Previous multi-view 3D human pose estimation methods neither correlate different human joints in each view nor model learnable correlations between the same joints in different views explicitly,meaning that skeleton s...Previous multi-view 3D human pose estimation methods neither correlate different human joints in each view nor model learnable correlations between the same joints in different views explicitly,meaning that skeleton structure information is not utilized and multi-view pose information is not completely fused.Moreover,existing graph convolutional operations do not consider the specificity of different joints and different views of pose information when processing skeleton graphs,making the correlation weights between nodes in the graph and their neighborhood nodes shared.Existing Graph Convolutional Networks(GCNs)cannot extract global and deeplevel skeleton structure information and view correlations efficiently.To solve these problems,pre-estimated multiview 2D poses are designed as a multi-view skeleton graph to fuse skeleton priors and view correlations explicitly to process occlusion problem,with the skeleton-edge and symmetry-edge representing the structure correlations between adjacent joints in each viewof skeleton graph and the view-edge representing the view correlations between the same joints in different views.To make graph convolution operation mine elaborate and sufficient skeleton structure information and view correlations,different correlation weights are assigned to different categories of neighborhood nodes and further assigned to each node in the graph.Based on the graph convolution operation proposed above,a Residual Graph Convolution(RGC)module is designed as the basic module to be combined with the simplified Hourglass architecture to construct the Hourglass-GCN as our 3D pose estimation network.Hourglass-GCNwith a symmetrical and concise architecture processes three scales ofmulti-viewskeleton graphs to extract local-to-global scale and shallow-to-deep level skeleton features efficiently.Experimental results on common large 3D pose dataset Human3.6M and MPI-INF-3DHP show that Hourglass-GCN outperforms some excellent methods in 3D pose estimation accuracy.展开更多
In recent years,semantic segmentation on 3D point cloud data has attracted much attention.Unlike 2D images where pixels distribute regularly in the image domain,3D point clouds in non-Euclidean space are irregular and...In recent years,semantic segmentation on 3D point cloud data has attracted much attention.Unlike 2D images where pixels distribute regularly in the image domain,3D point clouds in non-Euclidean space are irregular and inherently sparse.Therefore,it is very difficult to extract long-range contexts and effectively aggregate local features for semantic segmentation in 3D point cloud space.Most current methods either focus on local feature aggregation or long-range context dependency,but fail to directly establish a global-local feature extractor to complete the point cloud semantic segmentation tasks.In this paper,we propose a Transformer-based stratified graph convolutional network(SGT-Net),which enlarges the effective receptive field and builds direct long-range dependency.Specifically,we first propose a novel dense-sparse sampling strategy that provides dense local vertices and sparse long-distance vertices for subsequent graph convolutional network(GCN).Secondly,we propose a multi-key self-attention mechanism based on the Transformer to further weight augmentation for crucial neighboring relationships and enlarge the effective receptive field.In addition,to further improve the efficiency of the network,we propose a similarity measurement module to determine whether the neighborhood near the center point is effective.We demonstrate the validity and superiority of our method on the S3DIS and ShapeNet datasets.Through ablation experiments and segmentation visualization,we verify that the SGT model can improve the performance of the point cloud semantic segmentation.展开更多
Accurate tumor segmentation from brain tissues in Magnetic Resonance Imaging(MRI)imaging is crucial in the pre-surgical planning of brain tumor malignancy.MRI images’heterogeneous intensity and fuzzy boundaries make ...Accurate tumor segmentation from brain tissues in Magnetic Resonance Imaging(MRI)imaging is crucial in the pre-surgical planning of brain tumor malignancy.MRI images’heterogeneous intensity and fuzzy boundaries make brain tumor segmentation challenging.Furthermore,recent studies have yet to fully employ MRI sequences’considerable and supplementary information,which offers critical a priori knowledge.This paper proposes a clinical knowledge-based hybrid Swin Transformermultimodal brain tumor segmentation algorithmbased on how experts identify malignancies from MRI images.During the