当前,步态识别的主流方法常依赖堆叠卷积层来逐步扩大感受野,以融合局部特征,这种方法大多采用浅层网络,在提取步态图像的全局特征时存在一定的局限性,并缺乏对时序周期特征信息的关注。因此提出一种融合Transformer和3D卷积的深层神经...当前,步态识别的主流方法常依赖堆叠卷积层来逐步扩大感受野,以融合局部特征,这种方法大多采用浅层网络,在提取步态图像的全局特征时存在一定的局限性,并缺乏对时序周期特征信息的关注。因此提出一种融合Transformer和3D卷积的深层神经网络算法(3D convolutional gait recognition network based on adaptFormer and spect-conv,3D-ASgaitNet)。首先,初始残差卷积层将二进制轮廓数据转换为浮点编码特征图,以提供密集的低级结构特征;在此基础上,光谱层通过频域和时域的联合处理增强特征提取能力,并使用伪3D残差卷积模块进一步提取高级时空特征;最后融合AdaptFormer模块,通过轻量级的下采样-上采样网络结构,以适应不同的数据分布和任务需求,提供灵活的特征变换能力。3D-ASgaitNet分别在4个公开的室内数据集(CASIA-B、OU-MVLP)、室外数据集(GREW、Gait3D)上进行,分别取得99.84%、87.83%、45.32%、72.12%的识别准确率。实验结果表明,所提出方法在CASIA-B、Gait3D数据集中的识别准确率接近SOTA性能。展开更多
Deep learning(DL)has become a crucial technique for predicting the El Niño-Southern Oscillation(ENSO)and evaluating its predictability.While various DL-based models have been developed for ENSO predictions,many f...Deep learning(DL)has become a crucial technique for predicting the El Niño-Southern Oscillation(ENSO)and evaluating its predictability.While various DL-based models have been developed for ENSO predictions,many fail to capture the coherent multivariate evolution within the coupled ocean-atmosphere system of the tropical Pacific.To address this three-dimensional(3D)limitation and represent ENSO-related ocean-atmosphere interactions more accurately,a novel this 3D multivariate prediction model was proposed based on a Transformer architecture,which incorporates a spatiotemporal self-attention mechanism.This model,named 3D-Geoformer,offers several advantages,enabling accurate ENSO predictions up to one and a half years in advance.Furthermore,an integrated gradient method was introduced into the model to identify the sources of predictability for sea surface temperature(SST)variability in the eastern equatorial Pacific.Results reveal that the 3D-Geoformer effectively captures ENSO-related precursors during the evolution of ENSO events,particularly the thermocline feedback processes and ocean temperature anomaly pathways on and off the equator.By extending DL-based ENSO predictions from one-dimensional Niño time series to 3D multivariate fields,the 3D-Geoformer represents a significant advancement in ENSO prediction.This study provides details in the model formulation,analysis procedures,sensitivity experiments,and illustrative examples,offering practical guidance for the application of the model in ENSO research.展开更多
With respect to oceanic fluid dynamics,certain models have appeared,e.g.,an extended time-dependent(3+1)-dimensional shallow water wave equation in an ocean or a river,which we investigate in this paper.Using symbolic...With respect to oceanic fluid dynamics,certain models have appeared,e.g.,an extended time-dependent(3+1)-dimensional shallow water wave equation in an ocean or a river,which we investigate in this paper.Using symbolic computation,we find out,on one hand,a set of bilinear auto-Backlund transformations,which could connect certain solutions of that equation with other solutions of that equation itself,and on the other hand,a set of similarity reductions,which could go from that equation to a known ordinary differential equation.The results in this paper depend on all the oceanic variable coefficients in that equation.展开更多
OBJECTIVES:To investigate the effect of Bushen Tongluo recipe(BSTLR, 补肾通络方) on rats with diabetic kidney disease(DKD) and to explore the underlying mechanism of action. METHODS:The rat model of DKD was establishe...OBJECTIVES:To investigate the effect of Bushen Tongluo recipe(BSTLR, 补肾通络方) on rats with diabetic kidney disease(DKD) and to explore the underlying mechanism of action. METHODS:The rat model of DKD was established, and rats were treated with different doses of BSTLR. Body weight and the levels of urinary protein, α1-microglobulin, glucose, blood urea nitrogen, creatinine, Cystatin C, superoxide