OW-TAL: Learning Unknown Human Activities for Open-World Temporal Action Localization

Pattern Recognition（2023）

引用 2|浏览19

暂无评分

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.

查看译文

关键词

Temporal action localization,Open-world learning,Self-paced learning

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要