Three-stream fusion network for first-person interaction recognition

作者：

Highlights：

• We propose a novel three-stream framework for first-person interaction recognition.

• The three-stream correlation fusion can consider correlations between a target and a camera wearer.

• Superior performance by using the proposed three-stream architecture with the fusion method.

摘要

•We propose a novel three-stream framework for first-person interaction recognition.•The three-stream correlation fusion can consider correlations between a target and a camera wearer.•Superior performance by using the proposed three-stream architecture with the fusion method.

论文关键词：First-person vision,First-person interaction recognition,Three-stream fusion network,Three-stream correlation fusion,Camera ego-motion

论文评审过程：Received 3 March 2019, Revised 13 October 2019, Accepted 13 February 2020, Available online 18 February 2020, Version of Record 24 February 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107279