dismutase, malondialdehyde, and catalase were analyzed biochemically or by enzyme-linked immunosorbent assay. The pathological damage to renal tissues was assessed by hematoxylin-eosin staining. Immunohistochemical staining was carried out to detect the expression levels of fibronectin, E-cadherin, α-smooth muscle actin, laminin, vimentin, collagen type Ⅳ in kidney tissues. Western blot analysis was conducted to analyze the expression levels of Nephrin, Desmin, Podocin, transforming growth factor-β1, mothers against decapentaplegic homolog 3(Smad3), Notch1, jagged, hairy and enhancer of split 1(Hes1) in kidney tissues, and the expression levels of maternally expressed gene 3(MEG3) and mi R-145 were measured by quantitative reverse transcription-polymerase chain reaction. Moreover, dual-luciferase reporter assay was employed to verify the binding of mi R-145 to MEG3. RESULTS:BSTLR increased the body weight of DKD rats, effectively ameliorated the renal function and pathological injury in DKD, regulated the balance of renal oxidative stress, inhibited the TGF/Notch signaling pathway, and affected the variations in the lnc RNA MEG3/mi R-145 axis. CONCLUSION:BSTLR improved oxidative stress homeostasis, inhibited the TGF/Notch signaling pathway, and regulated the lnc RNA MEG3/mi R-145 axis, effectively delaying the progression of DKD.展开更多
We present a novel method for scale-invariant 3D face recognition by integrating computer-generated holography with the Mellin transform.This approach leverages the scale-invariance property of the Mellin transform to...We present a novel method for scale-invariant 3D face recognition by integrating computer-generated holography with the Mellin transform.This approach leverages the scale-invariance property of the Mellin transform to address challenges related to variations in 3D facial sizes during recognition.By applying the Mellin transform to computer-generated holograms and performing correlation between them,which,to the best of our knowledge,is being done for the first time,we have developed a robust recognition framework capable of managing significant scale variations without compromising recognition accuracy.Digital holograms of 3D faces are generated from a face database,and the Mellin transform is employed to enable robust recognition across scale factors ranging from 0.4 to 2.0.Within this range,the method achieves 100%recognition accuracy,as confirmed by both simulation-based and hybrid optical/digital experimental validations.Numerical calculations demonstrate that our method significantly enhances the accuracy and reliability of 3D face recognition,as evidenced by the sharp correlation peaks and higher peak-to-noise ratio(PNR)values than that of using conventional holograms without the Mellin transform.Additionally,the hybrid optical/digital joint transform correlation hardware further validates the method's effectiveness,demonstrating its capability to accurately identify and distinguish 3D faces at various scales.This work provides a promising solution for advanced biometric systems,especially for those which require 3D scale-invariant recognition.展开更多
In this paper, we built upon the estimating primaries by sparse inversion （EPSI） method. We use the 3D curvelet transform and modify the EPSI method to the sparse inversion of the biconvex optimization and Ll-norm r...In this paper, we built upon the estimating primaries by sparse inversion （EPSI） method. We use the 3D curvelet transform and modify the EPSI method to the sparse inversion of the biconvex optimization and Ll-norm regularization, and use alternating optimization to directly estimate the primary reflection coefficients and source wavelet. The 3D curvelet transform is used as a sparseness constraint when inverting the primary reflection coefficients, which results in avoiding the prediction subtraction process in the surface-related multiples elimination （SRME） method. The proposed method not only reduces the damage to the effective waves but also improves the elimination of multiples. It is also a wave equation- based method for elimination of surface multiple reflections, which effectively removes surface multiples under complex submarine conditions.展开更多
