network,enhancing its ability to model complex scene dynamics.Our contributions are threefold:(1)a pixel-wise dynamic pose estimation module that jointly resolves the pose transformations of moving objects and localized scene perturbations;(2)a physically-informed loss function that couples dynamic pose and depth predictions,designed to mitigate depth errors arising from high-speed distant objects and geometrically inconsistent motion profiles;(3)an efficient SE(3)transformation parameterization that streamlines network complexity and temporal pre-processing.Extensive experiments on the KITTI and NYU-V2 benchmarks show that our framework achieves state-of-the-art performance in both quantitative metrics and qualitative visual fidelity,significantly improving the robustness and generalization of monocular depth estimation under dynamic conditions.展开更多
Video action recognition(VAR)aims to analyze dynamic behaviors in videos and achieve semantic understanding.VAR faces challenges such as temporal dynamics,action-scene coupling,and the complexity of human interactions...Video action recognition(VAR)aims to analyze dynamic behaviors in videos and achieve semantic understanding.VAR faces challenges such as temporal dynamics,action-scene coupling,and the complexity of human interactions.Existing methods can be categorized into motion-level,event-level,and story-level ones based on spatiotemporal granularity.However,single-modal approaches struggle to capture complex behavioral semantics and human factors.Therefore,in recent years,vision-language models(VLMs)have been introduced into this field,providing new research perspectives for VAR.In this paper,we systematically review spatiotemporal hierarchical methods in VAR and explore how the introduction of large models has advanced the field.Additionally,we propose the concept of“Factor”to identify and integrate key information from both visual and textual modalities,enhancing multimodal alignment.We also summarize various multimodal alignment methods and provide in-depth analysis and insights into future research directions.展开更多
基金supported by National Natural Science Foundation of China(32122066,32201855)STI2030—Major Projects(2023ZD04076).
文摘Phenotypic prediction is a promising strategy for accelerating plant breeding.Data from multiple sources(called multi-view data)can provide complementary information to characterize a biological object from various aspects.By integrating multi-view information into phenotypic prediction,a multi-view best linear unbiased prediction(MVBLUP)method is proposed in this paper.To measure the importance of multiple data views,the differential evolution algorithm with an early stopping mechanism is used,by which we obtain a multi-view kinship matrix and then incorporate it into the BLUP model for phenotypic prediction.To further illustrate the characteristics of MVBLUP,we perform the empirical experiments on four multi-view datasets in different crops.Compared to the single-view method,the prediction accuracy of the MVBLUP method has improved by 0.038–0.201 on average.The results demonstrate that the MVBLUP is an effective integrative prediction method for multi-view data.
基金the National Natural Science Foundation of China(No.62063006)to the Guangxi Natural Science Foundation under Grant(Nos.2023GXNSFAA026025,AA24010001)+3 种基金to the Innovation Fund of Chinese Universities Industry-University-Research(ID:2023RY018)to the Special Guangxi Industry and Information Technology Department,Textile and Pharmaceutical Division(ID:2021 No.231)to the Special Research Project of Hechi University(ID:2021GCC028)to the Key Laboratory of AI and Information Processing,Education Department of Guangxi Zhuang Autonomous Region(Hechi University),No.2024GXZDSY009。
文摘In dynamic scenarios,visual simultaneous localization and mapping(SLAM)algorithms often incorrectly incorporate dynamic points during camera pose computation,leading to reduced accuracy and robustness.This paper presents a dynamic SLAM algorithm that leverages object detection and regional dynamic probability.Firstly,a parallel thread employs the YOLOX object detectionmodel to gather 2D semantic information and compensate for missed detections.Next,an improved K-means++clustering algorithm clusters bounding box regions,adaptively determining the threshold for extracting dynamic object contours as dynamic points change.This process divides the image into low dynamic,suspicious dynamic,and high dynamic regions.In the tracking thread,the dynamic point removal module assigns dynamic probability weights to the feature points in these regions.Combined with geometric methods,it detects and removes the dynamic points.The final evaluation on the public TUM RGB-D dataset shows that the proposed dynamic SLAM algorithm surpasses most existing SLAM algorithms,providing better pose estimation accuracy and robustness in dynamic environments.
