利用多焦点空间注意力进行口罩人脸识别的定位（英文版）

英文标题：Localization using Multi-Focal Spatial Attention for Masked Face Recognition中文摘要：本文提出的口罩人脸识别方法 (CAL and MFSA) 通过训练补充空间注意力集中于口罩区域和背景区域，并提取掩蔽不变特征的方式，在不影响传统人脸识别性能的前提下，提高了口罩人脸识别的准确性。英文摘要：Since the beginning of world-wide COVID-19 pandemic, facial masks have beenrecommended to limit the spread of the disease. However, these masks hidecertain facial attributes. Hence, it has become difficult for existing facerecognition systems to perform identity verification on masked faces. In thiscontext, it