A deep generic to specific recognition model for group membership analysis using non-verbal cues

作者：

Highlights：

• Group membership can be automatically recognized using body behaviors.

• The specific model outperforms the generic model for group membership recognition.

• The deep specific model outperforms the two-phase specific model.

• The deep specific model can be trained and tested in an end-to-end manner.

摘要

•Group membership can be automatically recognized using body behaviors.•The specific model outperforms the generic model for group membership recognition.•The deep specific model outperforms the two-phase specific model.•The deep specific model can be trained and tested in an end-to-end manner.

论文关键词：Non-verbal behavior analysis,Group membership,Automatic group analysis,Deep learning

论文评审过程：Received 6 October 2017, Revised 31 May 2018, Accepted 12 September 2018, Available online 3 October 2018, Version of Record 12 February 2019.

论文官网地址：https://doi.org/10.1016/j.imavis.2018.09.005