文摘The morphological description of wear particles in lubricating oil is crucial for wear state monitoring and fault diagnosis in aero-engines.Accurately and comprehensively acquiring three-dimensional(3D)morphological data of these particles has became a key focus in wear debris analysis.Herein,we develop a novel multi-view polarization-sensitive optical coherence tomography(PS-OCT)method to achieve accurate 3D morphology detection and reconstruction of aero-engine lubricant wear particles,effectively resolving occlusion-induced information loss while enabling material-specific characterization.The particle morphology is captured by multi-view imaging,followed by filtering,sharpening,and contour recognition.The method integrates advanced registration algorithms with Poisson reconstruction to generate high-precision 3D models.This approach not only provides accurate 3D morphological reconstruction but also mitigates information loss caused by particle occlusion,ensuring model completeness.Furthermore,by collecting polarization characteristics of typical metals and their oxides in aero-engine lubricants,this work comprehensively characterizes and comparatively analyzes particle polarization properties using Stokes vectors,polarization uniformity,and cumulative phase retardation,and obtains a three-dimensional model containing polarization information.Ultimately,the proposed method enables multidimensional information acquisition for the reliable identification of abrasive particle types.
文摘With the upgrading of tourism consumption patterns,the traditional renovation models of waterfront recreational spaces centered on landscape design can no longer meet the commercial and humanistic demands of modern cultural and tourism development.Based on scene theory as the analytical framework and taking the Xuan en Night Banquet Project in Enshi as a case study,this paper explores the design pathway for transforming waterfront areas in tourism cities from"spatial reconstruction"to"scene construction".The study argues that waterfront space renewal should transcend mere physical renovation.By implementing three core strategies:spatial narrative framework,ecological industry creation,and cultural empowerment,it is possible to construct integrated scenarios that blend cultural value,consumption spaces,and lifestyle elements.This approach ultimately fosters sustained vitality in waterfront areas and promotes the high-quality development of cultural and tourism industry.
基金funded by the Research Project:THTETN.05/24-25,VietnamAcademy of Science and Technology.
文摘Multi-view clustering is a critical research area in computer science aimed at effectively extracting meaningful patterns from complex,high-dimensional data that single-view methods cannot capture.Traditional fuzzy clustering techniques,such as Fuzzy C-Means(FCM),face significant challenges in handling uncertainty and the dependencies between different views.To overcome these limitations,we introduce a new multi-view fuzzy clustering approach that integrates picture fuzzy sets with a dual-anchor graph method for multi-view data,aiming to enhance clustering accuracy and robustness,termed Multi-view Picture Fuzzy Clustering(MPFC).In particular,the picture fuzzy set theory extends the capability to represent uncertainty by modeling three membership levels:membership degrees,neutral degrees,and refusal degrees.This allows for a more flexible representation of uncertain and conflicting data than traditional fuzzy models.Meanwhile,dual-anchor graphs exploit the similarity relationships between data points and integrate information across views.This combination improves stability,scalability,and robustness when handling noisy and heterogeneous data.Experimental results on several benchmark datasets demonstrate significant improvements in clustering accuracy and efficiency,outperforming traditional methods.Specifically,the MPFC algorithm demonstrates outstanding clustering performance on a variety of datasets,attaining a Purity(PUR)score of 0.6440 and an Accuracy(ACC)score of 0.6213 for the 3 Sources dataset,underscoring its robustness and efficiency.The proposed approach significantly contributes to fields such as pattern recognition,multi-view relational data analysis,and large-scale clustering problems.Future work will focus on extending the method for semi-supervised multi-view clustering,aiming to enhance adaptability,scalability,and performance in real-world applications.
基金supported by the Glocal University 30 Project Fund of Gyeongsang National University in 2025.
