A real-time and unsupervised face Re-Identification system for Human-Robot Interaction.

Pattern Recognition Letters(2019)

引用 25|浏览57
暂无评分
摘要
•An effective and unsupervised face Re-ID system for HRI is present.•It achieves 93.55% accuracy on the TERESA dataset and 90.41% on YTF dataset.•It achieves real-time performance at 10–26 Frames per Second.•It has been integrated into the HCI^2 Framework for the TERESA robot.
更多
查看译文
关键词
Real-time face re-identification,Open set re-ID,Multiple re-ID,Human-robot interaction,CNN descriptors,Online clustering
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