激光雷达点云3D物体检测,对于小物体如行人、自行车的检测精度较低,容易漏检误检,提出一种多尺度Transformer激光雷达点云3D物体检测方法 MSPT-RCNN(multi-scale point transformer-RCNN),提高点云3D物体检测精度。该方法包含两个阶段,...激光雷达点云3D物体检测,对于小物体如行人、自行车的检测精度较低,容易漏检误检,提出一种多尺度Transformer激光雷达点云3D物体检测方法 MSPT-RCNN(multi-scale point transformer-RCNN),提高点云3D物体检测精度。该方法包含两个阶段,即第一阶段(RPN)和第二阶段(RCNN)。RPN阶段通过多尺度Transformer网络提取点云特征,该网络包含多尺度邻域嵌入模块和跳跃连接偏移注意力模块,获取多尺度邻域几何信息和不同层次全局语义信息,生成高质量初始3D包围盒;在RCNN阶段,引入包围盒内的点云多尺度邻域几何信息,优化了包围盒位置、尺寸、朝向和置信度等信息。实验结果表明,该方法(MSPT-RCNN)具有较高检测精度,特别是对于远处和较小物体,提升更高。MSPT-RCNN通过有效学习点云数据中的多尺度几何信息,提取不同层次有效的语义信息,能够有效提升3D物体检测精度。展开更多
目的因为有雨图像中雨线存在方向、密度和大小等各方面的差异,单幅图像去雨依旧是一个充满挑战的研究问题。现有算法在某些复杂图像上仍存在过度去雨或去雨不足等问题,部分复杂图像的边缘高频信息在去雨过程中被抹除,或图像中残留雨成...目的因为有雨图像中雨线存在方向、密度和大小等各方面的差异,单幅图像去雨依旧是一个充满挑战的研究问题。现有算法在某些复杂图像上仍存在过度去雨或去雨不足等问题,部分复杂图像的边缘高频信息在去雨过程中被抹除,或图像中残留雨成分。针对上述问题,本文提出三维注意力和Transformer去雨网络(three-dimension attention and Transformer deraining network,TDATDN)。方法将三维注意力机制与残差密集块结构相结合,以解决残差密集块通道高维度特征融合问题;使用Transformer计算特征全局关联性;针对去雨过程中图像高频信息被破坏和结构信息被抹除的问题,将多尺度结构相似性损失与常用图像去雨损失函数结合参与去雨网络训练。结果本文将提出的TDATDN网络在Rain12000雨线数据集上进行实验。其中,峰值信噪比(peak signal to noise ratio,PSNR)达到33.01 d B,结构相似性(structural similarity,SSIM)达到0.9278。实验结果表明,本文算法对比以往基于深度学习的神经网络去雨算法,显著改善了单幅图像去雨效果。结论本文提出的TDATDN图像去雨网络结合了3D注意力机制、Transformer和编码器—解码器架构的优点,可较好地完成单幅图像去雨工作。展开更多
By selecting any one limb of 3-RSR parallel robot as a research object, the paper establishes a position and orienta- tion relationship matrix between the moving platform and the base by means of Denavit-Hartenberg （...By selecting any one limb of 3-RSR parallel robot as a research object, the paper establishes a position and orienta- tion relationship matrix between the moving platform and the base by means of Denavit-Hartenberg （D-H） transformation matrix. The error mapping model is derived from original error to the error of the platform by using matrix differential method. This model contains all geometric original errors of the robot. The nonlinear implicit function relation between po- sition and orientation error of the platform and the original geometric errors is simplified as a linear explicit function rela- tion. The results provide a basis for further studying error analysis and error compensation.展开更多
文摘当前,步态识别的主流方法常依赖堆叠卷积层来逐步扩大感受野,以融合局部特征,这种方法大多采用浅层网络,在提取步态图像的全局特征时存在一定的局限性,并缺乏对时序周期特征信息的关注。因此提出一种融合Transformer和3D卷积的深层神经网络算法(3D convolutional gait recognition network based on adaptFormer and spect-conv,3D-ASgaitNet)。首先,初始残差卷积层将二进制轮廓数据转换为浮点编码特征图,以提供密集的低级结构特征;在此基础上,光谱层通过频域和时域的联合处理增强特征提取能力,并使用伪3D残差卷积模块进一步提取高级时空特征;最后融合AdaptFormer模块,通过轻量级的下采样-上采样网络结构,以适应不同的数据分布和任务需求,提供灵活的特征变换能力。3D-ASgaitNet分别在4个公开的室内数据集(CASIA-B、OU-MVLP)、室外数据集(GREW、Gait3D)上进行,分别取得99.84%、87.83%、45.32%、72.12%的识别准确率。实验结果表明,所提出方法在CASIA-B、Gait3D数据集中的识别准确率接近SOTA性能。
基金Supported by the Laoshan Laboratory(No.LSKJ202202402)the National Natural Science Foundation of China(No.42030410)+2 种基金the Startup Foundation for Introducing Talent of Nanjing University of Information Science&Technology,and Jiangsu Innovation Research Group(No.JSSCTD 202346)supported by the China National Postdoctoral Program for Innovative Talents(No.BX20240169)the China Postdoctoral Science Foundation(No.2141062400101)。