文摘Scene graph prediction has emerged as a critical task in computer vision,focusing on transforming complex visual scenes into structured representations by identifying objects,their attributes,and the relationships among them.Extending this to 3D semantic scene graph(3DSSG)prediction introduces an additional layer of complexity because it requires the processing of point-cloud data to accurately capture the spatial and volumetric characteristics of a scene.A significant challenge in 3DSSG is the long-tailed distribution of object and relationship labels,causing certain classes to be severely underrepresented and suboptimal performance in these rare categories.To address this,we proposed a fusion prototypical network(FPN),which combines the strengths of conventional neural networks for 3DSSG with a Prototypical Network.The former are known for their ability to handle complex scene graph predictions while the latter excels in few-shot learning scenarios.By leveraging this fusion,our approach enhances the overall prediction accuracy and substantially improves the handling of underrepresented labels.Through extensive experiments using the 3DSSG dataset,we demonstrated that the FPN achieves state-of-the-art performance in 3D scene graph prediction as a single model and effectively mitigates the impact of the long-tailed distribution,providing a more balanced and comprehensive understanding of complex 3D environments.
文摘Crime scene investigation(CSI)is an important link in the criminal justice system as it serves as a bridge between establishing the happenings during an incident and possibly identifying the accountable persons,providing light in the dark.The International Organization for Standardization(ISO)and the International Electrotechnical Commission(IEC)collaborated to develop the ISO/IEC 17020:2012 standard to govern the quality of CSI,a branch of inspection activity.These protocols include the impartiality and competence of the crime scene investigators involved,contemporary recording of scene observations and data obtained,the correct use of resources during scene processing,forensic evidence collection and handling procedures,and the confidentiality and integrity of any scene information obtained from other parties etc.The preparatory work,the accreditation processes involved and the implementation of new quality measures to the existing quality management system in order to achieve the ISO/IE 17020:2012 accreditation at the Forensic Science Division of the Government Laboratory in Hong Kong are discussed in this paper.
基金supported by the National Key R&D Program of China(2023YFC3304600).
文摘Existing multi-view deep subspace clustering methods aim to learn a unified representation from multi-view data,while the learned representation is difficult to maintain the underlying structure hidden in the origin samples,especially the high-order neighbor relationship between samples.To overcome the above challenges,this paper proposes a novel multi-order neighborhood fusion based multi-view deep subspace clustering model.We creatively integrate the multi-order proximity graph structures of different views into the self-expressive layer by a multi-order neighborhood fusion module.By this design,the multi-order Laplacian matrix supervises the learning of the view-consistent self-representation affinity matrix;then,we can obtain an optimal global affinity matrix where each connected node belongs to one cluster.In addition,the discriminative constraint between views is designed to further improve the clustering performance.A range of experiments on six public datasets demonstrates that the method performs better than other advanced multi-view clustering methods.The code is available at https://github.com/songzuolong/MNF-MDSC(accessed on 25 December 2024).
文摘Remote sensing scene image classification is a prominent research area within remote sensing.Deep learningbased methods have been extensively utilized and have shown significant advancements in this field.Recent progress in these methods primarily focuses on enhancing feature representation capabilities to improve performance.The challenge lies in the limited spatial resolution of small-sized remote sensing images,as well as image blurring and sparse data.These factors contribute to lower accuracy in current deep learning models.Additionally,deeper networks with attention-based modules require a substantial number of network parameters,leading to high computational costs and memory usage.In this article,we introduce ERSNet,a lightweight novel attention-guided network for remote sensing scene image classification.ERSNet is constructed using a deep separable convolutional network and incorporates an attention mechanism.It utilizes spatial attention,channel attention,and channel self-attention to enhance feature representation and accuracy,while also reducing computational complexity and memory usage.Experimental results indicate that,compared to existing state-of-the-art methods,ERSNet has a significantly lower parameter count of only 1.2 M and reduced Flops.It achieves the highest classification accuracy of 99.14%on the EuroSAT dataset,demonstrating its suitability for application on mobile terminal devices.Furthermore,experimental results from the UCMerced land use dataset and the Brazilian coffee scene also confirm the strong generalization ability of this method.
