Temporal filtering networks for online action detection

作者：

Highlights：

• We propose a new approach, named Temporal Filtering Network (TFN), to boost the performance of online action detection by distinguishing between relevant and irrelevant temporal information.

• We simply implement TFN by introducing a filtering module without complex architectures.

• We perform extensive experiments on two benchmark datasets, where our TFN outperforms state-of-the-art methods by a large margin.

• We demonstrate the effectiveness and potential of our filtering modules by conducting comprehensive ablation studies.

摘要

•We propose a new approach, named Temporal Filtering Network (TFN), to boost the performance of online action detection by distinguishing between relevant and irrelevant temporal information.•We simply implement TFN by introducing a filtering module without complex architectures.•We perform extensive experiments on two benchmark datasets, where our TFN outperforms state-of-the-art methods by a large margin.•We demonstrate the effectiveness and potential of our filtering modules by conducting comprehensive ablation studies.

论文关键词：Online action detection,Temporal filtering networks,Filter modules,TFN

论文评审过程：Received 20 November 2019, Revised 25 September 2020, Accepted 7 October 2020, Available online 10 October 2020, Version of Record 17 October 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107695