Using temporal information for recognizing actions from still images

作者：

Highlights：

• We propose to use temporal information to improve still image action recognition.

• We formulate this problem as a novel transfer learning problem.

• We propose a new still image action dataset with a corresponding video dataset to evaluate T2SIL.

• We propose three transfer learning solutions and show while adversarial feature generation is not helpful for T2SIL, improvements can be attained with deep embedding learning and TSN frameworks.

摘要

•We propose to use temporal information to improve still image action recognition.•We formulate this problem as a novel transfer learning problem.•We propose a new still image action dataset with a corresponding video dataset to evaluate T2SIL.•We propose three transfer learning solutions and show while adversarial feature generation is not helpful for T2SIL, improvements can be attained with deep embedding learning and TSN frameworks.

论文关键词：Still image action recognition,Two-stream,Optical-flow,Dynamic-images

论文评审过程：Received 31 October 2018, Revised 14 July 2019, Accepted 31 July 2019, Available online 31 July 2019, Version of Record 8 August 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.106989