文摘The increasing prevalence of multi-view data has made multi-view clustering a crucial technique for discovering latent structures from heterogeneous representations.However,traditional fuzzy clustering algorithms show limitations with the inherent uncertainty and imprecision of such data,as they rely on a single-dimensional membership value.To overcome these limitations,we propose an auto-weighted multi-view neutrosophic fuzzy clustering(AW-MVNFC)algorithm.Our method leverages the neutrosophic framework,an extension of fuzzy sets,to explicitly model imprecision and ambiguity through three membership degrees.The core novelty of AWMVNFC lies in a hierarchical weighting strategy that adaptively learns the contributions of both individual data views and the importance of each feature within a view.Through a unified objective function,AW-MVNFC jointly optimizes the neutrosophic membership assignments,cluster centers,and the distributions of view and feature weights.Comprehensive experiments conducted on synthetic and real-world datasets demonstrate that our algorithm achieves more accurate and stable clustering than existing methods,demonstrating its effectiveness in handling the complexities of multi-view data.
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In the dynamic scene of autonomous vehicles,the depth estimation of monocular cameras often faces the problem of inaccurate edge depth estimation.To solve this problem,we propose an unsupervised monocular depth estimation model based on edge enhancement,which is specifically aimed at the depth perception challenge in dynamic scenes.The model consists of two core networks:a deep prediction network and a motion estimation network,both of which adopt an encoder-decoder architecture.The depth prediction network is based on the U-Net structure of ResNet18,which is responsible for generating the depth map of the scene.The motion estimation network is based on the U-Net structure of Flow-Net,focusing on the motion estimation of dynamic targets.In the decoding stage of the motion estimation network,we innovatively introduce an edge-enhanced decoder,which integrates a convolutional block attention module(CBAM)in the decoding process to enhance the recognition ability of the edge features of moving objects.In addition,we also designed a strip convolution module to improve the model’s capture efficiency of discrete moving targets.To further improve the performance of the model,we propose a novel edge regularization method based on the Laplace operator,which effectively accelerates the convergence process of themodel.Experimental results on the KITTI and Cityscapes datasets show that compared with the current advanced dynamic unsupervised monocular model,the proposed model has a significant improvement in depth estimation accuracy and convergence speed.Specifically,the rootmean square error(RMSE)is reduced by 4.8%compared with the DepthMotion algorithm,while the training convergence speed is increased by 36%,which shows the superior performance of the model in the depth estimation task in dynamic scenes.
基金supported by National 2011 Collaborative Innovation Center of Wireless Communication Technologies under Grant 2242022k60006。
文摘This paper presents a comprehensive framework that enables communication scene recognition through deep learning and multi-sensor fusion.This study aims to address the challenge of current communication scene recognition methods that struggle to adapt in dynamic environments,as they typically rely on post-response mechanisms that fail to detect scene changes before users experience latency.The proposed framework leverages data from multiple smartphone sensors,including acceleration sensors,gyroscopes,magnetic field sensors,and orientation sensors,to identify different communication scenes,such as walking,running,cycling,and various modes of transportation.Extensive experimental comparative analysis with existing methods on the open-source SHL-2018 dataset confirmed the superior performance of our approach in terms of F1 score and processing speed.Additionally,tests using a Microsoft Surface Pro tablet and a self-collected Beijing-2023 dataset have validated the framework's efficiency and generalization capability.The results show that our framework achieved an F1 score of 95.15%on SHL-2018and 94.6%on Beijing-2023,highlighting its robustness across different datasets and conditions.Furthermore,the levels of computational complexity and power consumption associated with the algorithm are moderate,making it suitable for deployment on mobile devices.
