To address the issues of frequent identity switches(IDs)and degraded identification accuracy in multi object tracking(MOT)under complex occlusion scenarios,this study proposes an occlusion-robust tracking framework ba...To address the issues of frequent identity switches(IDs)and degraded identification accuracy in multi object tracking(MOT)under complex occlusion scenarios,this study proposes an occlusion-robust tracking framework based on face-pedestrian joint feature modeling.By constructing a joint tracking model centered on“intra-class independent tracking+cross-category dynamic binding”,designing a multi-modal matching metric with spatio-temporal and appearance constraints,and innovatively introducing a cross-category feature mutual verification mechanism and a dual matching strategy,this work effectively resolves performance degradation in traditional single-category tracking methods caused by short-term occlusion,cross-camera tracking,and crowded environments.Experiments on the Chokepoint_Face_Pedestrian_Track test set demonstrate that in complex scenes,the proposed method improves Face-Pedestrian Matching F1 area under the curve(F1 AUC)by approximately 4 to 43 percentage points compared to several traditional methods.The joint tracking model achieves overall performance metrics of IDF1:85.1825%and MOTA:86.5956%,representing improvements of 0.91 and 0.06 percentage points,respectively,over the baseline model.Ablation studies confirm the effectiveness of key modules such as the Intersection over Area(IoA)/Intersection over Union(IoU)joint metric and dynamic threshold adjustment,validating the significant role of the cross-category identity matching mechanism in enhancing tracking stability.Our_model shows a 16.7%frame per second(FPS)drop vs.fairness of detection and re-identification in multiple object tracking(FairMOT),with its cross-category binding module adding aboute 10%overhead,yet maintains near-real-time performance for essential face-pedestrian tracking at small resolutions.展开更多
A personalized outfit recommendation has emerged as a hot research topic in the fashion domain.However,existing recommendations do not fully exploit user style preferences.Typically,users prefer particular styles such...A personalized outfit recommendation has emerged as a hot research topic in the fashion domain.However,existing recommendations do not fully exploit user style preferences.Typically,users prefer particular styles such as casual and athletic styles,and consider attributes like color and texture when selecting outfits.To achieve personalized outfit recommendations in line with user style preferences,this paper proposes a personal style guided outfit recommendation with multi-modal fashion compatibility modeling,termed as PSGNet.Firstly,a style classifier is designed to categorize fashion images of various clothing types and attributes into distinct style categories.Secondly,a personal style prediction module extracts user style preferences by analyzing historical data.Then,to address the limitations of single-modal representations and enhance fashion compatibility,both fashion images and text data are leveraged to extract multi-modal features.Finally,PSGNet integrates these components through Bayesian personalized ranking(BPR)to unify the personal style and fashion compatibility,where the former is used as personal style features and guides the output of the personalized outfit recommendation tailored to the target user.Extensive experiments on large-scale datasets demonstrate that the proposed model is efficient on the personalized outfit recommendation.展开更多
Accurate calibration of surgical instruments and ultrasound probes is essential for achieving high precision in image guided minimally invasive procedures.However,existing methods typically treat the calibration of th...Accurate calibration of surgical instruments and ultrasound probes is essential for achieving high precision in image guided minimally invasive procedures.However,existing methods typically treat the calibration of the needle tip and the ultrasound probe as two independent processes,lacking an integrated calibration mechanism,which often leads to cumulative errors and reduced spatial consistency.To address this challenge,we propose a joint calibration model that unifies the calibration of the surgical needle tip and the ultrasound probe within a single coordinate system.The method formulates the calibration process through a series of mathematical models and coordinate transformation models and employs a gradient descent based optimization to refine the parameters of these models.By establishing and iteratively optimizing a template coordinate system through modeling of constrained spherical motion,the proposed joint calibration model achieves submillimeter accuracy in needle tip localization.Building upon this,an N line based calibration model is developed to determine the spatial relationship between the probe and the ultrasound image plane,resulting in an average pixel deviation of only 1.2373 mm.Experimental results confirm that this unified modeling approach effectively overcomes the limitations of separate calibration schemes,significantly enhancing both precision and robustness,and providing a reliable computational model for surgical navigation systems that require high spatial accuracy without relying on ionizing radiation.展开更多
Structural defects such as joints or faults are inherent to almost any rock mass.In many situations those defects have a major impact on slope stability as they can control the possible failure mechanisms.Having a goo...Structural defects such as joints or faults are inherent to almost any rock mass.In many situations those defects have a major impact on slope stability as they can control the possible failure mechanisms.Having a good estimate of their strength then becomes crucial.The roughness of a structure is a major contributor to its strength through two different aspects,i.e.the morphology of the surface(or the shape)and the strength of the asperities(related to the strength of the rock).In the current state of practice,roughness is assessed through idealized descriptions(Patton strength criterion)or through empirical parameters(Barton JRC).In both cases,the multi-dimensionality of the roughness is ignored.In this study,we propose to take advantage of the latest developments in numerical techniques.With3D photogrammetry and/or laser mapping,practitioners have access to the real morphology of an exposed structure.The derived triangulated surface was introduced into the DEM(discrete element method)code PFC3D to create a synthetic rock joint.The interaction between particles on either side of the discontinuity was described by a smooth-joint model(SJM),hence suppressing the artificial roughness introduced by the particle discretization.Shear tests were then performed on the synthetic rock joint.A good correspondence between strengths predicted by the model and strengths derived from well-established techniques was obtained for thefirst time.Amongst the benefits of the methodology is the possibility offered by the model to be used in a quantitative way for shear strength estimates,to reproduce the progressive degradation of the asperities upon shearing and to analyze structures of different scales without introducing any empirical relation.展开更多