文摘Deep learning(DL)has become a crucial technique for predicting the El Niño-Southern Oscillation(ENSO)and evaluating its predictability.While various DL-based models have been developed for ENSO predictions,many fail to capture the coherent multivariate evolution within the coupled ocean-atmosphere system of the tropical Pacific.To address this three-dimensional(3D)limitation and represent ENSO-related ocean-atmosphere interactions more accurately,a novel this 3D multivariate prediction model was proposed based on a Transformer architecture,which incorporates a spatiotemporal self-attention mechanism.This model,named 3D-Geoformer,offers several advantages,enabling accurate ENSO predictions up to one and a half years in advance.Furthermore,an integrated gradient method was introduced into the model to identify the sources of predictability for sea surface temperature(SST)variability in the eastern equatorial Pacific.Results reveal that the 3D-Geoformer effectively captures ENSO-related precursors during the evolution of ENSO events,particularly the thermocline feedback processes and ocean temperature anomaly pathways on and off the equator.By extending DL-based ENSO predictions from one-dimensional Niño time series to 3D multivariate fields,the 3D-Geoformer represents a significant advancement in ENSO prediction.This study provides details in the model formulation,analysis procedures,sensitivity experiments,and illustrative examples,offering practical guidance for the application of the model in ENSO research.
基金financially supported by the Scientific Research Foundation of North China University of Technology(Grant Nos.11005136024XN147-87 and 110051360024XN151-86).
文摘With respect to oceanic fluid dynamics,certain models have appeared,e.g.,an extended time-dependent(3+1)-dimensional shallow water wave equation in an ocean or a river,which we investigate in this paper.Using symbolic computation,we find out,on one hand,a set of bilinear auto-Backlund transformations,which could connect certain solutions of that equation with other solutions of that equation itself,and on the other hand,a set of similarity reductions,which could go from that equation to a known ordinary differential equation.The results in this paper depend on all the oceanic variable coefficients in that equation.
文摘OBJECTIVES:To investigate the effect of Bushen Tongluo recipe(BSTLR, 补肾通络方) on rats with diabetic kidney disease(DKD) and to explore the underlying mechanism of action. METHODS:The rat model of DKD was established, and rats were treated with different doses of BSTLR. Body weight and the levels of urinary protein, α1-microglobulin, glucose, blood urea nitrogen, creatinine, Cystatin C, superoxide dismutase, malondialdehyde, and catalase were analyzed biochemically or by enzyme-linked immunosorbent assay. The pathological damage to renal tissues was assessed by hematoxylin-eosin staining. Immunohistochemical staining was carried out to detect the expression levels of fibronectin, E-cadherin, α-smooth muscle actin, laminin, vimentin, collagen type Ⅳ in kidney tissues. Western blot analysis was conducted to analyze the expression levels of Nephrin, Desmin, Podocin, transforming growth factor-β1, mothers against decapentaplegic homolog 3(Smad3), Notch1, jagged, hairy and enhancer of split 1(Hes1) in kidney tissues, and the expression levels of maternally expressed gene 3(MEG3) and mi R-145 were measured by quantitative reverse transcription-polymerase chain reaction. Moreover, dual-luciferase reporter assay was employed to verify the binding of mi R-145 to MEG3. RESULTS:BSTLR increased the body weight of DKD rats, effectively ameliorated the renal function and pathological injury in DKD, regulated the balance of renal oxidative stress, inhibited the TGF/Notch signaling pathway, and affected the variations in the lnc RNA MEG3/mi R-145 axis. CONCLUSION:BSTLR improved oxidative stress homeostasis, inhibited the TGF/Notch signaling pathway, and regulated the lnc RNA MEG3/mi R-145 axis, effectively delaying the progression of DKD.
基金financial supports from the National Natural Science Foundation of China(Grant No.6227511362405124).
