A novel online action detection framework from untrimmed video streams

作者：

Highlights：

• In this paper, we address an online action detection problem.

• This is challenging since a limited amount of information is available.

• Future frame generation network is proposed to overcome this limitation.

• Video data augmentation method is also exploited to resolve temporal variation.

摘要

•In this paper, we address an online action detection problem.•This is challenging since a limited amount of information is available.•Future frame generation network is proposed to overcome this limitation.•Video data augmentation method is also exploited to resolve temporal variation.

论文关键词：Online action detection,Untrimmed video stream,Future frame generation,3D convolutional neural network,Long short-term memory

论文评审过程：Received 3 June 2018, Revised 9 March 2020, Accepted 25 April 2020, Available online 14 May 2020, Version of Record 14 May 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107396