The paper investigated the equivalent continuum modeling of beam-like repetitive truss structures considering the flexibility of joints,which models the contact between the truss member and joint by spring-damper with...The paper investigated the equivalent continuum modeling of beam-like repetitive truss structures considering the flexibility of joints,which models the contact between the truss member and joint by spring-damper with six directional stiffnesses and dampings.Firstly,a two-node hybrid joint-beam element was derived for modeling the truss member with flexible end joints,and a condensed model for the repeating element with flexible joints was obtained.Then,the energy equivalence method was adopted to equivalently model the truss structure with flexible joints and material damping as a spatial viscoelastic anisotropic beam model.Afterwards,the equations of motion for the equivalent beam model were derived and solved analytically in the frequency domain.In the numerical studies,the correctness of the presented method was verified by comparisons of the natural frequencies and frequency responses evaluated by the equivalent beam model with the results of the finite element method model.展开更多
The coal-bearing strata of the deep Upper Paleozoic in the GS Sag have high hydrocarbon potential. Because of the absence of seismic data, we use electromagnetic （MT） and gravity data jointly to delineate the distri...The coal-bearing strata of the deep Upper Paleozoic in the GS Sag have high hydrocarbon potential. Because of the absence of seismic data, we use electromagnetic （MT） and gravity data jointly to delineate the distribution of deep targets based on well logging and geological data. First, a preliminary geological model is established by using three-dimensional （3D） MT inversion results. Second, using the formation density and gravity anomalies, the preliminary geological model is modified by interactive inversion of the gravity data. Then, we conduct MT-constrained inversion based on the modified model to obtain an optimal geological model until the deviations at all stations are minimized. Finally, the geological model and a seismic profile in the middle of the sag is analysed. We determine that the deep reflections of the seismic profile correspond to the Upper Paleozoic that reaches thickness up to 800 m. The processing of field data suggests that the joint MT-gravity modeling and constrained inversion can reduce the multiple solutions for single geophysical data and thus improve the recognition of deep formations. The MT-constrained inversion is consistent with the geological features in the seismic section. This suggests that the joint MT and gravity modeling and constrained inversion can be used to delineate deep targets in similar basins.展开更多
To map the rock joints in the underground rock mass,a method was proposed to semiautomatically detect the rock joints from borehole imaging logs using a deep learning algorithm.First,450 images containing rock joints ...To map the rock joints in the underground rock mass,a method was proposed to semiautomatically detect the rock joints from borehole imaging logs using a deep learning algorithm.First,450 images containing rock joints were selected from borehole ZKZ01 in the Rumei hydropower station.These images were labeled to establish ground truth which was subdivided into training,validation,and testing data.Second,the YOLO v2 model with optimal parameter settings was constructed.Third,the training and validation data were used for model training,while the test data was used to generate the precision-recall curve for prediction evaluation.Fourth,the trained model was applied to a new borehole ZKZ02 to verify the feasibility of the model.There were 12 rock joints detected from the selected images in borehole ZKZ02 and four geometric parameters for each rock joint were determined by sinusoidal curve fitting.The average precision of the trained model reached 0.87.展开更多
Gesture recognition is used in many practical applications such as human-robot interaction, medical rehabilitation and sign language. With increasing motion sensor development, multiple data sources have become availa...Gesture recognition is used in many practical applications such as human-robot interaction, medical rehabilitation and sign language. With increasing motion sensor development, multiple data sources have become available, which leads to the rise of multi-modal gesture recognition. Since our previous approach to gesture recognition depends on a unimodal system, it is difficult to classify similar motion patterns. In order to solve this problem, a novel approach which integrates motion, audio and video models is proposed by using dataset captured by Kinect. The proposed system can recognize observed gestures by using three models. Recognition results of three models are integrated by using the proposed framework and the output becomes the final result. The motion and audio models are learned by using Hidden Markov Model. Random Forest which is the video classifier is used to learn the video model. In the experiments to test the performances of the proposed system, the motion and audio models most suitable for gesture recognition are chosen by varying feature vectors and learning methods. Additionally, the unimodal and multi-modal models are compared with respect to recognition accuracy. All the experiments are conducted on dataset provided by the competition organizer of MMGRC, which is a workshop for Multi-Modal Gesture Recognition Challenge. The comparison results show that the multi-modal model composed of three models scores the highest recognition rate. This improvement of recognition accuracy means that the complementary relationship among three models improves the accuracy of gesture recognition. The proposed system provides the application technology to understand human actions of daily life more precisely.展开更多
Metal magnetic memory（MMM） testing has been widely used to detect welded joints. However, load levels, environmental magnetic field, and measurement noises make the MMM data dispersive and bring difficulty to quanti...Metal magnetic memory（MMM） testing has been widely used to detect welded joints. However, load levels, environmental magnetic field, and measurement noises make the MMM data dispersive and bring difficulty to quantitative evaluation. In order to promote the development of quantitative MMM reliability assessment, a new MMM model is presented for welded joints. Steel Q235 welded specimens are tested along the longitudinal and horizontal lines by TSC-2M-8 instrument in the tensile fatigue experiments. The X-ray testing is carried out synchronously to verify the MMM results. It is found that MMM testing can detect the hidden crack earlier than X-ray testing. Moreover, the MMM gradient vector sum K_（vs） is sensitive to the damage degree, especially at early and hidden damage stages. Considering the dispersion of MMM data, the K_（vs） statistical law is investigated, which shows that K_（vs） obeys Gaussian distribution. So K_（vs） is the suitable MMM parameter to establish reliability model of welded joints. At last, the original quantitative MMM reliability model is first presented based on the improved stress strength interference theory. It is shown that the reliability degree R gradually decreases with the decreasing of the residual life ratio T, and the maximal error between prediction reliability degree R_1 and verification reliability degree R_2 is 9.15%. This presented method provides a novel tool of reliability testing and evaluating in practical engineering for welded joints.展开更多
