Research on Human Pose Estimation Based on Improved ConvNeXt V2
WANG Jiaxiang
HE Liwen
Abstract：Human pose estimation typically involves detecting the joint positions and poses of the human body in an image.However,factors such as occlusion,complex textures,and changes in lighting make feature extraction difficult,making human pose estimation a challenging problem.In this paper,an improved ConvNeXt V2-based human pose estimation algorithm is pro-posed.A standard large-kernel convolution is decomposed into three convolutions,which are depthwise convolution(DW-Conv),depthwise dilation convolution(DW-D-Conv),and 1x1 channel convolution(1x1 Conv).Without changing the receptive field,this approach not only reduces computational complexity but also captures long-distance interdependent features.Additionally,by incorporating attention mechanisms into the network,this paper achieves adaptive spatial and channel dimensions,thereby improv-ing the network's feature extraction capabilities.Finally,experimental results demonstrate that the improved ConvNeXt V2 network outperforms the original ConvNeXt V2 network and other networks in human pose estimation to a certain degree.
Keywords：human pose estimationconvolutional neural networkattention mechanism
Publication Date：2025-12-20
Online Publishing Date：2026-03-09(First online date of this platform, not the publication date of the document)
Pages：5( 3540-3544 )