encoder phase,a dual backbone network with a Swin Transformer backbone to capture long dependencies from 3D MR images and a Convolutional Neural Network(CNN)-based backbone to represent local features have been constructed.Instead of directly connecting all the MRI sequences,the proposed method re-organizes them and splits them into two groups based on MRI principles and characteristics:T1 and T1ce,T2 and Flair.These aggregated images are received by the dual-stem Swin Transformer-based encoder branch,and the multimodal sequence-interacted cross-attention module(MScAM)captures the interactive information between two sets of linked modalities in each stage.In the CNN-based encoder branch,a triple down-sampling module(TDsM)has been proposed to balance the performance while downsampling.In the final stage of the encoder,the feature maps acquired from two branches are concatenated as input to the decoder,which is constrained by MScAM outputs.The proposed method has been evaluated on datasets from the MICCAI BraTS2021 Challenge.The results of the experiments demonstrate that the method algorithm can precisely segment brain tumors,especially the portions within tumors.展开更多
Autonomous navigation is a fundamental problem in robotics.Traditional methods generally build point cloud map or dense feature map in perceptual space;due to lack of cognition and memory formation mechanism,tradition...Autonomous navigation is a fundamental problem in robotics.Traditional methods generally build point cloud map or dense feature map in perceptual space;due to lack of cognition and memory formation mechanism,traditional methods exist poor robustness and low cognitive ability.As a new navigation technology that draws inspiration from mammal’s navigation,bionic navigation method can map perceptual information into cognitive space,and have strong autonomy and environment adaptability.To improve the robot’s autonomous navigation ability,this paper proposes a cognitive map-based hierarchical navigation method.First,the mammals’navigation-related grid cells and head direction cells are modeled to provide the robots with location cognition.And then a global path planning strategy based on cognitive map is proposed,which can anticipate one preferred global path to the target with high efficiency and short distance.Moreover,a hierarchical motion controlling method is proposed,with which the target navigation can be divided into several sub-target navigation,and the mobile robot can reach to these sub-targets with high confidence level.Finally,some experiments are implemented,the results show that the proposed path planning method can avoid passing through obstacles and obtain one preferred global path to the target with high efficiency,and the time cost does not increase extremely with the increase of experience nodes number.The motion controlling results show that the mobile robot can arrive at the target successfully only depending on its self-motion information,which is an effective attempt and reflects strong bionic properties.展开更多
tRNA-derived small RNAs(tsRNAs)are novel non-coding RNAs that are involved in the occurrence and progression of diverse diseases.However,their exact presence and function in hepatocellular carcinoma(HCC)remain unclear...tRNA-derived small RNAs(tsRNAs)are novel non-coding RNAs that are involved in the occurrence and progression of diverse diseases.However,their exact presence and function in hepatocellular carcinoma(HCC)remain unclear.Here,differentially expressed tsRNAs in HCC were profiled.A novel tsRNA,tRNAGln-TTG derived 5′-tiRNA-Gln,is significantly downregulated,and its expression level is correlated with progression in patients.In HCC cells,5′-tiRNA-Gln overexpression impaired the proliferation,migration,and invasion in vitro and in vivo,while 5′-tiRNA-Gln knockdown yielded opposite results.5′-tiRNA-Gln exerted its function by binding eukaryotic initiation factor 4A-I(EIF4A1),which unwinds complex RNA secondary structures during translation initiation,causing the partial inhibition of translation.The suppressed downregulated proteins include ARAF,MEK1/2 and STAT3,causing the impaired signaling pathway related to HCC progression.Furthermore,based on the construction of a mutant 5′-tiRNA-Gln,the sequence of forming intramolecular G-quadruplex structure is crucial for 5′-tiRNA-Gln to strongly bind EIF4A1 and repress translation.Clinically,5′-tiRNA-Gln expression level is negatively correlated with ARAF,MEK1/2,and STAT3 in HCC tissues.Collectively,these findings reveal that 5′-tiRNA-Gln interacts with EIF4A1 to reduce related mRNA binding through the intramolecular Gquadruplex structure,and this process partially inhibits translation and HCC progression.展开更多
基金supported in part by the National Natural Science Foundation of China under Grants 61973065,U20A20197,61973063.