To gain a thorough understanding of the load state of parallel kinematic machines(PKMs), a methodology of elastodynamic modeling and joint reaction prediction is proposed. For this purpose, a Sprint Z3 model is used a...To gain a thorough understanding of the load state of parallel kinematic machines(PKMs), a methodology of elastodynamic modeling and joint reaction prediction is proposed. For this purpose, a Sprint Z3 model is used as a case study to illustrate the process of joint reaction analysis. The substructure synthesis method is applied to deriving an analytical elastodynamic model for the 3-PRS PKM device, in which the compliances of limbs and joints are considered. Each limb assembly is modeled as a spatial beam with non-uniform cross-section supported by lumped virtual springs at the centers of revolute and spherical joints. By introducing the deformation compatibility conditions between the limbs and the platform, the governing equations of motion of the system are obtained. After degenerating the governing equations into quasi-static equations, the effects of the gravity on system deflections and joint reactions are investigated with the purpose of providing useful information for the kinematic calibration and component strength calculations as well as structural optimizations of the 3-PRS PKM module. The simulation results indicate that the elastic deformation of the moving platform in the direction of gravity caused by gravity is quite large and cannot be ignored. Meanwhile, the distributions of joint reactions are axisymmetric and position-dependent. It is worthy to note that the proposed elastodynamic modeling method combines the benefits of accuracy of finite element method and concision of analytical method so that it can be used to predict the stiffness characteristics and joint reactions of a PKM throughout its entire workspace in a quick and accurate manner. Moreover, the present model can also be easily applied to evaluating the overall rigidity performance as well as statics of other PKMs with high efficiency after minor modifications.展开更多
The improved version of Los Alamos model with the multi-modal fission approach is used to analyse the prompt fission neutron spectrum and multiplicity for the neutron-induced fission of 237Np. The spectra of neutrons ...The improved version of Los Alamos model with the multi-modal fission approach is used to analyse the prompt fission neutron spectrum and multiplicity for the neutron-induced fission of 237Np. The spectra of neutrons emitted from fragments for the three most dominant fission modes （standard Ⅰ, standard Ⅱ and superlong） are calculated separately and the total spectrum is synthesized. The multi-modal parameters contained in the spectrum model are determined on the basis of experimental data of fission fragment mass distributions. The calculated total prompt fission neutron spectrum and multiplicity are better agreement with the experimental data than those obtained from the conventional treatment of the Los Alamos model.展开更多
How nonlinear joints affect the response of large space structures is an important problem to investigate.In this paper,a multi-harmonic equivalent modeling method is presented to establish a frequency-domain model of...How nonlinear joints affect the response of large space structures is an important problem to investigate.In this paper,a multi-harmonic equivalent modeling method is presented to establish a frequency-domain model of planar repetitive structures with nonlinear joints.First,at the local level,the nonlinear joint is modeled by the multi-harmonic describing function matrix.The element of the hybrid beam is obtained by the dynamic condensation of the beam-joint element.Second,at the global level,the displacement-equivalence method is used to model the multi-harmonic Euler continuum beam equivalent to the planar repetitive structure.Then,the pseudo-arc-length continuation method is applied to track the multi-harmonic trajectory of response.Afterwards,an experiment is conducted to validate the correctness of the modeling method,considering the effect of hanging rope and air damping.In the numerical studies,several simulation results indicate the similarity of response between a single-degree-of-freedom system with a single nonlinear joint and the system of the planar repetitive structure with a large number of nonlinear joints.Finally,the component of higher-order harmonics is shown to be important for predicting the resonance frequencies and amplitudes.展开更多
An attempt is made to improve the evaluation of the prompt fission neutron emis- sion from 233U（n, f） reaction for incident neutron energies below 6 MeV. The multi-modal fission approach is applied to the improved v...An attempt is made to improve the evaluation of the prompt fission neutron emis- sion from 233U（n, f） reaction for incident neutron energies below 6 MeV. The multi-modal fission approach is applied to the improved version of Los Alamos model and the point by point model. The prompt fission neutron spectra and the prompt fission neutron as a function of fragment mass （usually named ＂sawtooth＂ data） v（A） are calculated independently for the three most dominant fission modes （standard I, standard II and superlong）, and the total spectra and v（A） are syn- thesized. The multi-modal parameters are determined on the basis of experimental data of fission fragment mass distributions. The present calculation results can describe the experimental data very well, and the proposed treatment is thus a useful tool for prompt fission neutron emission prediction.展开更多
Clearance between the moving joints is unavoidable in real working process. At present, many researches are mainly focused on dynamics of plane revolute joint in plane mechanism, but few on dynamics of spatial spheric...Clearance between the moving joints is unavoidable in real working process. At present, many researches are mainly focused on dynamics of plane revolute joint in plane mechanism, but few on dynamics of spatial spherical joint clearance in spatial parallel mechanism. In this paper, a general method is proposed for establishing dynamic equations of spatial parallel mechanism with spatial spherical clearance by Lagrange multiplier method. The kinematic model and contact force model of the spherical joint clearance were established successively. Lagrange multiplier method was used to deduce the dynamics equation of 4 UPS-UPU mechanism with spherical clearance joint systematically. The influence of friction coefficient on dynamics response of 4 UPS-UPU mechanism with spherical clearance joint was analyzed. Non-linear characteristics of clearance joint and moving platform were analyzed by Poincare map, phase diagram, and bifurcation diagram. The results show that variation of friction coefficient and clearance value had little effect on stability of the mechanism, but the chaotic phenomenon was found at spherical clearance joint. The research has theoretical guiding significance for improving the dynamic performance and avoiding of chaos of parallel mechanisms including spherical joint clearance.展开更多
Aimed at the problems of design difficulty and weak kinematic performance caused by spherical joint,a novel PRC+PRCR+RR humanoid ankle joint based on the partially decoupled spherical parallel mechanism is proposed.Ac...Aimed at the problems of design difficulty and weak kinematic performance caused by spherical joint,a novel PRC+PRCR+RR humanoid ankle joint based on the partially decoupled spherical parallel mechanism is proposed.According to screw theory,the degree of freedom and decoupling characteristics of this mechanism are analyzed.Based on Klein formula and virtual work principle,the kinematic expressions of each link and dynamic model are established.The correctness of the dynamic model is verified by combining the virtual prototype software and the ankle pose function obtained by gait planning and Fourier fitting.The workspace of this mechanism is mapped into a two-dimensional polar coordinate system with the azimuth and elevation angles of the spherical coordinate system as parameters.The motion/force transmission index and constraint index of this mechanism are evaluated and expressed in the workspace,showing this mechanism with excellent kinematic characteristics.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