基金supported in part by the National Natural Science Foundation of China[Grant number 62471075]the Major Science and Technology Project Grant of the Chongqing Municipal Education Commission[Grant number KJZD-M202301901]Graduate Innovation Fund of Chongqing[gzlcx20253235].
文摘Semantic segmentation in street scenes is a crucial technology for autonomous driving to analyze the surrounding environment.In street scenes,issues such as high image resolution caused by a large viewpoints and differences in object scales lead to a decline in real-time performance and difficulties in multi-scale feature extraction.To address this,we propose a bilateral-branch real-time semantic segmentationmethod based on semantic information distillation(BSDNet)for street scene images.The BSDNet consists of a Feature Conversion Convolutional Block(FCB),a Semantic Information Distillation Module(SIDM),and a Deep Aggregation Atrous Convolution Pyramid Pooling(DASP).FCB reduces the semantic gap between the backbone and the semantic branch.SIDM extracts high-quality semantic information fromthe Transformer branch to reduce computational costs.DASP aggregates information lost in atrous convolutions,effectively capturingmulti-scale objects.Extensive experiments conducted on Cityscapes,CamVid,and ADE20K,achieving an accuracy of 81.7% Mean Intersection over Union(mIoU)at 70.6 Frames Per Second(FPS)on Cityscapes,demonstrate that our method achieves a better balance between accuracy and inference speed.
文摘Recognizing road scene context from a single image remains a critical challenge for intelligent autonomous driving systems,particularly in dynamic and unstructured environments.While recent advancements in deep learning have significantly enhanced road scene classification,simultaneously achieving high accuracy,computational efficiency,and adaptability across diverse conditions continues to be difficult.To address these challenges,this study proposes HybridLSTM,a novel and efficient framework that integrates deep learning-based,object-based,and handcrafted feature extraction methods within a unified architecture.HybridLSTM is designed to classify four distinct road scene categories—crosswalk(CW),highway(HW),overpass/tunnel(OP/T),and parking(P)—by leveraging multiple publicly available datasets,including Places-365,BDD100K,LabelMe,and KITTI,thereby promoting domain generalization.The framework fuses object-level features extracted using YOLOv5 and VGG19,scene-level global representations obtained from a modified VGG19,and fine-grained texture features captured through eight handcrafted descriptors.This hybrid feature fusion enables the model to capture both semantic context and low-level visual cues,which are critical for robust scene understanding.To model spatial arrangements and latent sequential dependencies present even in static imagery,the combined features are processed through a Long Short-Term Memory(LSTM)network,allowing the extraction of discriminative patterns across heterogeneous feature spaces.Extensive experiments conducted on 2725 annotated road scene images,with an 80:20 training-to-testing split,validate the effectiveness of the proposed model.HybridLSTM achieves a classification accuracy of 96.3%,a precision of 95.8%,a recall of 96.1%,and an F1-score of 96.0%,outperforming several existing state-of-the-art methods.These results demonstrate the robustness,scalability,and generalization capability of HybridLSTM across varying environments and scene complexities.Moreover,the framework is optimized to balance classification performance with computational efficiency,making it highly suitable for real-time deployment in embedded autonomous driving systems.Future work will focus on extending the model to multi-class detection within a single frame and optimizing it further for edge-device deployments to reduce computational overhead in practical applications.
基金co-supported by the Science and Technology Innovation Program of Hunan Province,China(No.2023RC3023)the National Natural Science Foundation of China(No.12272404)。
文摘The autonomous landing guidance of fixed-wing aircraft in unknown structured scenes presents a substantial technological challenge,particularly regarding the effectiveness of solutions for monocular visual relative pose estimation.This study proposes a novel airborne monocular visual estimation method based on structured scene features to address this challenge.First,a multitask neural network model is established for segmentation,depth estimation,and slope estimation on monocular images.And a monocular image comprehensive three-dimensional information metric is designed,encompassing length,span,flatness,and slope information.Subsequently,structured edge features are leveraged to filter candidate landing regions adaptively.By leveraging the three-dimensional information metric,the optimal landing region is accurately and efficiently identified.Finally,sparse two-dimensional key point is used to parameterize the optimal landing region for the first time and a high-precision relative pose estimation is achieved.Additional measurement information is introduced to provide the autonomous landing guidance information between the aircraft and the optimal landing region.Experimental results obtained from both synthetic and real data demonstrate the effectiveness of the proposed method in monocular pose estimation for autonomous aircraft landing guidance in unknown structured scenes.