文摘Previous multi-view 3D human pose estimation methods neither correlate different human joints in each view nor model learnable correlations between the same joints in different views explicitly,meaning that skeleton structure information is not utilized and multi-view pose information is not completely fused.Moreover,existing graph convolutional operations do not consider the specificity of different joints and different views of pose information when processing skeleton graphs,making the correlation weights between nodes in the graph and their neighborhood nodes shared.Existing Graph Convolutional Networks(GCNs)cannot extract global and deeplevel skeleton structure information and view correlations efficiently.To solve these problems,pre-estimated multiview 2D poses are designed as a multi-view skeleton graph to fuse skeleton priors and view correlations explicitly to process occlusion problem,with the skeleton-edge and symmetry-edge representing the structure correlations between adjacent joints in each viewof skeleton graph and the view-edge representing the view correlations between the same joints in different views.To make graph convolution operation mine elaborate and sufficient skeleton structure information and view correlations,different correlation weights are assigned to different categories of neighborhood nodes and further assigned to each node in the graph.Based on the graph convolution operation proposed above,a Residual Graph Convolution(RGC)module is designed as the basic module to be combined with the simplified Hourglass architecture to construct the Hourglass-GCN as our 3D pose estimation network.Hourglass-GCNwith a symmetrical and concise architecture processes three scales ofmulti-viewskeleton graphs to extract local-to-global scale and shallow-to-deep level skeleton features efficiently.Experimental results on common large 3D pose dataset Human3.6M and MPI-INF-3DHP show that Hourglass-GCN outperforms some excellent methods in 3D pose estimation accuracy.
基金supported in part by the National Natural Science Foundation of China under Grant Nos.U20A20197,62306187the Foundation of Ministry of Industry and Information Technology TC220H05X-04.
文摘In recent years,semantic segmentation on 3D point cloud data has attracted much attention.Unlike 2D images where pixels distribute regularly in the image domain,3D point clouds in non-Euclidean space are irregular and inherently sparse.Therefore,it is very difficult to extract long-range contexts and effectively aggregate local features for semantic segmentation in 3D point cloud space.Most current methods either focus on local feature aggregation or long-range context dependency,but fail to directly establish a global-local feature extractor to complete the point cloud semantic segmentation tasks.In this paper,we propose a Transformer-based stratified graph convolutional network(SGT-Net),which enlarges the effective receptive field and builds direct long-range dependency.Specifically,we first propose a novel dense-sparse sampling strategy that provides dense local vertices and sparse long-distance vertices for subsequent graph convolutional network(GCN).Secondly,we propose a multi-key self-attention mechanism based on the Transformer to further weight augmentation for crucial neighboring relationships and enlarge the effective receptive field.In addition,to further improve the efficiency of the network,we propose a similarity measurement module to determine whether the neighborhood near the center point is effective.We demonstrate the validity and superiority of our method on the S3DIS and ShapeNet datasets.Through ablation experiments and segmentation visualization,we verify that the SGT model can improve the performance of the point cloud semantic segmentation.
基金supported in part by the National Natural Science Foundation of China under Grant No.U20A20197Liaoning Key Research and Development Project 2020JH2/10100040+1 种基金Natural Science Foundation of Liaoning Province 2021-KF-12-01the Foundation of National Key Laboratory OEIP-O-202005.