Rock joints always have a smaller strength,and it plays an important influence on the overall strength of rock mass.The mechanical behavior of rock joints is mainly governed by the surface topography,normal stress,and...Rock joints always have a smaller strength,and it plays an important influence on the overall strength of rock mass.The mechanical behavior of rock joints is mainly governed by the surface topography,normal stress,and failure degree.In this study,a series of direct shear tests for four different rough rock joints under five normal stresses was carried out.The shear and normal stiffnesses were first determined,and the shear shrinkage effect was represented by a shear-normal coupling coefficient.Assuming that the strength of the joint is composed of frictional and cohesive parts,the evolutions of cohesion,friction angle with joint roughness coefficient(JRC),and plastic shear displacement are obtained.The dilatancy behavior is described by the dilation angle,which is considered a function of JRC,plastic shear displacement,and normal stress.A cohesive-frictional elastoplastic constitutive model is hence proposed.The theoretical curves under constant normal stress conditions of the proposed model are in good agreement with the experimental results.The shear behaviors under constant normal stiffness and constant normal displacement conditions can be predicted using the new constitutive model.展开更多
The configuration of underground powerhouses is crucial in pumped-storage hydropower projects,which play a vital role in maintaining grid stability,facilitating the integration of renewable energy sources,and managing...The configuration of underground powerhouses is crucial in pumped-storage hydropower projects,which play a vital role in maintaining grid stability,facilitating the integration of renewable energy sources,and managing flood risks.However,geotechnical challenges,such as complex joint orientations,anisotropy in in-situ stress,and rock damage caused by excavation,require thorough stability assessments.This research employs the ubiquitous anisotropic joint model within FLAC3D to investigate the effects of joint dip angle,joint dip direction,and the alignment of in-situ stress on the stability of surrounding rock formations.The key parameters analyzed include joint cohesion,friction angle,and the magnitude of in-situ stress.The numerical results indicate that deformation is minimized when the axis of the powerhouse is aligned with the major principal stress.Furthermore,joint dip angles between 65°and 70°lead to a 50%reduction in both displacement and plastic zone volume.Additionally,angles less than 40°between the joint dip direction and the powerhouse axis enhance stability.These findings provide practical recommendations for optimizing the orientation of powerhouses in geomechanical contexts similar to those characterized by foliated sericite phyllite with moderate joint persistence.展开更多
Firstly, studies on propagation of one-dimensional normally incident wave in rock mass containing no joint, a single joint and two parallel joints were conducted by Three Dimensional Distinct Element Codes(3DEC). By c...Firstly, studies on propagation of one-dimensional normally incident wave in rock mass containing no joint, a single joint and two parallel joints were conducted by Three Dimensional Distinct Element Codes(3DEC). By comparison of the modeling results with the theoretical solutions, it has been found that a good agreement between them has been achieved. It is verified that the 3DEC is capable of modeling wave propagation in rock masses. Secondly, propagation of normally incident P-wave across two parallel joints was studied. The modeling results show that transmission coefficient increases with the increasing ratio of joint spacing to wavelength at first, then decreases with the increasing ratio of joint spacing to wavelength, lastly keeps constant. Finally, effect of interlayer on wave propagation is investigated. It is shown that interlayer results in marked attenuation and leading phase, and that attenuation increases with the increasing frequency and the increasing thickness of interlayer.展开更多
Prolonged cyclic water intrusion has progressively developed joints in the hydro-fluctuation belt,elevating the instability risk of reservoir bank slopes.To investigate its impact on joint shear damage evolution,joint...Prolonged cyclic water intrusion has progressively developed joints in the hydro-fluctuation belt,elevating the instability risk of reservoir bank slopes.To investigate its impact on joint shear damage evolution,joint samples were prepared using three representative roughness curves and subjected to direct shear testing following cyclic water intrusion.A shear damage constitutive model considering the coupling effect of cyclic water intrusion and load was developed based on macroscopic phenomenological damage mechanics and micro-statistical theory.Results indicate:(1)All critical shear mechanical parameters(including peak shear strength,shear stiffness,basic friction angle,and joint compressive strength)exhibit progressive deterioration with increasing water intrusion cycles;(2)Model validation through experimental curve comparisons confirms its reliability.The model demonstrates that intensified water intrusion cycles reduce key mechanical indices,inducing a brittle-to-ductile transition in joint surface deformation—a behavior consistent with experimental observations;(3)Damage under cyclic water intrusion and load coupling follows an S-shaped trend,divided into stabilization(water-dominated stage),development(load-dominated stage),and completion stages.The research provides valuable insights for stability studies,such as similar model experiments for reservoir bank slopes and other water-related projects.展开更多
基金supported by the confidential research grant No.a8317。
文摘To address the issues of frequent identity switches(IDs)and degraded identification accuracy in multi object tracking(MOT)under complex occlusion scenarios,this study proposes an occlusion-robust tracking framework based on face-pedestrian joint feature modeling.By constructing a joint tracking model centered on“intra-class independent tracking+cross-category dynamic binding”,designing a multi-modal matching metric with spatio-temporal and appearance constraints,and innovatively introducing a cross-category feature mutual verification mechanism and a dual matching strategy,this work effectively resolves performance degradation in traditional single-category tracking methods caused by short-term occlusion,cross-camera tracking,and crowded environments.Experiments on the Chokepoint_Face_Pedestrian_Track test set demonstrate that in complex scenes,the proposed method improves Face-Pedestrian Matching F1 area under the curve(F1 AUC)by approximately 4 to 43 percentage points compared to several traditional methods.The joint tracking model achieves overall performance metrics of IDF1:85.1825%and MOTA:86.5956%,representing improvements of 0.91 and 0.06 percentage points,respectively,over the baseline model.Ablation studies confirm the effectiveness of key modules such as the Intersection over Area(IoA)/Intersection over Union(IoU)joint metric and dynamic threshold adjustment,validating the significant role of the cross-category identity matching mechanism in enhancing tracking stability.Our_model shows a 16.7%frame per second(FPS)drop vs.fairness of detection and re-identification in multiple object tracking(FairMOT),with its cross-category binding module adding aboute 10%overhead,yet maintains near-real-time performance for essential face-pedestrian tracking at small resolutions.
