Effective actor-centric human-object interaction detection

作者：

Highlights：

• We propose a novel actor-centric HOI detection framework to explore the relationships between one human and multiple objects.

• We formulate the HOI detection task as a pixel-wise classification problem in a one-stage-like procedure.

• We present an RGBM Generator to provide the actor-centric guidance and get the final prediction by scoremap indexing.

• Both quantitative and qualitative results prove the superiority of our method, especially for complex images.

摘要

•We propose a novel actor-centric HOI detection framework to explore the relationships between one human and multiple objects.•We formulate the HOI detection task as a pixel-wise classification problem in a one-stage-like procedure.•We present an RGBM Generator to provide the actor-centric guidance and get the final prediction by scoremap indexing.•Both quantitative and qualitative results prove the superiority of our method, especially for complex images.

论文关键词：Human-object interaction detection,Global context utilizing,Pixel-wise prediction,Deep learning

论文评审过程：Received 25 December 2021, Accepted 19 February 2022, Available online 25 February 2022, Version of Record 8 March 2022.

论文官网地址：https://doi.org/10.1016/j.imavis.2022.104422