文摘Accurate tumor segmentation from brain tissues in Magnetic Resonance Imaging(MRI)imaging is crucial in the pre-surgical planning of brain tumor malignancy.MRI images’heterogeneous intensity and fuzzy boundaries make brain tumor segmentation challenging.Furthermore,recent studies have yet to fully employ MRI sequences’considerable and supplementary information,which offers critical a priori knowledge.This paper proposes a clinical knowledge-based hybrid Swin Transformermultimodal brain tumor segmentation algorithmbased on how experts identify malignancies from MRI images.During the encoder phase,a dual backbone network with a Swin Transformer backbone to capture long dependencies from 3D MR images and a Convolutional Neural Network(CNN)-based backbone to represent local features have been constructed.Instead of directly connecting all the MRI sequences,the proposed method re-organizes them and splits them into two groups based on MRI principles and characteristics:T1 and T1ce,T2 and Flair.These aggregated images are received by the dual-stem Swin Transformer-based encoder branch,and the multimodal sequence-interacted cross-attention module(MScAM)captures the interactive information between two sets of linked modalities in each stage.In the CNN-based encoder branch,a triple down-sampling module(TDsM)has been proposed to balance the performance while downsampling.In the final stage of the encoder,the feature maps acquired from two branches are concatenated as input to the decoder,which is constrained by MScAM outputs.The proposed method has been evaluated on datasets from the MICCAI BraTS2021 Challenge.The results of the experiments demonstrate that the method algorithm can precisely segment brain tumors,especially the portions within tumors.
基金funded by the National Natural Science Foundation of China-Liaoning Joint Fund(Grants:U20A20197)the National Natural Science Foundation of China(Grants:62173064)the Fundamental Research Funds for the Central Universities(Grants:N2326005).
文摘Autonomous navigation is a fundamental problem in robotics.Traditional methods generally build point cloud map or dense feature map in perceptual space;due to lack of cognition and memory formation mechanism,traditional methods exist poor robustness and low cognitive ability.As a new navigation technology that draws inspiration from mammal’s navigation,bionic navigation method can map perceptual information into cognitive space,and have strong autonomy and environment adaptability.To improve the robot’s autonomous navigation ability,this paper proposes a cognitive map-based hierarchical navigation method.First,the mammals’navigation-related grid cells and head direction cells are modeled to provide the robots with location cognition.And then a global path planning strategy based on cognitive map is proposed,which can anticipate one preferred global path to the target with high efficiency and short distance.Moreover,a hierarchical motion controlling method is proposed,with which the target navigation can be divided into several sub-target navigation,and the mobile robot can reach to these sub-targets with high confidence level.Finally,some experiments are implemented,the results show that the proposed path planning method can avoid passing through obstacles and obtain one preferred global path to the target with high efficiency,and the time cost does not increase extremely with the increase of experience nodes number.The motion controlling results show that the mobile robot can arrive at the target successfully only depending on its self-motion information,which is an effective attempt and reflects strong bionic properties.
基金generously supported by the National Natural Science Foundation of China(Nos.82072650 and 81902405)Key Research and Development Program of Zhejiang Province(No.2021C03121)+1 种基金2019 Liver Cancer Diagnosis and Treatment Communication Fund(No.CXPJJH11900009-12)Grant from Health Commission of Zhejiang Province(No.JBZX-202004).
文摘tRNA-derived small RNAs(tsRNAs)are novel non-coding RNAs that are involved in the occurrence and progression of diverse diseases.However,their exact presence and function in hepatocellular carcinoma(HCC)remain unclear.Here,differentially expressed tsRNAs in HCC were profiled.A novel tsRNA,tRNAGln-TTG derived 5′-tiRNA-Gln,is significantly downregulated,and its expression level is correlated with progression in patients.In HCC cells,5′-tiRNA-Gln overexpression impaired the proliferation,migration,and invasion in vitro and in vivo,while 5′-tiRNA-Gln knockdown yielded opposite results.5′-tiRNA-Gln exerted its function by binding eukaryotic initiation factor 4A-I(EIF4A1),which unwinds complex RNA secondary structures during translation initiation,causing the partial inhibition of translation.The suppressed downregulated proteins include ARAF,MEK1/2 and STAT3,causing the impaired signaling pathway related to HCC progression.Furthermore,based on the construction of a mutant 5′-tiRNA-Gln,the sequence of forming intramolecular G-quadruplex structure is crucial for 5′-tiRNA-Gln to strongly bind EIF4A1 and repress translation.Clinically,5′-tiRNA-Gln expression level is negatively correlated with ARAF,MEK1/2,and STAT3 in HCC tissues.Collectively,these findings reveal that 5′-tiRNA-Gln interacts with EIF4A1 to reduce related mRNA binding through the intramolecular Gquadruplex structure,and this process partially inhibits translation and HCC progression.