基金Shanghai Frontier Science Research Center for Modern Textiles,Donghua University,ChinaOpen Project of Henan Key Laboratory of Intelligent Manufacturing of Mechanical Equipment,Zhengzhou University of Light Industry,China(No.IM202303)National Key Research and Development Program of China(No.2019YFB1706300)。
文摘A personalized outfit recommendation has emerged as a hot research topic in the fashion domain.However,existing recommendations do not fully exploit user style preferences.Typically,users prefer particular styles such as casual and athletic styles,and consider attributes like color and texture when selecting outfits.To achieve personalized outfit recommendations in line with user style preferences,this paper proposes a personal style guided outfit recommendation with multi-modal fashion compatibility modeling,termed as PSGNet.Firstly,a style classifier is designed to categorize fashion images of various clothing types and attributes into distinct style categories.Secondly,a personal style prediction module extracts user style preferences by analyzing historical data.Then,to address the limitations of single-modal representations and enhance fashion compatibility,both fashion images and text data are leveraged to extract multi-modal features.Finally,PSGNet integrates these components through Bayesian personalized ranking(BPR)to unify the personal style and fashion compatibility,where the former is used as personal style features and guides the output of the personalized outfit recommendation tailored to the target user.Extensive experiments on large-scale datasets demonstrate that the proposed model is efficient on the personalized outfit recommendation.
基金Support by Sichuan Science and Technology Program[2023YFSY0026,2023YFH0004].
文摘Accurate calibration of surgical instruments and ultrasound probes is essential for achieving high precision in image guided minimally invasive procedures.However,existing methods typically treat the calibration of the needle tip and the ultrasound probe as two independent processes,lacking an integrated calibration mechanism,which often leads to cumulative errors and reduced spatial consistency.To address this challenge,we propose a joint calibration model that unifies the calibration of the surgical needle tip and the ultrasound probe within a single coordinate system.The method formulates the calibration process through a series of mathematical models and coordinate transformation models and employs a gradient descent based optimization to refine the parameters of these models.By establishing and iteratively optimizing a template coordinate system through modeling of constrained spherical motion,the proposed joint calibration model achieves submillimeter accuracy in needle tip localization.Building upon this,an N line based calibration model is developed to determine the spatial relationship between the probe and the ultrasound image plane,resulting in an average pixel deviation of only 1.2373 mm.Experimental results confirm that this unified modeling approach effectively overcomes the limitations of separate calibration schemes,significantly enhancing both precision and robustness,and providing a reliable computational model for surgical navigation systems that require high spatial accuracy without relying on ionizing radiation.
基金funding provided by the Swiss Federal Office for Water and Geology
文摘Structural defects such as joints or faults are inherent to almost any rock mass.In many situations those defects have a major impact on slope stability as they can control the possible failure mechanisms.Having a good estimate of their strength then becomes crucial.The roughness of a structure is a major contributor to its strength through two different aspects,i.e.the morphology of the surface(or the shape)and the strength of the asperities(related to the strength of the rock).In the current state of practice,roughness is assessed through idealized descriptions(Patton strength criterion)or through empirical parameters(Barton JRC).In both cases,the multi-dimensionality of the roughness is ignored.In this study,we propose to take advantage of the latest developments in numerical techniques.With3D photogrammetry and/or laser mapping,practitioners have access to the real morphology of an exposed structure.The derived triangulated surface was introduced into the DEM(discrete element method)code PFC3D to create a synthetic rock joint.The interaction between particles on either side of the discontinuity was described by a smooth-joint model(SJM),hence suppressing the artificial roughness introduced by the particle discretization.Shear tests were then performed on the synthetic rock joint.A good correspondence between strengths predicted by the model and strengths derived from well-established techniques was obtained for thefirst time.Amongst the benefits of the methodology is the possibility offered by the model to be used in a quantitative way for shear strength estimates,to reproduce the progressive degradation of the asperities upon shearing and to analyze structures of different scales without introducing any empirical relation.
基金This work was supported by the National Natural Science Foundation of China(Grants 11702146,11732006 and 11827801)the Equipment Pre-research Foundation(Grant 6140210010202).