基金supported by the National Natural Science Foundation of China(Grant No.:62101087)the China Postdoctoral Science Foundation(Grant No.:2021MD703942)+2 种基金the Chongqing Postdoctoral Research Project Special Funding,China(Grant No.:2021XM2016)the Science Foundation of Chongqing Municipal Commission of Education,China(Grant No.:KJQN202100642)the Chongqing Natural Science Foundation,China(Grant No.:cstc2021jcyj-msxmX0834).
文摘Drug repurposing offers a promising alternative to traditional drug development and significantly re-duces costs and timelines by identifying new therapeutic uses for existing drugs.However,the current approaches often rely on limited data sources and simplistic hypotheses,which restrict their ability to capture the multi-faceted nature of biological systems.This study introduces adaptive multi-view learning(AMVL),a novel methodology that integrates chemical-induced transcriptional profiles(CTPs),knowledge graph(KG)embeddings,and large language model(LLM)representations,to enhance drug repurposing predictions.AMVL incorporates an innovative similarity matrix expansion strategy and leverages multi-view learning(MVL),matrix factorization,and ensemble optimization techniques to integrate heterogeneous multi-source data.Comprehensive evaluations on benchmark datasets(Fdata-set,Cdataset,and Ydataset)and the large-scale iDrug dataset demonstrate that AMVL outperforms state-of-the-art(SOTA)methods,achieving superior accuracy in predicting drug-disease associations across multiple metrics.Literature-based validation further confirmed the model's predictive capabilities,with seven out of the top ten predictions corroborated by post-2011 evidence.To promote transparency and reproducibility,all data and codes used in this study were open-sourced,providing resources for pro-cessing CTPs,KG,and LLM-based similarity calculations,along with the complete AMVL algorithm and benchmarking procedures.By unifying diverse data modalities,AMVL offers a robust and scalable so-lution for accelerating drug discovery,fostering advancements in translational medicine and integrating multi-omics data.We aim to inspire further innovations in multi-source data integration and support the development of more precise and efficient strategies for advancing drug discovery and translational medicine.
基金supported by the Natural Science Foundation of China,Grant No.62103052.
文摘Drone swarm systems,equipped with photoelectric imaging and intelligent target perception,are essential for reconnaissance and strike missions in complex and high-risk environments.They excel in information sharing,anti-jamming capabilities,and combat performance,making them critical for future warfare.However,varied perspectives in collaborative combat scenarios pose challenges to object detection,hindering traditional detection algorithms and reducing accuracy.Limited angle-prior data and sparse samples further complicate detection.This paper presents the Multi-View Collaborative Detection System,which tackles the challenges of multi-view object detection in collaborative combat scenarios.The system is designed to enhance multi-view image generation and detection algorithms,thereby improving the accuracy and efficiency of object detection across varying perspectives.First,an observation model for three-dimensional targets through line-of-sight angle transformation is constructed,and a multi-view image generation algorithm based on the Pix2Pix network is designed.For object detection,YOLOX is utilized,and a deep feature extraction network,BA-RepCSPDarknet,is developed to address challenges related to small target scale and feature extraction challenges.Additionally,a feature fusion network NS-PAFPN is developed to mitigate the issue of deep feature map information loss in UAV images.A visual attention module(BAM)is employed to manage appearance differences under varying angles,while a feature mapping module(DFM)prevents fine-grained feature loss.These advancements lead to the development of BA-YOLOX,a multi-view object detection network model suitable for drone platforms,enhancing accuracy and effectively targeting small objects.
