Bidirectional Long Short-Term Memory with Temporal Dense Sampling for human action recognition

作者：

Highlights：

• Temporal dense sampling to extract significant activations in temporal axis.

• Multi-stream bidirectional LSTM to encode spatial and temporal dependencies.

• Fusion network to adaptively assign weight for each stream.

摘要

•Temporal dense sampling to extract significant activations in temporal axis.•Multi-stream bidirectional LSTM to encode spatial and temporal dependencies.•Fusion network to adaptively assign weight for each stream.

论文关键词：Human action recognition,Bidirectional LSTM,Temporal Dense Sampling

论文评审过程：Received 17 March 2021, Revised 31 May 2021, Accepted 7 August 2022, Available online 12 August 2022, Version of Record 17 August 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118484