OW-TAL: Learning Unknown Human Activities for Open-World Temporal Action Localization
作者：
Highlights：
• Develop a two-branch framework for open-world temporal action localization.
• Design a unified UK-Net to model unknown and known actions.
• Employ self-paced learning strategy to guide class-incremental learning.
摘要
•Develop a two-branch framework for open-world temporal action localization.•Design a unified UK-Net to model unknown and known actions.•Employ self-paced learning strategy to guide class-incremental learning.
论文关键词：Temporal action localization,Open-world learning,Self-paced learning
论文评审过程：Received 29 January 2022, Revised 28 August 2022, Accepted 4 September 2022, Available online 7 September 2022, Version of Record 11 September 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2022.109027
