Entropy guided attention network for weakly-supervised action localization
作者：
Highlights：
• An EGA-Net is proposed for weakly-supervised temporal action localization, which treats background frames as out-of-domain samples.
• A novel Entropy Guided Loss is proposed to leverage entropy to distinguish action and background.
• A new Global Similarity Loss is designed to enhance action features by pushing them to approach their corresponding class centers.
• Extensive experiments are conducted on three challenging benchmarking datasets with superior results.
摘要
•An EGA-Net is proposed for weakly-supervised temporal action localization, which treats background frames as out-of-domain samples.•A novel Entropy Guided Loss is proposed to leverage entropy to distinguish action and background.•A new Global Similarity Loss is designed to enhance action features by pushing them to approach their corresponding class centers.•Extensive experiments are conducted on three challenging benchmarking datasets with superior results.
论文关键词：Temporal action localization,Weakly-supervised learning,Entropy guided loss,Global similarity loss
论文评审过程：Received 5 November 2021, Revised 7 April 2022, Accepted 17 April 2022, Available online 18 April 2022, Version of Record 25 April 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2022.108718
