An adversarial human pose estimation network injected with graph structure

作者：

Highlights：

• We inject the graph structure into a GAN-based human pose estimation model to capture the relationship of body joints.

• Because the graph based discriminator is not needed during testing, the complexity of our pose estimation model does not increase.

• Experimental results on three public benchmark datasets show the effectiveness of our method.

摘要

•We inject the graph structure into a GAN-based human pose estimation model to capture the relationship of body joints.•Because the graph based discriminator is not needed during testing, the complexity of our pose estimation model does not increase.•Experimental results on three public benchmark datasets show the effectiveness of our method.

论文关键词：Human pose estimation,Cascade feature network,Graph structure network,Generative adversarial network

论文评审过程：Received 31 March 2020, Revised 15 October 2020, Accepted 22 January 2021, Available online 9 February 2021, Version of Record 18 February 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.107863