文摘The paper investigated the equivalent continuum modeling of beam-like repetitive truss structures considering the flexibility of joints,which models the contact between the truss member and joint by spring-damper with six directional stiffnesses and dampings.Firstly,a two-node hybrid joint-beam element was derived for modeling the truss member with flexible end joints,and a condensed model for the repeating element with flexible joints was obtained.Then,the energy equivalence method was adopted to equivalently model the truss structure with flexible joints and material damping as a spatial viscoelastic anisotropic beam model.Afterwards,the equations of motion for the equivalent beam model were derived and solved analytically in the frequency domain.In the numerical studies,the correctness of the presented method was verified by comparisons of the natural frequencies and frequency responses evaluated by the equivalent beam model with the results of the finite element method model.
基金supported by the National Science and Technology Major Project(No.2016ZX05018006)the National Key Research Development Program(No.2016YFC0601104)the National Natural Science Foundation of China(No.41472136)
文摘The coal-bearing strata of the deep Upper Paleozoic in the GS Sag have high hydrocarbon potential. Because of the absence of seismic data, we use electromagnetic （MT） and gravity data jointly to delineate the distribution of deep targets based on well logging and geological data. First, a preliminary geological model is established by using three-dimensional （3D） MT inversion results. Second, using the formation density and gravity anomalies, the preliminary geological model is modified by interactive inversion of the gravity data. Then, we conduct MT-constrained inversion based on the modified model to obtain an optimal geological model until the deviations at all stations are minimized. Finally, the geological model and a seismic profile in the middle of the sag is analysed. We determine that the deep reflections of the seismic profile correspond to the Upper Paleozoic that reaches thickness up to 800 m. The processing of field data suggests that the joint MT-gravity modeling and constrained inversion can reduce the multiple solutions for single geophysical data and thus improve the recognition of deep formations. The MT-constrained inversion is consistent with the geological features in the seismic section. This suggests that the joint MT and gravity modeling and constrained inversion can be used to delineate deep targets in similar basins.
基金supported by the National Key R&D Program of China(No.2023YFC3081200)the National Natural Science Foundation of China(No.42077264)。
文摘To map the rock joints in the underground rock mass,a method was proposed to semiautomatically detect the rock joints from borehole imaging logs using a deep learning algorithm.First,450 images containing rock joints were selected from borehole ZKZ01 in the Rumei hydropower station.These images were labeled to establish ground truth which was subdivided into training,validation,and testing data.Second,the YOLO v2 model with optimal parameter settings was constructed.Third,the training and validation data were used for model training,while the test data was used to generate the precision-recall curve for prediction evaluation.Fourth,the trained model was applied to a new borehole ZKZ02 to verify the feasibility of the model.There were 12 rock joints detected from the selected images in borehole ZKZ02 and four geometric parameters for each rock joint were determined by sinusoidal curve fitting.The average precision of the trained model reached 0.87.
基金Supported by Grant-in-Aid for Young Scientists(A)(Grant No.26700021)Japan Society for the Promotion of Science and Strategic Information and Communications R&D Promotion Programme(Grant No.142103011)Ministry of Internal Affairs and Communications
文摘Gesture recognition is used in many practical applications such as human-robot interaction, medical rehabilitation and sign language. With increasing motion sensor development, multiple data sources have become available, which leads to the rise of multi-modal gesture recognition. Since our previous approach to gesture recognition depends on a unimodal system, it is difficult to classify similar motion patterns. In order to solve this problem, a novel approach which integrates motion, audio and video models is proposed by using dataset captured by Kinect. The proposed system can recognize observed gestures by using three models. Recognition results of three models are integrated by using the proposed framework and the output becomes the final result. The motion and audio models are learned by using Hidden Markov Model. Random Forest which is the video classifier is used to learn the video model. In the experiments to test the performances of the proposed system, the motion and audio models most suitable for gesture recognition are chosen by varying feature vectors and learning methods. Additionally, the unimodal and multi-modal models are compared with respect to recognition accuracy. All the experiments are conducted on dataset provided by the competition organizer of MMGRC, which is a workshop for Multi-Modal Gesture Recognition Challenge. The comparison results show that the multi-modal model composed of three models scores the highest recognition rate. This improvement of recognition accuracy means that the complementary relationship among three models improves the accuracy of gesture recognition. The proposed system provides the application technology to understand human actions of daily life more precisely.
基金Supported by National Natural Science Foundation of China(Grant Nos.11272084,11472076)PetroChina Innovation Foundation(Grant No.2015D-5006-0602)Postdoctoral Science Research Developmental Foundation of Chinese Heilongjiang Province(Grant No.LBH-Q13035)
文摘Metal magnetic memory（MMM） testing has been widely used to detect welded joints. However, load levels, environmental magnetic field, and measurement noises make the MMM data dispersive and bring difficulty to quantitative evaluation. In order to promote the development of quantitative MMM reliability assessment, a new MMM model is presented for welded joints. Steel Q235 welded specimens are tested along the longitudinal and horizontal lines by TSC-2M-8 instrument in the tensile fatigue experiments. The X-ray testing is carried out synchronously to verify the MMM results. It is found that MMM testing can detect the hidden crack earlier than X-ray testing. Moreover, the MMM gradient vector sum K_（vs） is sensitive to the damage degree, especially at early and hidden damage stages. Considering the dispersion of MMM data, the K_（vs） statistical law is investigated, which shows that K_（vs） obeys Gaussian distribution. So K_（vs） is the suitable MMM parameter to establish reliability model of welded joints. At last, the original quantitative MMM reliability model is first presented based on the improved stress strength interference theory. It is shown that the reliability degree R gradually decreases with the decreasing of the residual life ratio T, and the maximal error between prediction reliability degree R_1 and verification reliability degree R_2 is 9.15%. This presented method provides a novel tool of reliability testing and evaluating in practical engineering for welded joints.