文摘We present a novel method for scale-invariant 3D face recognition by integrating computer-generated holography with the Mellin transform.This approach leverages the scale-invariance property of the Mellin transform to address challenges related to variations in 3D facial sizes during recognition.By applying the Mellin transform to computer-generated holograms and performing correlation between them,which,to the best of our knowledge,is being done for the first time,we have developed a robust recognition framework capable of managing significant scale variations without compromising recognition accuracy.Digital holograms of 3D faces are generated from a face database,and the Mellin transform is employed to enable robust recognition across scale factors ranging from 0.4 to 2.0.Within this range,the method achieves 100%recognition accuracy,as confirmed by both simulation-based and hybrid optical/digital experimental validations.Numerical calculations demonstrate that our method significantly enhances the accuracy and reliability of 3D face recognition,as evidenced by the sharp correlation peaks and higher peak-to-noise ratio(PNR)values than that of using conventional holograms without the Mellin transform.Additionally,the hybrid optical/digital joint transform correlation hardware further validates the method's effectiveness,demonstrating its capability to accurately identify and distinguish 3D faces at various scales.This work provides a promising solution for advanced biometric systems,especially for those which require 3D scale-invariant recognition.
基金supported by the National Science and Technology Major Project (No.2011ZX05023-005-008)
文摘In this paper, we built upon the estimating primaries by sparse inversion （EPSI） method. We use the 3D curvelet transform and modify the EPSI method to the sparse inversion of the biconvex optimization and Ll-norm regularization, and use alternating optimization to directly estimate the primary reflection coefficients and source wavelet. The 3D curvelet transform is used as a sparseness constraint when inverting the primary reflection coefficients, which results in avoiding the prediction subtraction process in the surface-related multiples elimination （SRME） method. The proposed method not only reduces the damage to the effective waves but also improves the elimination of multiples. It is also a wave equation- based method for elimination of surface multiple reflections, which effectively removes surface multiples under complex submarine conditions.
文摘激光雷达点云3D物体检测,对于小物体如行人、自行车的检测精度较低,容易漏检误检,提出一种多尺度Transformer激光雷达点云3D物体检测方法 MSPT-RCNN(multi-scale point transformer-RCNN),提高点云3D物体检测精度。该方法包含两个阶段,即第一阶段(RPN)和第二阶段(RCNN)。RPN阶段通过多尺度Transformer网络提取点云特征,该网络包含多尺度邻域嵌入模块和跳跃连接偏移注意力模块,获取多尺度邻域几何信息和不同层次全局语义信息,生成高质量初始3D包围盒;在RCNN阶段,引入包围盒内的点云多尺度邻域几何信息,优化了包围盒位置、尺寸、朝向和置信度等信息。实验结果表明,该方法(MSPT-RCNN)具有较高检测精度,特别是对于远处和较小物体,提升更高。MSPT-RCNN通过有效学习点云数据中的多尺度几何信息,提取不同层次有效的语义信息,能够有效提升3D物体检测精度。
文摘目的因为有雨图像中雨线存在方向、密度和大小等各方面的差异,单幅图像去雨依旧是一个充满挑战的研究问题。现有算法在某些复杂图像上仍存在过度去雨或去雨不足等问题,部分复杂图像的边缘高频信息在去雨过程中被抹除,或图像中残留雨成分。针对上述问题,本文提出三维注意力和Transformer去雨网络(three-dimension attention and Transformer deraining network,TDATDN)。方法将三维注意力机制与残差密集块结构相结合,以解决残差密集块通道高维度特征融合问题;使用Transformer计算特征全局关联性;针对去雨过程中图像高频信息被破坏和结构信息被抹除的问题,将多尺度结构相似性损失与常用图像去雨损失函数结合参与去雨网络训练。结果本文将提出的TDATDN网络在Rain12000雨线数据集上进行实验。其中,峰值信噪比(peak signal to noise ratio,PSNR)达到33.01 d B,结构相似性(structural similarity,SSIM)达到0.9278。实验结果表明,本文算法对比以往基于深度学习的神经网络去雨算法,显著改善了单幅图像去雨效果。结论本文提出的TDATDN图像去雨网络结合了3D注意力机制、Transformer和编码器—解码器架构的优点,可较好地完成单幅图像去雨工作。
基金National Natural Science Foundation of China(No.51275486)the Specialized Research Fund for the Doctoral Program of Higher Education(No.20111420110005)
文摘By selecting any one limb of 3-RSR parallel robot as a research object, the paper establishes a position and orienta- tion relationship matrix between the moving platform and the base by means of Denavit-Hartenberg （D-H） transformation matrix. The error mapping model is derived from original error to the error of the platform by using matrix differential method. This model contains all geometric original errors of the robot. The nonlinear implicit function relation between po- sition and orientation error of the platform and the original geometric errors is simplified as a linear explicit function rela- tion. The results provide a basis for further studying error analysis and error compensation.
