Multi-scale single-stage pose detection with adaptive sample training in the classroom scene

作者：

Highlights：

• An efficient and effective single-stage pose detection method is proposed.

• Adaptive positive sample training strategy is proposed to improve the performance.

• Experimental results verify the effectiveness of our method.

摘要

•An efficient and effective single-stage pose detection method is proposed.•Adaptive positive sample training strategy is proposed to improve the performance.•Experimental results verify the effectiveness of our method.

论文关键词：Pose detection,Object detection,Classroom scene

论文评审过程：Received 29 October 2020, Revised 25 March 2021, Accepted 29 March 2021, Available online 31 March 2021, Version of Record 12 April 2021.

论文官网地址：https://doi.org/10.1016/j.knosys.2021.107008