基金Project(Kfkt2013-12)supported by Open Research Fund of Key Laboratory of High Performance Complex Manufacturing of Central South University,ChinaProject(2014002)supported by the Open Fund of Shanghai Key Laboratory of Digital Manufacture for Thin-walled Structures,ChinaProject(51375013)supported by the National Natural Science Foundation of China
文摘To gain a thorough understanding of the load state of parallel kinematic machines(PKMs), a methodology of elastodynamic modeling and joint reaction prediction is proposed. For this purpose, a Sprint Z3 model is used as a case study to illustrate the process of joint reaction analysis. The substructure synthesis method is applied to deriving an analytical elastodynamic model for the 3-PRS PKM device, in which the compliances of limbs and joints are considered. Each limb assembly is modeled as a spatial beam with non-uniform cross-section supported by lumped virtual springs at the centers of revolute and spherical joints. By introducing the deformation compatibility conditions between the limbs and the platform, the governing equations of motion of the system are obtained. After degenerating the governing equations into quasi-static equations, the effects of the gravity on system deflections and joint reactions are investigated with the purpose of providing useful information for the kinematic calibration and component strength calculations as well as structural optimizations of the 3-PRS PKM module. The simulation results indicate that the elastic deformation of the moving platform in the direction of gravity caused by gravity is quite large and cannot be ignored. Meanwhile, the distributions of joint reactions are axisymmetric and position-dependent. It is worthy to note that the proposed elastodynamic modeling method combines the benefits of accuracy of finite element method and concision of analytical method so that it can be used to predict the stiffness characteristics and joint reactions of a PKM throughout its entire workspace in a quick and accurate manner. Moreover, the present model can also be easily applied to evaluating the overall rigidity performance as well as statics of other PKMs with high efficiency after minor modifications.
基金Project supported by the State Key Development Program for Basic Research of China (Grant Nos 2008CB717803 and 2007ID103)the Research Fund for the Doctoral Program of Higher Education of China (Gant No 200610001023)
文摘The improved version of Los Alamos model with the multi-modal fission approach is used to analyse the prompt fission neutron spectrum and multiplicity for the neutron-induced fission of 237Np. The spectra of neutrons emitted from fragments for the three most dominant fission modes （standard Ⅰ, standard Ⅱ and superlong） are calculated separately and the total spectrum is synthesized. The multi-modal parameters contained in the spectrum model are determined on the basis of experimental data of fission fragment mass distributions. The calculated total prompt fission neutron spectrum and multiplicity are better agreement with the experimental data than those obtained from the conventional treatment of the Los Alamos model.
基金This work was supported by the National Natural Science Foundation of China(Grant Nos.11827801,12172181 and 11732006).
文摘How nonlinear joints affect the response of large space structures is an important problem to investigate.In this paper,a multi-harmonic equivalent modeling method is presented to establish a frequency-domain model of planar repetitive structures with nonlinear joints.First,at the local level,the nonlinear joint is modeled by the multi-harmonic describing function matrix.The element of the hybrid beam is obtained by the dynamic condensation of the beam-joint element.Second,at the global level,the displacement-equivalence method is used to model the multi-harmonic Euler continuum beam equivalent to the planar repetitive structure.Then,the pseudo-arc-length continuation method is applied to track the multi-harmonic trajectory of response.Afterwards,an experiment is conducted to validate the correctness of the modeling method,considering the effect of hanging rope and air damping.In the numerical studies,several simulation results indicate the similarity of response between a single-degree-of-freedom system with a single nonlinear joint and the system of the planar repetitive structure with a large number of nonlinear joints.Finally,the component of higher-order harmonics is shown to be important for predicting the resonance frequencies and amplitudes.
基金supported by the State Key Development Program for Basic Research of China (Nos. 2008CB717803, 2009GB107001, and2007CB209903)the Research Fund for the Doctoral Program of Higher Education of China (No. 200610011023)
文摘An attempt is made to improve the evaluation of the prompt fission neutron emis- sion from 233U（n, f） reaction for incident neutron energies below 6 MeV. The multi-modal fission approach is applied to the improved version of Los Alamos model and the point by point model. The prompt fission neutron spectra and the prompt fission neutron as a function of fragment mass （usually named ＂sawtooth＂ data） v（A） are calculated independently for the three most dominant fission modes （standard I, standard II and superlong）, and the total spectra and v（A） are syn- thesized. The multi-modal parameters are determined on the basis of experimental data of fission fragment mass distributions. The present calculation results can describe the experimental data very well, and the proposed treatment is thus a useful tool for prompt fission neutron emission prediction.
基金Sponsored by the Natural Science Foundation of Shandong Province(Grand No.ZR2017MEE066)the Shandong Key Research and Development Public Welfare Program(2019GGX104001)。
文摘Clearance between the moving joints is unavoidable in real working process. At present, many researches are mainly focused on dynamics of plane revolute joint in plane mechanism, but few on dynamics of spatial spherical joint clearance in spatial parallel mechanism. In this paper, a general method is proposed for establishing dynamic equations of spatial parallel mechanism with spatial spherical clearance by Lagrange multiplier method. The kinematic model and contact force model of the spherical joint clearance were established successively. Lagrange multiplier method was used to deduce the dynamics equation of 4 UPS-UPU mechanism with spherical clearance joint systematically. The influence of friction coefficient on dynamics response of 4 UPS-UPU mechanism with spherical clearance joint was analyzed. Non-linear characteristics of clearance joint and moving platform were analyzed by Poincare map, phase diagram, and bifurcation diagram. The results show that variation of friction coefficient and clearance value had little effect on stability of the mechanism, but the chaotic phenomenon was found at spherical clearance joint. The research has theoretical guiding significance for improving the dynamic performance and avoiding of chaos of parallel mechanisms including spherical joint clearance.
