典型文献
Video-based body geometric aware network for 3D hu-man pose estimation
文献摘要：
Three-dimensional human pose estimation(3D HPE)has broad application prospects in the fields of trajectory predic-tion,posture tracking and action analysis.However,the frequent self-occlusions and the substantial depth ambiguity in two-dimensional(2D)representations hinder the further improvement of accuracy.In this paper,we propose a novel video-based human body geometric aware network to mitigate the above problems.Our network can implicitly be aware of the geometric constraints of the human body by capturing spatial and temporal context information from 2D skeleton data.Specifically,a novel skeleton attention(SA)mechanism is proposed to model geometric context de-pendencies among different body joints,thereby improving the spatial feature representation ability of the network.To enhance the temporal consistency,a novel multilayer perceptron(MLP)-Mixer based structure is exploited to compre-hensively learn temporal context information from input sequences.We conduct experiments on publicly available challenging datasets to evaluate the proposed approach.The results outperform the previous best approach by 0.5 mm in the Human3.6m dataset.It also demonstrates significant improvements in HumanEva-I dataset.
文献关键词：
中图分类号：
作者姓名：
LI Chaonan;LIU Sheng;YAO Lu;ZOU Siyu
作者机构：
College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310023,China
文献出处：
引用格式：
[1]LI Chaonan;LIU Sheng;YAO Lu;ZOU Siyu-.Video-based body geometric aware network for 3D hu-man pose estimation)[J].光电子快报（英文版）,2022(05):313-320
A类：
pendencies,Mixer,HumanEva
B类：
Video,body,geometric,aware,network,estimation,Three,dimensional,human,HPE,has,broad,application,prospects,fields,trajectory,predic,posture,tracking,action,analysis,However,frequent,self,occlusions,substantial,depth,ambiguity,2D,representations,hinder,further,accuracy,In,this,paper,novel,video,mitigate,above,problems,Our,implicitly,constraints,capturing,spatial,temporal,context,information,from,skeleton,Specifically,attention,SA,mechanism,proposed,model,among,different,joints,thereby,improving,feature,ability,To,enhance,consistency,multilayer,perceptron,MLP,structure,exploited,compre,hensively,learn,input,sequences,We,conduct,experiments,publicly,available,challenging,datasets,evaluate,approach,results,outperform,previous,best,Human3,6m,It,also,demonstrates,significant,improvements
AB值：
0.597456
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