文摘High-resolution sub-meter satellite data play an increasingly crucial role in the 3D real-scene China construction initiative.Current research on 3D reconstruction using high-resolution satellite data primarily focuses on two approaches:Multi-stereo fusion and multi-view matching.While algorithms based on these two methodologies for multi-view image 3D reconstruction have reached relative maturity,no systematic comparison has been conducted specifically on satellite data to evaluate the relative merits of multi-stereo fusion versus multi-view matching methods.This paper conducts a comparative analysis of the practical accuracy of both approaches using high-resolution satellite datasets from diverse geographical regions.To ensure fairness in accuracy comparison,both methodologies employ non-local dense matching for cost optimization.Results demonstrate that the multi-stereo fusion method outperforms multi-view matching in all evaluation metrics,exhibiting approximately 1.2%higher average matching accuracy and 10.7%superior elevation precision in the experimental datasets.Therefore,for 3D modeling applications using satellite data,we recommend adopting the multi-stereo fusion approach for digital surface model(DSM)product generation.
基金supported in part by the National Natural Science Foundation of China under Grants 62071345。
文摘Self-supervised monocular depth estimation has emerged as a major research focus in recent years,primarily due to the elimination of ground-truth depth dependence.However,the prevailing architectures in this domain suffer from inherent limitations:existing pose network branches infer camera ego-motion exclusively under static-scene and Lambertian-surface assumptions.These assumptions are often violated in real-world scenarios due to dynamic objects,non-Lambertian reflectance,and unstructured background elements,leading to pervasive artifacts such as depth discontinuities(“holes”),structural collapse,and ambiguous reconstruction.To address these challenges,we propose a novel framework that integrates scene dynamic pose estimation into the conventional self-supervised depth network,enhancing its ability to model complex scene dynamics.Our contributions are threefold:(1)a pixel-wise dynamic pose estimation module that jointly resolves the pose transformations of moving objects and localized scene perturbations;(2)a physically-informed loss function that couples dynamic pose and depth predictions,designed to mitigate depth errors arising from high-speed distant objects and geometrically inconsistent motion profiles;(3)an efficient SE(3)transformation parameterization that streamlines network complexity and temporal pre-processing.Extensive experiments on the KITTI and NYU-V2 benchmarks show that our framework achieves state-of-the-art performance in both quantitative metrics and qualitative visual fidelity,significantly improving the robustness and generalization of monocular depth estimation under dynamic conditions.
基金supported by the Zhejiang Provincial Natural Science Foundation of China(No.LQ23F030001)the National Natural Science Foundation of China(No.62406280)+5 种基金the Autism Research Special Fund of Zhejiang Foundation for Disabled Persons(No.2023008)the Liaoning Province Higher Education Innovative Talents Program Support Project(No.LR2019058)the Liaoning Province Joint Open Fund for Key Scientific and Technological Innovation Bases(No.2021-KF-12-05)the Central Guidance on Local Science and Technology Development Fund of Liaoning Province(No.2023JH6/100100066)the Key Laboratory for Biomedical Engineering of Ministry of Education,Zhejiang University,Chinain part by the Open Research Fund of the State Key Laboratory of Cognitive Neuroscience and Learning.
文摘Video action recognition(VAR)aims to analyze dynamic behaviors in videos and achieve semantic understanding.VAR faces challenges such as temporal dynamics,action-scene coupling,and the complexity of human interactions.Existing methods can be categorized into motion-level,event-level,and story-level ones based on spatiotemporal granularity.However,single-modal approaches struggle to capture complex behavioral semantics and human factors.Therefore,in recent years,vision-language models(VLMs)have been introduced into this field,providing new research perspectives for VAR.In this paper,we systematically review spatiotemporal hierarchical methods in VAR and explore how the introduction of large models has advanced the field.Additionally,we propose the concept of“Factor”to identify and integrate key information from both visual and textual modalities,enhancing multimodal alignment.We also summarize various multimodal alignment methods and provide in-depth analysis and insights into future research directions.