基金the Zhejiang Province Foundation for Distinguished Young Scholars of China(No.LR18E050003)the National Natural Science Foundation of China(Nos.51975523 and 51475424)。
文摘Aimed at the problems of design difficulty and weak kinematic performance caused by spherical joint,a novel PRC+PRCR+RR humanoid ankle joint based on the partially decoupled spherical parallel mechanism is proposed.According to screw theory,the degree of freedom and decoupling characteristics of this mechanism are analyzed.Based on Klein formula and virtual work principle,the kinematic expressions of each link and dynamic model are established.The correctness of the dynamic model is verified by combining the virtual prototype software and the ankle pose function obtained by gait planning and Fourier fitting.The workspace of this mechanism is mapped into a two-dimensional polar coordinate system with the azimuth and elevation angles of the spherical coordinate system as parameters.The motion/force transmission index and constraint index of this mechanism are evaluated and expressed in the workspace,showing this mechanism with excellent kinematic characteristics.
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financial support from the National Natural Science Foundation of China(Grant Nos.52074269,52474157 and 51979272).
文摘Rock joints always have a smaller strength,and it plays an important influence on the overall strength of rock mass.The mechanical behavior of rock joints is mainly governed by the surface topography,normal stress,and failure degree.In this study,a series of direct shear tests for four different rough rock joints under five normal stresses was carried out.The shear and normal stiffnesses were first determined,and the shear shrinkage effect was represented by a shear-normal coupling coefficient.Assuming that the strength of the joint is composed of frictional and cohesive parts,the evolutions of cohesion,friction angle with joint roughness coefficient(JRC),and plastic shear displacement are obtained.The dilatancy behavior is described by the dilation angle,which is considered a function of JRC,plastic shear displacement,and normal stress.A cohesive-frictional elastoplastic constitutive model is hence proposed.The theoretical curves under constant normal stress conditions of the proposed model are in good agreement with the experimental results.The shear behaviors under constant normal stiffness and constant normal displacement conditions can be predicted using the new constitutive model.
文摘The configuration of underground powerhouses is crucial in pumped-storage hydropower projects,which play a vital role in maintaining grid stability,facilitating the integration of renewable energy sources,and managing flood risks.However,geotechnical challenges,such as complex joint orientations,anisotropy in in-situ stress,and rock damage caused by excavation,require thorough stability assessments.This research employs the ubiquitous anisotropic joint model within FLAC3D to investigate the effects of joint dip angle,joint dip direction,and the alignment of in-situ stress on the stability of surrounding rock formations.The key parameters analyzed include joint cohesion,friction angle,and the magnitude of in-situ stress.The numerical results indicate that deformation is minimized when the axis of the powerhouse is aligned with the major principal stress.Furthermore,joint dip angles between 65°and 70°lead to a 50%reduction in both displacement and plastic zone volume.Additionally,angles less than 40°between the joint dip direction and the powerhouse axis enhance stability.These findings provide practical recommendations for optimizing the orientation of powerhouses in geomechanical contexts similar to those characterized by foliated sericite phyllite with moderate joint persistence.
基金Major projects(50490272, 50490274) supported by the National Natural Science Foundation of China Project (2002CB412703) supported by the National Basic Research Program of China
文摘Firstly, studies on propagation of one-dimensional normally incident wave in rock mass containing no joint, a single joint and two parallel joints were conducted by Three Dimensional Distinct Element Codes(3DEC). By comparison of the modeling results with the theoretical solutions, it has been found that a good agreement between them has been achieved. It is verified that the 3DEC is capable of modeling wave propagation in rock masses. Secondly, propagation of normally incident P-wave across two parallel joints was studied. The modeling results show that transmission coefficient increases with the increasing ratio of joint spacing to wavelength at first, then decreases with the increasing ratio of joint spacing to wavelength, lastly keeps constant. Finally, effect of interlayer on wave propagation is investigated. It is shown that interlayer results in marked attenuation and leading phase, and that attenuation increases with the increasing frequency and the increasing thickness of interlayer.
基金supported by Shandong Provincial Colleges and Universities Youth Innovation Technol ogy Support Program(No.2023KJ092)Natural Science Foundation of Shandong Province(No.ZR2024ME060)Key Laboratory of Geological Safety of Coastal Urban Underground Space,Ministry of Natural Resources(No.BHKF2024Z06)。
文摘Prolonged cyclic water intrusion has progressively developed joints in the hydro-fluctuation belt,elevating the instability risk of reservoir bank slopes.To investigate its impact on joint shear damage evolution,joint samples were prepared using three representative roughness curves and subjected to direct shear testing following cyclic water intrusion.A shear damage constitutive model considering the coupling effect of cyclic water intrusion and load was developed based on macroscopic phenomenological damage mechanics and micro-statistical theory.Results indicate:(1)All critical shear mechanical parameters(including peak shear strength,shear stiffness,basic friction angle,and joint compressive strength)exhibit progressive deterioration with increasing water intrusion cycles;(2)Model validation through experimental curve comparisons confirms its reliability.The model demonstrates that intensified water intrusion cycles reduce key mechanical indices,inducing a brittle-to-ductile transition in joint surface deformation—a behavior consistent with experimental observations;(3)Damage under cyclic water intrusion and load coupling follows an S-shaped trend,divided into stabilization(water-dominated stage),development(load-dominated stage),and completion stages.The research provides valuable insights for stability studies,such as similar model experiments for reservoir bank slopes and other water-related projects.
