Effective action recognition with embedded key point shifts

作者：

Highlights：

• A new module utilizing embedded key point shifts for efficient action recognition.

• KPSEM extracts and embeds regional key point shifts from high-level feature maps.

• Network with KPSEM achieves state-of-the-art performance on benchmark datasets.

摘要

•A new module utilizing embedded key point shifts for efficient action recognition.•KPSEM extracts and embeds regional key point shifts from high-level feature maps.•Network with KPSEM achieves state-of-the-art performance on benchmark datasets.

论文关键词：Action recognition,Temporal feature,Key point shifts

论文评审过程：Received 25 August 2020, Revised 5 June 2021, Accepted 6 July 2021, Available online 18 July 2021, Version of Record 24 July 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108172