Supported on available paleomagnetic data,a new Columbia(Nuna)supercontinent reconstruction is proposed based on matching U-Pb-dated 1.79-1.75 Ga Large Igneous Province(LIP)mafic unit fragments and particularly on lin...Supported on available paleomagnetic data,a new Columbia(Nuna)supercontinent reconstruction is proposed based on matching U-Pb-dated 1.79-1.75 Ga Large Igneous Province(LIP)mafic unit fragments and particularly on linking their dykes into radiating systems.Information from the literature is augmented with the herein dated 1762 Ma(U-Pb)Januária dyke swarm from the São Francisco Craton(Brazil).展开更多
Three-dimensional skeleton-based action recognition(3D SAR)has gained important attention within the computer vision community,owing to the inherent advantages offered by skeleton data.As a result,a plethora of impres...Three-dimensional skeleton-based action recognition(3D SAR)has gained important attention within the computer vision community,owing to the inherent advantages offered by skeleton data.As a result,a plethora of impressive works,including those based on conventional handcrafted features and learned feature extraction methods,have been conducted over the years.However,prior surveys on action recognition have primarily focused on video or red-green-blue(RGB)data-dominated approaches,with limited coverage of reviews related to skeleton data.Furthermore,despite the extensive application of deep learning methods in this field,there has been a notable absence of research that provides an introductory or comprehensive review from the perspective of deep learning architectures.To address these limitations,this survey first underscores the importance of action recognition and emphasizes the significance of 3-dimensional(3D)skeleton data as a valuable modality.Subsequently,we provide a comprehensive introduction to mainstream action recognition techniques based on 4 fundamental deep architectures,i.e.,recurrent neural networks,convolutional neural networks,graph convolutional network,and Transformers.All methods with the corresponding architectures are then presented in a data-driven manner with detailed discussion.Finally,we offer insights into the current largest 3D skeleton dataset,NTU-RGB+D,and its new edition,NTU-RGB+D 120,along with an overview of several top-performing algorithms on these datasets.To the best of our knowledge,this research represents the first comprehensive discussion of deep learning-based action recognition using 3D skeleton data.展开更多
基金support of the Brazilian National Council for Scientific and Technological Development(CNPq).
文摘Supported on available paleomagnetic data,a new Columbia(Nuna)supercontinent reconstruction is proposed based on matching U-Pb-dated 1.79-1.75 Ga Large Igneous Province(LIP)mafic unit fragments and particularly on linking their dykes into radiating systems.Information from the literature is augmented with the herein dated 1762 Ma(U-Pb)Januária dyke swarm from the São Francisco Craton(Brazil).
基金supported by the National Natural Science Foundation of China(No.62203476)the Natural Science Foundation of Shenzhen(No.JCYJ20230807120801002).
文摘Three-dimensional skeleton-based action recognition(3D SAR)has gained important attention within the computer vision community,owing to the inherent advantages offered by skeleton data.As a result,a plethora of impressive works,including those based on conventional handcrafted features and learned feature extraction methods,have been conducted over the years.However,prior surveys on action recognition have primarily focused on video or red-green-blue(RGB)data-dominated approaches,with limited coverage of reviews related to skeleton data.Furthermore,despite the extensive application of deep learning methods in this field,there has been a notable absence of research that provides an introductory or comprehensive review from the perspective of deep learning architectures.To address these limitations,this survey first underscores the importance of action recognition and emphasizes the significance of 3-dimensional(3D)skeleton data as a valuable modality.Subsequently,we provide a comprehensive introduction to mainstream action recognition techniques based on 4 fundamental deep architectures,i.e.,recurrent neural networks,convolutional neural networks,graph convolutional network,and Transformers.All methods with the corresponding architectures are then presented in a data-driven manner with detailed discussion.Finally,we offer insights into the current largest 3D skeleton dataset,NTU-RGB+D,and its new edition,NTU-RGB+D 120,along with an overview of several top-performing algorithms on these datasets.To the best of our knowledge,this research represents the first comprehensive discussion of deep learning-based action recognition using 3D skeleton data.
