Skeleton-based relational reasoning for group activity analysis
作者：
Highlights：
• Group activity recognition using skeletons to reason about the actors interactions.
• Novel method describes the interactions via learned relations between human joints.
• Usage of previously unexplored interactions between humans and objects.
• Leveraging of individual action information for higher quality feature learning.
• Tailored attention mechanism over relations gives more importance to key individuals.
摘要
•Group activity recognition using skeletons to reason about the actors interactions.•Novel method describes the interactions via learned relations between human joints.•Usage of previously unexplored interactions between humans and objects.•Leveraging of individual action information for higher quality feature learning.•Tailored attention mechanism over relations gives more importance to key individuals.
论文关键词：Group activity recognition,Skeleton information,Relational network,Attention mechanisms
论文评审过程：Received 26 October 2020, Revised 13 September 2021, Accepted 2 October 2021, Available online 4 October 2021, Version of Record 10 October 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.108360
