Discriminative context learning with gated recurrent unit for group activity recognition

作者：

Highlights：

• A novel feature DGCF to represent context information of group activity is proposed and used as input to GRU for sequence modeling.

• A data augmentation method for trajectory data to reduce overfitting problem in neural network is proposed.

• Superior performance by using the proposed DGCF and data augmentation method.

摘要

•A novel feature DGCF to represent context information of group activity is proposed and used as input to GRU for sequence modeling.•A data augmentation method for trajectory data to reduce overfitting problem in neural network is proposed.•Superior performance by using the proposed DGCF and data augmentation method.

论文关键词：Group activity recognition,Sequence modeling,Recurrent neural network,Gated recurrent unit,Data augmentation,Video surveillance

论文评审过程：Received 24 March 2017, Revised 16 October 2017, Accepted 30 October 2017, Available online 31 October 2017, Version of Record 7 November 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.10.037